CN107016363B - Bill image management device, bill image management system, and bill image management method - Google Patents
Bill image management device, bill image management system, and bill image management method Download PDFInfo
- Publication number
- CN107016363B CN107016363B CN201710203940.4A CN201710203940A CN107016363B CN 107016363 B CN107016363 B CN 107016363B CN 201710203940 A CN201710203940 A CN 201710203940A CN 107016363 B CN107016363 B CN 107016363B
- Authority
- CN
- China
- Prior art keywords
- image
- bill
- scanning
- basic
- scanned
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Image Analysis (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The invention provides a bill image management device, a bill image management system including the bill image management device, and a bill image management method. The invention provides a bill image management device, comprising: a first scanning acquisition unit; a second scanning acquisition unit; a basic image discrimination unit for discriminating each basic sheet image in the first scanned image; a basic image position determining part for obtaining the corresponding image position according to the identified basic note image; a conventional image intercepting part which intercepts the corresponding conventional bill image from the second scanning image according to the image position; and a regular image storage part for storing regular bill images, wherein the first scanning preset parameters at least comprise a first scanning density value, the second scanning preset parameters at least comprise a second scanning density value, and the first scanning density value is larger than the second scanning density value.
Description
Technical Field
The present invention relates to a sheet image management apparatus, a sheet image management system including the sheet image management apparatus, and a sheet image management method.
Background
Under the trend of financial electronization, information technology means has become a new business growth point in the financial industry, and the informatization for quickly, accurately and efficiently realizing daily business has become an increasingly urgent business requirement of financial units such as banks and the like. In order to realize electronic storage of a large number of paper archives with various types, works such as document scanning, data entry, manual proofreading and the like are required. Traditional manual entry mode, the user need invest in a large amount of human costs and time cost, has not only raised the operation cost, enters the speed and is difficult to promote moreover, and the error rate is difficult to reduce, brings many negative effects to improving business processing ageing, promotion enterprise service quality.
In addition, manual document building and manual inquiry are needed for each bill, so that the labor intensity is high, errors are easy to occur, and the efficiency and the service quality are low; and the bills lack of backup, such as the irretrievable loss caused by flood, fire or insect and mouse bites; moreover, the bill can not be transmitted by modern network electronic transmission, and the financial requirement of increasingly fast pace can not be met. Therefore, the management of the electronic bill takes place.
However, when recording bills at present, two modes of shooting by a camera or scanning by a scanner are mainly used. However, the following disadvantages still exist in the two ways:
1. the efficiency is low, and because batch processing cannot be carried out, shooting or scanning must be carried out one by one;
2. the obtained bill image is not equal in size to the original bill (the A4 or A5 size is always fixed), and the effective pixel of the obtained bill image is low;
3. because the bill is light and thin, the bill is easy to be placed incorrectly, the acquired bill image is possibly askew, and the probability of misidentification and rejection is increased in the subsequent text recognition.
Disclosure of Invention
The present invention has been made to solve the above-described problems, and an object thereof is to provide a sheet image management apparatus, a sheet image management system including the sheet image management apparatus, and a sheet image management method.
In order to achieve the purpose, the invention adopts the following structure:
< Structure 1>
The present invention provides a bill image management apparatus having such a feature that it comprises: a first scanning acquisition unit that performs a first scan on a plurality of bills placed at the same time based on a first predetermined scanning parameter to acquire a first scan image including each of the bill images of the plurality of bills as a basic bill image; the second scanning acquisition part is used for carrying out second scanning on the plurality of bills according to second preset scanning parameters so as to acquire second scanning images which take each bill image containing the plurality of bills as a conventional bill image; a basic image discrimination unit for discriminating each basic sheet image in the first scanned image; a basic image position determining part for obtaining the corresponding image position according to the identified basic note image; a conventional image intercepting part which intercepts the corresponding conventional bill image from the second scanning image according to the image position; and a regular image storage part for storing regular bill images, wherein the first predetermined scanning parameters at least comprise a first scanning density value, the second predetermined scanning parameters at least comprise a second scanning density value, and the first scanning density value is larger than the second scanning density value.
< Structure 2>
Further, the present invention provides a bill image management system having such features that includes: the bill image management device scans a plurality of bills placed at the same time and captures and stores conventional bill images corresponding to the plurality of bills respectively; and an image content recognition device which is connected with the bill image management device in a communication way, and recognizes and stores the character content in the intercepted conventional bill image so as to be used for management, wherein the bill image management device is the bill image management device of < structure 1 >.
< Structure 3>
Further, the present invention provides a bill image management method having such features that it includes: adopting a first scanning acquisition part to carry out first scanning on a plurality of bills placed at the same time according to a first preset scanning parameter so as to acquire a first scanning image which takes each bill image containing the plurality of bills as a basic bill image; a second scanning acquisition part is adopted to carry out second scanning on the plurality of bills according to a second preset scanning parameter so as to acquire a second scanning image which takes each bill image containing the plurality of bills as a conventional bill image; adopting a basic image identification part to identify each basic bill image in the first scanning image; acquiring a corresponding image position according to the distinguished basic bill image by adopting a basic image position determining part; intercepting a corresponding conventional bill image from the second scanned image by a conventional image intercepting part according to the image position; and storing the regular bill image by using a regular image storage part, wherein the first preset scanning parameter at least comprises a first scanning density value, the second preset scanning parameter at least comprises a second scanning density value, and the first scanning density value is larger than the second scanning density value.
Action and Effect of the invention
According to the bill image management apparatus, the bill image management system and the method of the present invention, since the basic image discriminating portion discriminates each of the basic bill images in the first scanned image; the basic image position determining part acquires a corresponding image position according to the distinguished basic note image; the conventional image intercepting part intercepts a corresponding conventional bill image from the second scanned image according to the image position; the conventional image storage part is used for storing conventional bill images, so that firstly, a plurality of bills placed at the same time can be scanned, namely, the bills are processed in batch, and the time is saved; secondly, the use is simple, and the bill can be randomly placed at any position of the scanning plate; thirdly, the obtained bill image and the original bill are in the same size, the effective pixel of the obtained bill image is high, and the memory occupied by the bill image is saved; and finally, the acquired bill image is an image in the correct direction, so that the subsequent flow in text recognition is saved, and the probability of false recognition and rejection is reduced.
Drawings
FIG. 1 is a block diagram of a document image management system in an embodiment of the invention;
FIG. 2 is a block diagram of a ticket image management apparatus in an embodiment of the present invention;
FIG. 3a is a schematic illustration of a first scan image acquired in an embodiment of the present invention; FIG. 3b is a schematic illustration of a second scan image acquired in an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a first scanned image after performing black-and-white binarization and performing a reverse color according to an embodiment of the present invention;
FIG. 5 is a schematic illustration of median filtering of a black and white scanned image in an embodiment of the present invention;
FIG. 6 is an enlarged schematic view of a white pixel of a black-and-white scanned image according to an embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating a restored black-and-white scanned image in an embodiment of the present invention;
FIG. 8 is a schematic illustration of basic document image discrimination in a black and white scanned image in an embodiment of the present invention;
fig. 9 is a block diagram of an image content recognition apparatus in an embodiment of the present invention; and
FIG. 10 is a flow chart of the operation of the document image management system in an embodiment of the present invention.
Detailed Description
The document image management apparatus, document image management system, and document image management method according to the present invention will be described in detail below with reference to the accompanying drawings.
In a first aspect, the present invention provides a document image management apparatus including: a first scanning acquisition unit that performs a first scan on a plurality of bills placed at the same time based on a first predetermined scanning parameter to acquire a first scan image including each of the bill images of the plurality of bills as a basic bill image; the second scanning acquisition part is used for carrying out second scanning on the plurality of bills according to second preset scanning parameters so as to acquire second scanning images which take each bill image containing the plurality of bills as a conventional bill image; a basic image discrimination unit for discriminating each basic sheet image in the first scanned image; a basic image position determining part for obtaining the corresponding image position according to the identified basic note image; a conventional image intercepting part which intercepts the corresponding conventional bill image from the second scanning image according to the image position; and a regular image storage part for storing regular bill images, wherein the first predetermined scanning parameters at least comprise a first scanning density value, the second predetermined scanning parameters at least comprise a second scanning density value, and the first scanning density value is larger than the second scanning density value.
In the first aspect, the present invention may further include: a preprocessing section, wherein the preprocessing section includes: the black-and-white image conversion unit is used for carrying out binarization processing on the first scanning image and carrying out reverse color conversion to obtain a black-and-white scanning image; and a white pixel amplification unit which amplifies white pixels of the black-and-white scanned image so that outlines in the black-and-white scanned image are consistent, and the basic image discrimination unit discriminates a plurality of basic bill images in the black-and-white scanned image according to the outlines.
In the first aspect, the present invention may further have a feature that: wherein the basic image discrimination section includes: the outline searching unit is used for searching the outline in the black-and-white scanning image according to the distribution of the coherent white pixels; and a bill region determination setting unit that determines an image in which a region area included in the outline satisfies a predetermined area condition based on the outline, and sets the image as a basic bill image.
In the first aspect, the present invention may further have a feature that: wherein the basic image discrimination section includes: a contour searching unit that searches for a contour in the first scanned image; and a bill region determination setting unit that determines an image in which a region area included in the outline satisfies a predetermined area condition based on the outline, and sets the image as a basic bill image.
In the first aspect, the present invention may further have a feature that: wherein the predetermined area condition is that an area content of the area of the region in the first scanned image is between 5% and 60%.
In a second aspect, the present invention provides a document image management system including: the bill image management device scans a plurality of bills placed at the same time and captures and stores conventional bill images corresponding to the plurality of bills respectively; and an image content recognition device which is connected with the bill image management device in a communication way and is used for recognizing and storing the character content in the intercepted conventional bill image so as to be used for management, wherein the bill image management device is the bill image management device of the first embodiment.
In the second embodiment, there may be a feature that: wherein the image content recognition device comprises: a character content recognition unit for recognizing character content; a content derivation unit configured to derive the recognized character content; and a character content storage unit for storing the derived character content.
In addition, as a third aspect, the present invention provides a document image management method including: adopting a first scanning acquisition part to carry out first scanning on a plurality of bills placed at the same time according to a first preset scanning parameter so as to acquire a first scanning image which takes each bill image containing the plurality of bills as a basic bill image; a second scanning acquisition part is adopted to carry out second scanning on the plurality of bills according to a second preset scanning parameter so as to acquire a second scanning image which takes each bill image containing the plurality of bills as a conventional bill image; adopting a basic image identification part to identify each basic bill image in the first scanning image; acquiring a corresponding image position according to the distinguished basic bill image by adopting a basic image position determining part; intercepting a corresponding conventional bill image from the second scanned image by a conventional image intercepting part according to the image position; and storing the regular bill image by using a regular image storage part, wherein the first preset scanning parameter at least comprises a first scanning density value, the second preset scanning parameter at least comprises a second scanning density value, and the first scanning density value is larger than the second scanning density value.
< example >
Fig. 1 is a block diagram of a ticket image management system in an embodiment of the present invention.
As shown in fig. 1, a ticket image management system 100 is a system for ticket management, and includes a ticket image management apparatus 10 and an image content recognition apparatus 20.
The bill image management apparatus 10 scans a plurality of bills placed at the same time, and captures and stores conventional bill images corresponding to the plurality of bills, respectively. The intelligent image acquisition device is arranged on intelligent equipment connected with a scanner, and can acquire images scanned by the scanner in time. The communication network usage management apparatus 10 is communicatively connected to the image content recognition apparatus 20 via the communication network 30. In this embodiment, the intelligent device may be a computer, a personal computer, a mobile phone, or other devices that can be carried by the user, so that the user can perform related operations.
Fig. 2 is a block diagram of a ticket image management apparatus in an embodiment of the present invention.
As shown in fig. 2, the bill image management apparatus 10 includes a predetermined rule storage unit 11, a first scan acquisition unit 12, a second scan acquisition unit 13, a preprocessing unit 14, a basic image discrimination unit 15, a basic image position determination unit 16, a regular image cutout unit 17, a regular image storage unit 18, a management-side communication unit 19, and a management-side control unit 110 that controls the above units.
The predetermined rule storage unit 11 stores a first predetermined scanning parameter, a second predetermined scanning parameter, and a predetermined area condition. The first predetermined scanning parameters include a first scanning density value and a first scanning density value. The second predetermined scan parameter includes a second scan density value and a second scan resolution. The first scanning concentration value is larger than the second scanning concentration value, and the first scanning resolution is smaller than the second scanning resolution. In this embodiment, the first scanning density value is greater than the second scanning density value, so that the outline of the basic bill image is relatively clearer than that of a conventional bill image, and the outline can be found more easily. The first scanning resolution is smaller than the second scanning resolution, so that the first scanning time is shorter than the second scanning time, the time is saved, and the use impression of a user is improved. The predetermined area condition is that an area content of the area of the region in the first scanned image is between 5% and 60%.
The first scan acquiring section 12 performs a first scan on a plurality of bills placed simultaneously in accordance with a first predetermined scan parameter to acquire a first scan image including each of the bill images of the plurality of bills as a basic bill image.
The second scan acquiring section 13 performs a second scan on the plurality of bills in accordance with a second predetermined scan parameter to acquire each of the bill images including the plurality of bills as a second scan image of the regular bill image.
FIG. 3a is a schematic illustration of a first scan image acquired in an embodiment of the present invention; fig. 3b is a schematic illustration of a second scan image acquired in an embodiment of the present invention.
As shown in fig. 3a and 3b, the outline of the base document image in the first scanned image is more prominent than the outline of the regular document image in the second scanned image, but the resolution of the base document image in the first scanned image is lower than the resolution of the regular document image in the second scanned image. In addition, the basic bill image in the first scanned image is not only dark in overall color and poor in appearance, but also the characters on the back side of the bill are scanned due to the fact that the bill is thin and are overlapped with the characters on the front side, and reading and subsequent OCR processing are affected.
The preprocessing section 14 includes a black-and-white image conversion unit 141, a filtering unit 142, a white pixel enlargement unit 143, and a white pixel reduction unit 144.
The black-and-white image conversion unit 141 performs binarization processing on the first scanned image and performs reverse color conversion to obtain a black-and-white scanned image. In this embodiment, the binarization processing is to obtain a binarization threshold value by using an extra-large algorithm; the reverse color processing is to change the white point to the black point and the black point to the white point.
Fig. 4 is a schematic diagram of the first scanned image after performing black-and-white binarization processing and reversing color in the embodiment of the invention.
As shown in fig. 4, the basic document image and the background in the black and white scanned image obtained by the processing of the black and white image conversion unit 141 are distinguished more clearly, so as to better perform the contour recognition later.
The filtering unit 142 removes random noise generated by scanning by using a median filtering method to reduce interference.
Fig. 5 is a schematic diagram of median filtering of a black and white scanned image in an embodiment of the present invention.
As shown in fig. 5, the white pixels representing noise in the black-and-white scanned image processed by the filtering unit 142 are reduced.
The white pixel enlargement unit 143 performs enlargement processing on the white pixels of the black-and-white scanned image so that the contours existing in the black-and-white scanned image become coherent. The white pixel amplifying unit 143 amplifies the white pixel using a dilation algorithm.
Fig. 6 is a schematic diagram of white pixel enlargement of a black-and-white scanning image in the embodiment of the invention.
As shown in fig. 6, the contours existing in the black-and-white scanned image after being processed by the white pixel enlargement unit 143 become coherent.
The white pixel reduction unit 144 reduces the enlarged white pixels and reduces the size of the basic document image to the size of the original document.
Fig. 7 is a schematic diagram of a black-and-white scanned image after being restored in the embodiment of the present invention.
As shown in fig. 7, the basic document image in the black-and-white scanned image obtained by the above processing is more significantly helpful for the subsequent basic image discrimination section 15.
The basic image discrimination section 15 discriminates each basic sheet image in the first scanned image. The basic image discrimination section 15 includes a contour search unit 151 and a bill area determination setting unit 152.
The contour finding unit 151 finds a contour in the black-and-white scanned image according to the distribution of the consecutive white pixels. In this embodiment, the outline searching unit 151 adopts an OpenCV public algorithm to identify the outline of the basic document image and then searches the outline of the basic document image.
The bill region determination setting unit 152 determines an image in which the region area included in the outline of the basic bill image satisfies a predetermined area condition based on the outline of the basic bill image, and sets the image as the basic bill image. The predetermined area condition is that an area content of the area of the region in the first scanned image is between 5% and 60%.
FIG. 8 is a schematic illustration of basic document image discrimination in a black and white scanned image in an embodiment of the present invention.
As shown in fig. 8, the basic image discrimination section 15 discriminates the basic sheet images and marks the sheet images with circumscribed rectangles. In order to ensure that the external rectangle is consistent with the original document in size, each side of the external rectangle can be pushed into the basic document image until the number of intersection points of the side length of the external rectangle and the outline is more than one twentieth of the side length of the external rectangle, and then the operation is stopped.
The basic image position determining section 16 acquires a corresponding image position from the recognized basic sheet image.
The regular image cutout 17 cuts out the corresponding regular bill image from the second scanned image according to the image position.
The regular image storage section 18 is for storing a regular bill image.
The management-side communication unit 19 transmits the regular ticket image stored in the regular image storage unit 18 to the image content recognition device 20 via the communication network 30.
The management-side control section 110 contains a computer program for controlling the operations of the predetermined rule storage section 11, the first scan acquisition section 12, the second scan acquisition section 13, the preprocessing section 14, the base image discrimination section 15, the base image position determination section 16, the normal image cutout section 17, the normal image storage section 18, and the management-side communication section 19.
Fig. 9 is a block diagram of an image content identifying apparatus in an embodiment of the present invention.
As shown in fig. 9, the image content recognition device 20 is communicatively connected to the ticket image management device 10, and recognizes and stores character content in the intercepted regular ticket image for management. The image content recognition apparatus 20 includes a recognition-side communication unit 21, a character content recognition unit 22, a content derivation unit 23, a character content storage unit 24, and a recognition-side control unit 25 that controls the above units.
The identification-side communication unit 21 receives the regular bill image transmitted from the bill image management device 10.
The character content recognition portion 22 is used for recognizing the character content in the received intercepted regular bill image.
The content derivation unit 23 is configured to derive the character content recognized by the character content recognition unit 22.
The character content storage unit 24 stores the character content derived by the content derivation unit 23.
The recognition-side control unit 25 includes a computer program for controlling the operations of the character content recognition unit 22, the content derivation unit 23, and the character content storage unit 24.
FIG. 10 is a flow chart of the operation of the document image management system in an embodiment of the present invention.
As shown in fig. 10, in the present embodiment, the operation flow of the ticket image management system 100 includes the following steps:
in step S1, the first scan acquiring unit 12 performs a first scan on the plurality of bills placed at the same time according to a first predetermined scan parameter to acquire a first scan image containing each of the bill images of the plurality of bills as a basic bill image, and then proceeds to step S2.
In step S2, the second scan acquiring part 13 performs the second scan on the plurality of bills according to the second predetermined scan parameter to acquire the second scan image containing the respective bill images of the plurality of bills as the regular bill image, and then proceeds to step S3.
In step S3, the black-and-white image conversion unit 141 binarizes the first scanned image and performs reverse color conversion to obtain a black-and-white scanned image, and then proceeds to step S4.
In step S4, the filtering unit 142 removes random noise generated by scanning by using a median filtering method to reduce interference, and then proceeds to step S5.
In step S5, the white pixel enlargement unit 143 performs enlargement processing on the white pixels of the black-and-white scanned image so that the contours existing in the black-and-white scanned image become coherent, and then proceeds to step S6.
In step S6, the white pixel reduction unit 144 reduces the enlarged white pixels and reduces the size of the basic document image to the size of the original document, and then proceeds to step S7.
In step S7, the contour search unit 151 searches for a contour in the black-and-white scanned image according to the distribution of the consecutive white pixels, and then proceeds to step S8.
In step S8, the document region determination setting unit 152 determines an image in which the region area included in the outline of the basic document image satisfies a predetermined area condition based on the outline of the basic document image, sets the image as the basic document image, and proceeds to step S9.
In step S9, the basic image position determination section 16 acquires the corresponding image position from the discriminated basic document image, and then proceeds to step S10.
In step S10, the normal image cutout section 17 cuts out the corresponding normal bill image from the second scanned image in accordance with the image position, and then proceeds to step S11.
In step S11, the basic image position determination section 16 acquires the corresponding image position from the discriminated basic document image, and then proceeds to step S12.
In step S12, the normal image cutout section 17 cuts out the corresponding normal bill image from the second scanned image in accordance with the image position, and then proceeds to step S13.
In step S13, the regular image storage section 18 stores the regular ticket image, and then proceeds to step S14.
In step S14, the management-side communication section 19 transmits the regular ticket image stored in the regular image storage section 18 to the image content recognition apparatus 20 via the communication network 30, and then proceeds to step S15.
In step S15, the recognition-side communication unit 21 receives the regular ticket image transmitted from the ticket image management apparatus 10, and then proceeds to step S16.
In step S16, the character content recognition section 22 recognizes the character content in the received clipped regular ticket image, and then proceeds to step S17.
In step S17, the content derivation unit 23 derives the character content recognized by the character content recognition unit 22, and the process proceeds to step S18.
In step S18, the character content storage unit 24 stores the character content derived by the content derivation unit 23, and then enters an end state.
Effects and effects of the embodiments
According to the bill image management apparatus, the bill image management system, and the method according to the present embodiment, since the basic image discrimination section discriminates each basic bill image in the first scanned image; the basic image position determining part acquires a corresponding image position according to the distinguished basic note image; the conventional image intercepting part intercepts a corresponding conventional bill image from the second scanned image according to the image position; the conventional image storage part is used for storing conventional bill images, so that firstly, a plurality of bills placed at the same time can be scanned, namely, the bills are processed in batch, and the time is saved; secondly, the use is simple, and the bill can be randomly placed at any position of the scanning plate; thirdly, the obtained bill image and the original bill are in the same size, the effective pixel of the obtained bill image is high, and the memory occupied by the bill image is saved; and finally, the acquired bill image is an image in the correct direction, so that the subsequent flow in text recognition is saved, and the probability of false recognition and rejection is reduced.
The above embodiments are preferred examples of the present invention, and are not intended to limit the scope of the present invention.
In the present embodiment, the second scan acquiring section has acquired the second scan image before the preprocessing section, but in the present invention, the second scan acquiring section may acquire the second scan image just before the regular image intercepting section intercepts the regular bill image.
In addition, in the present embodiment, the document image management apparatus further includes a preprocessing unit, and as the document image management apparatus of the present invention, it is possible to acquire a more accurate position of the basic document image without processing the first scan image. In this case, the contour searching means in the basic image discrimination section may directly search for the contour in the first scanned image.
In the present embodiment, the preprocessing unit in the document image management apparatus includes the monochrome image conversion unit, the filter unit, the white pixel enlargement unit, and the white pixel reduction unit, but the preprocessing unit of the present invention may include only the monochrome image conversion unit and the white pixel enlargement unit.
Claims (7)
1. A document image management apparatus, comprising:
a first scanning acquisition unit that performs a first scan on a plurality of bills placed at the same time based on a first predetermined scanning parameter to acquire a first scan image including each of the bill images of the plurality of bills as a basic bill image;
a second scanning acquisition part for performing a second scanning on the plurality of bills according to a second predetermined scanning parameter to acquire a second scanning image containing each bill image of the plurality of bills as a regular bill image;
a preprocessing unit that processes the first scan image;
a basic image identification part for performing contour search on the first scanning image based on the processing of the preprocessing part, identifying each basic note image in the first scanning image based on a preset area condition, and labeling each basic note image with a circumscribed rectangle;
a basic image position determining part for obtaining the corresponding image position according to the identified basic note image;
a conventional image intercepting part which intercepts the corresponding conventional bill image from the second scanning image according to the image position; and
a regular image storage section for storing the regular bill image,
wherein the first predetermined scanning parameters comprise at least a first scanning concentration value,
the second predetermined scan parameter comprises at least a second scanned intensity value,
the first scanned concentration value is greater than the second scanned concentration value,
the predetermined area condition is that the area content of the area of the base bill image in the first scanned image is between 5% and 60%,
the preprocessing section includes:
a black-and-white image conversion unit which performs binarization processing on the first scanning image and performs reverse color conversion to obtain a black-and-white scanning image;
and a white pixel enlargement unit that enlarges white pixels of the black-and-white scanned image so that contours existing in the black-and-white scanned image are consecutive, and that causes the basic image discrimination unit to discriminate the plurality of basic document images in the black-and-white scanned image based on the contours.
2. The document image management apparatus according to claim 1, wherein:
wherein the basic image discriminating portion includes:
the contour searching unit is used for searching the contour in the black-and-white scanning image according to the distribution of the coherent white pixels;
and a bill region determination setting unit configured to determine an image in which a region area included in the outline satisfies the predetermined area condition based on the outline, and set the image as the basic bill image.
3. The document image management apparatus according to claim 1, wherein:
wherein the basic image discriminating portion includes:
a contour searching unit that searches for a contour in the first scanned image;
and a bill region determination setting unit configured to determine an image in which a region area included in the outline satisfies a predetermined area condition based on the outline, and set the image as the basic bill image.
4. The document image management apparatus according to claim 1, wherein:
after the basic image distinguishing part marks each basic bill image by using a circumscribed rectangle, each edge of the circumscribed rectangle is further pushed towards the inside of the basic bill image until the number of intersection points of the side length of the circumscribed rectangle and the outline of the basic bill image is more than one twentieth of the side length of the circumscribed rectangle, and then the basic bill image distinguishing part stops.
5. A document image management system for documents, comprising:
the bill image management device scans a plurality of bills placed at the same time and captures and stores conventional bill images corresponding to the bills respectively; and
image content recognition means, communicatively connected to the bill image management means, for recognizing and storing character content in the intercepted regular bill image for management,
the document image management apparatus according to any one of claims 1 to 4.
6. The document image management system according to claim 5, wherein:
wherein the image content recognition apparatus has:
a character content recognition unit configured to recognize the character content;
a content derivation unit configured to derive the recognized character content; and
and a character content storage unit for storing the derived character content.
7. A bill image management method for managing bill images, comprising:
adopting a first scanning acquisition part to carry out first scanning on a plurality of bills placed at the same time according to a first preset scanning parameter so as to acquire a first scanning image which takes each bill image containing the plurality of bills as a basic bill image;
a second scanning acquisition part is adopted to carry out second scanning on the plurality of bills according to a second preset scanning parameter so as to acquire a second scanning image which takes each bill image containing the plurality of bills as a conventional bill image;
processing the first scanned image by using a preprocessing unit;
performing contour search on the first scanned image based on the processing of the preprocessing part and identifying each basic bill image in the first scanned image based on a preset area condition by using a basic image identification part;
acquiring a corresponding image position according to the distinguished basic bill image by adopting a basic image position determining part;
intercepting the corresponding conventional bill image from the second scanned image by a conventional image intercepting part according to the image position; and
storing the regular bill image with a regular image storage section,
wherein the first predetermined scanning parameters comprise at least a first scanning concentration value,
the second predetermined scan parameter comprises at least a second scanned intensity value,
the first scanned concentration value is greater than the second scanned concentration value,
the predetermined area condition is that the area content of the area of the base bill image in the first scanned image is between 5% and 60%,
the processing of the preprocessing section includes:
performing binarization processing on the first scanning image by adopting a black-and-white image conversion unit and performing reverse color conversion to obtain a black-and-white scanning image;
adopting a white pixel amplifying unit to amplify white pixels of the black-white scanning image to enable the outlines in the black-white scanning image to be consistent,
the basic image discrimination unit discriminates the plurality of basic sheet images in the black-and-white scanned image from the contour.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710203940.4A CN107016363B (en) | 2017-03-30 | 2017-03-30 | Bill image management device, bill image management system, and bill image management method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710203940.4A CN107016363B (en) | 2017-03-30 | 2017-03-30 | Bill image management device, bill image management system, and bill image management method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107016363A CN107016363A (en) | 2017-08-04 |
| CN107016363B true CN107016363B (en) | 2020-06-05 |
Family
ID=59446663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710203940.4A Expired - Fee Related CN107016363B (en) | 2017-03-30 | 2017-03-30 | Bill image management device, bill image management system, and bill image management method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107016363B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255881B (en) * | 2018-09-29 | 2021-07-20 | 北京单多啦科技有限公司 | Automatic bill filing system and method |
| CN109460766B (en) * | 2018-09-29 | 2022-03-15 | 济南企财通软件有限公司 | Device and method for extracting ticket image from ticket paper |
| CN109344836B (en) * | 2018-09-30 | 2021-05-14 | 金蝶软件（中国）有限公司 | Character recognition method and equipment |
| CN109446995A (en) * | 2018-10-30 | 2019-03-08 | 广西科技大学 | The treating method and apparatus of billing information |
| WO2021023111A1 (en) * | 2019-08-02 | 2021-02-11 | 杭州睿琪软件有限公司 | Methods and devices for recognizing number of receipts and regions of a plurality of receipts in image |
| CN111178268B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Exercise book content identification system |
| CN111144342B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Page content identification system |
| CN111176775B (en) * | 2019-12-30 | 2023-04-07 | 福建天晴数码有限公司 | Page generation system |
| CN111144343B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Answer sheet content identification system |
| CN111178269B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Answer sheet content identification method |
| CN110942054B (en) * | 2019-12-30 | 2023-06-30 | 福建天晴数码有限公司 | Page content identification method |
| CN111221607B (en) * | 2019-12-30 | 2023-04-07 | 福建天晴数码有限公司 | Page generation method |
| CN110969152B (en) * | 2019-12-30 | 2023-04-18 | 福建天晴数码有限公司 | Exercise book content identification method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102789658A (en) * | 2012-03-02 | 2012-11-21 | 成都三泰电子实业股份有限公司 | Ultraviolet anti-counterfeiting check authenticity verification method |
| CN103021069A (en) * | 2012-11-21 | 2013-04-03 | 深圳市兆图电子有限公司 | High-speed note image acquisition processing system and acquisition processing method thereof |
| CN103456075A (en) * | 2013-09-06 | 2013-12-18 | 广州广电运通金融电子股份有限公司 | Paper money processing method and device |
| CN103606220A (en) * | 2013-12-10 | 2014-02-26 | 江苏国光信息产业股份有限公司 | Check printed number recognition system and check printed number recognition method based on white light image and infrared image |
| CN103617415A (en) * | 2013-11-19 | 2014-03-05 | 北京京东尚科信息技术有限公司 | Device and method for automatically identifying invoice |
| CN105303363A (en) * | 2015-09-28 | 2016-02-03 | 四川长虹电器股份有限公司 | Data processing method and data processing system |
| CN105320951A (en) * | 2014-06-23 | 2016-02-10 | 株式会社日立信息通信工程 | Optical character recognition apparatus and optical character recognition method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7426291B2 (en) * | 2002-07-29 | 2008-09-16 | Seiko Epson Corporation | Apparatus and method for binarizing images of negotiable instruments using a binarization method chosen based on an image of a partial area |
| JP5262869B2 (en) * | 2009-03-12 | 2013-08-14 | 株式会社リコー | Image processing system, image processing server, MFP, and image processing method |
-
2017
- 2017-03-30 CN CN201710203940.4A patent/CN107016363B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102789658A (en) * | 2012-03-02 | 2012-11-21 | 成都三泰电子实业股份有限公司 | Ultraviolet anti-counterfeiting check authenticity verification method |
| CN103021069A (en) * | 2012-11-21 | 2013-04-03 | 深圳市兆图电子有限公司 | High-speed note image acquisition processing system and acquisition processing method thereof |
| CN103456075A (en) * | 2013-09-06 | 2013-12-18 | 广州广电运通金融电子股份有限公司 | Paper money processing method and device |
| CN103617415A (en) * | 2013-11-19 | 2014-03-05 | 北京京东尚科信息技术有限公司 | Device and method for automatically identifying invoice |
| CN103606220A (en) * | 2013-12-10 | 2014-02-26 | 江苏国光信息产业股份有限公司 | Check printed number recognition system and check printed number recognition method based on white light image and infrared image |
| CN105320951A (en) * | 2014-06-23 | 2016-02-10 | 株式会社日立信息通信工程 | Optical character recognition apparatus and optical character recognition method |
| CN105303363A (en) * | 2015-09-28 | 2016-02-03 | 四川长虹电器股份有限公司 | Data processing method and data processing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107016363A (en) | 2017-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107016363B (en) | Bill image management device, bill image management system, and bill image management method | |
| US11538235B2 (en) | Methods and apparatus to determine the dimensions of a region of interest of a target object from an image using target object landmarks | |
| CN110008944B (en) | OCR recognition method and device based on template matching and storage medium | |
| US7209599B2 (en) | System and method for scanned image bleedthrough processing | |
| US7636483B2 (en) | Code type determining method and code boundary detecting method | |
| US8009928B1 (en) | Method and system for detecting and recognizing text in images | |
| US8373905B2 (en) | Semantic classification and enhancement processing of images for printing applications | |
| JP6139396B2 (en) | Method and program for compressing binary image representing document | |
| WO2019153739A1 (en) | Identity authentication method, device, and apparatus based on face recognition, and storage medium | |
| US11341739B2 (en) | Image processing device, image processing method, and program recording medium | |
| CN111274957A (en) | Webpage verification code identification method, device, terminal and computer storage medium | |
| CN108108734B (en) | A kind of license plate recognition method and device | |
| JP2003525560A (en) | Improved method of image binarization | |
| JP6630341B2 (en) | Optical detection of symbols | |
| CN113139535A (en) | OCR document recognition method | |
| CN103606220A (en) | Check printed number recognition system and check printed number recognition method based on white light image and infrared image | |
| CN111814780A (en) | Bill image processing method, device and equipment and storage medium | |
| KR102102403B1 (en) | Code authentication method of counterfeit print image and its application system | |
| JP2024107599A (en) | Information processing system, method and program | |
| JP2019128690A (en) | Handwritten character recognition system | |
| CN109635798B (en) | Information extraction method and device | |
| KR101676000B1 (en) | Method for Detecting and Security-Processing Fingerprint in Digital Documents made between Bank, Telecommunications Firm or Insurance Company and Private person | |
| CN108647570B (en) | Zebra crossing detection method and device and computer readable storage medium | |
| CN116503871A (en) | Character segmentation preprocessing method, terminal device and computer readable storage medium | |
| CN112215783A (en) | Image noise point identification method, device, storage medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200605 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |