TWI382359B - Apparatus and method for image processing - Google Patents

Description

Image processing device and method

The present invention relates to image processing, and in particular, the present invention relates to an image processing apparatus for dividing an image into a plurality of sub-images by edge detection, and processing pixels in each sub-image to enhance image sharpness and method.

In recent years, as the technology related to image processing has been continuously improved, many image processing methods have been used to improve some of the shortcomings inherent in images to enhance the quality of images.

For example, an image processing method called binarization is used to convert an image originally having a grayscale into a binary image with only black and white distribution. For an image with a 256-level luminance value, the 0-level luminance value corresponds to black, and the 255-level luminance value corresponds to white.

The binarized image processing method uses the principle of probability statistics to find the optimal brightness threshold in the image, and distinguishes the pixels belonging to two different clusters. As long as the pixel whose brightness value is higher than the threshold value, make it white (for example, the brightness value is set to 255). Conversely, if the brightness value of the pixel is lower than the threshold value, make it black (for example, the brightness value is set to 0) ). The purpose of this step is to highlight the contrast of the shape of the object. Through the binarization method in the image processing, the object and the background can be presented with black and white information for the subsequent steps.

However, according to the image processing results obtained by the currently used binarized image processing method, the actual effect is not satisfactory. Especially when the background pattern is complicated or the color is dark, it is very likely that the partial pixel brightness value in a certain image area is lower than the threshold value, and the entire image area is regarded as black, thus causing binarization. In the latter image, there may be a large black area that should not have appeared.

Accordingly, it is a primary object of the present invention to provide an image processing apparatus and method to solve the above problems.

The present invention relates to an image processing apparatus and method for dividing an image into a plurality of sub-images by detecting a sub-image edge, and performing brightness adjustment for each pixel in the sub-image.

An image processing apparatus according to an embodiment of the present invention is an image processing apparatus. The image processing device includes a detection module, a division module, a calculation module, a determination module and an adjustment module. The detection module is configured to detect at least one sub-image boundary in an image. The dividing module is electrically connected to the detecting module, and is configured to divide the image into a plurality of sub-images according to the at least one sub-image boundary, each of the sub-images respectively comprising a plurality of pixels and each corresponding to a brightness Threshold value. The computing module is electrically connected to the dividing module, and is configured to analyze brightness of a plurality of pixels included in each sub-image area, and calculate a brightness threshold corresponding to each sub-image area. The determining module is electrically connected to the dividing module and the computing module, and is configured to determine whether a brightness of a pixel of the pixel included in one of the sub-images of the sub-images is greater than corresponding to The brightness threshold of the target sub-image. The adjustment module is electrically connected to the determination module. If the judgment result of the determination module is yes, the adjustment module increases the brightness of the pixel. On the other hand, if the determination result of the determination module is no, the adjustment module reduces the brightness of the pixel.

Compared with the prior art, the image processing device and the image processing method according to the present invention divide the image into a plurality of sub-images by detecting the edge of the sub-image, and perform brightness adjustment for each pixel in the sub-image. Since the image processing apparatus and the image processing method according to the present invention can more accurately divide different sub-images, the effect of the binarized image processing can be effectively improved, and the processed image can be made clearer and improved. When the background pattern of the image is more complicated or the color is darker, there will be a large abnormal black area.

The advantages and spirit of the present invention will be further understood from the following detailed description of the invention.

A first embodiment of the present invention is an image processing apparatus. Please refer to FIG. 1. FIG. 1 is a functional block diagram of the image processing apparatus. As shown in FIG. 1 , the image processing device 10 includes a detection module 12 , a division module 14 , a calculation module 15 , a determination module 16 , and an adjustment module 18 .

Next, the functions of the respective modules included in the image processing apparatus 10 will be described in detail.

The detection module 12 is configured to detect at least one sub-image boundary in an image. In practical applications, the image can be a business card, a card, a photo or a file. Various images and text may be included on the image. As for the so-called sub-image boundary described above, it refers to the edge of each pattern or text displayed in the image.

The partitioning module 14 is electrically connected to the detecting module 12, and is configured to divide the image into a plurality of sub-image regions according to the at least one sub-image boundary, wherein each of the sub-image regions respectively includes a plurality of pixels. Therefore, if there are five sub-image boundaries detected by the detection module 12 of the image processing device 10, the division module 14 divides the image into six sub-image regions according to the five sub-image boundaries.

The computing module 15 is electrically connected to the dividing module 14 for analyzing the brightness of the plurality of pixels included in each of the sub-image areas to calculate a brightness threshold corresponding to each of the sub-image areas.

For example, as shown in FIG. 2, in the image 20, the detection module 12 of the image processing apparatus 10 can detect two sub-image edges 22 and 24. At this time, the dividing module 14 can divide the image 20 into three sub-image areas A, B and C according to the two sub-image edges 22 and 24. Each of the sub-image areas A, B, and C respectively includes a plurality of pixels. Then, the calculation module 15 of the image processing apparatus 10 calculates a brightness threshold corresponding to each sub-image area for each of the plurality of pixels of each sub-image area.

In the above example, no other pattern or character is included in the sub-image area, regardless of the sub-image area A, B or C. Please refer to Figure 3, which shows another example. As shown in FIG. 3, in the image 30, the detecting module 12 in the image processing apparatus 10 according to the present invention can detect the two sub-image edges 22 and 24 as shown in FIG. Another sub-image edge 26 is detected. At this time, the dividing module 14 can divide the image 20 into four sub-image areas A, B, C and D according to the three sub-image edges 22, 24 and 26.

It should be noted that since the sub-image area D is actually included in the sub-image area B, if the sub-image area D is not separately divided, the sub-image area B is directly used for conventional binarized image processing. In the case of the program, the resulting image is likely to be distorted.

Therefore, in the present invention, the detection module 12 in the image processing apparatus 10 plays a very important role. If the detection module 12 can correctly detect all the sub-image edges included in the image, the division mode Group 14 can correctly divide the image into multiple sub-image areas based on the detected sub-image edges.

The determining module 16 is electrically connected to the dividing module 14 and the computing module 15 and is configured to determine whether a brightness of one of the pixels of the target sub-image area in the sub-image areas is greater than Corresponding to the brightness threshold value of the target sub-image area.

That is to say, each sub-image area has a brightness threshold value, and the determination module 16 will respectively determine whether the brightness of each pixel included in a target sub-image area is greater than the target sub-image. The brightness threshold of the image area.

As for the brightness threshold value of the target sub-image area, the principle of probability statistics is used, for example, using the conventional Otsu's method, selecting the best among the brightness values of all the pixels included in the target sub-image area. One of the brightness threshold values.

The adjustment module 18 is electrically connected to the determination module 16. If the determination result of the determination module 16 is yes, the adjustment module 18 increases the brightness of the pixel. On the other hand, if the determination result of the determination module 16 is negative, the adjustment module 18 lowers the brightness of the pixel.

In practical applications, since the different sub-image regions respectively have different brightness threshold values, when the image processing device 10 performs binarized image processing on the pixels included in a certain target sub-image region, corresponding to the target sub-image The brightness threshold value of the area is the brightness threshold value required for binarization processing of the target sub-image area.

Generally, if the determining module 16 determines that the brightness of a pixel in the target sub-image is greater than the brightness threshold of the sub-image, the adjustment module 18 adjusts the brightness of the pixel to white (for example, brightness). The value is set to 255). On the other hand, if the determining module 16 determines that the brightness of a pixel in the target sub-image is less than the brightness threshold of the sub-image, the adjustment module 18 adjusts the brightness of the pixel to black (for example, brightness). The value is set to 0). However, the user may set the first brightness value and the second brightness value to any brightness value according to their actual needs, and may even form some special image effects, and thus is not limited to this example.

A second embodiment of the present invention is an image processing method. Please refer to FIG. 4, which is a flow chart showing the image processing method.

As shown in FIG. 4, first, the method performs step S1 to detect at least one sub-image boundary in an image. In practical applications, the image can be a business card, a card, a photo or a file. Various images and text may be included on the image. As for the so-called sub-image boundary described above, it refers to the edge of each pattern or text displayed in the image.

Next, the method performs step S2, and divides the image into a plurality of sub-image regions according to the at least one sub-image boundary. Each of the sub-image areas respectively includes a plurality of pixels. For example, if the method detects three sub-image boundaries, the method divides the image into four sub-image areas according to the three sub-image boundaries.

Then, the method performs step S3, and calculates a brightness threshold corresponding to each sub-image area according to the plurality of pixels included in each sub-image area.

Then, the method performs step S4 to determine whether a brightness of one of the pixels included in one of the target sub-images is greater than the brightness threshold corresponding to the target sub-image area. That is to say, each sub-image area has a brightness threshold value, and in step S4, the method will respectively determine whether the brightness of each pixel included in a certain target sub-image area is greater than The brightness threshold of the sub-image area.

As for the brightness threshold value of the target sub-image area, the principle of probability statistics is used, for example, using the conventional Otsu's method, the best is selected from the brightness of all the pixels included in the target sub-image area. A brightness threshold.

Next, according to the judgment result of step S4, the method will perform different steps. If the result of the determination in step S4 is YES, the method executes S5 to increase the brightness of the pixel. On the other hand, if the result of the determination in the step S4 is NO, the method executes S6 to lower the brightness of the pixel.

In practical applications, if the method performs the step S4, the result of the determination is that if the brightness of a pixel in the target sub-image area is greater than the brightness threshold of the sub-image area, the brightness of the pixel is generally Adjust to white (for example, the brightness value is set to 255). On the other hand, if the method performs the step S4, the result of the determination is that when the brightness of a pixel in the sub-image area is smaller than the brightness threshold of the sub-image area, the brightness of the pixel is generally adjusted to Black (for example, the brightness value is set to 0). However, the user can also set the first brightness value and the second brightness value to any brightness value as needed, and thus is not limited by this example.

Compared with the prior art, the image processing apparatus and the image processing method according to the present invention divide the image into a plurality of sub-images by detecting the edge of the sub-image, and respectively perform brightness adjustment for each pixel in each sub-image. Since the image processing apparatus and the image processing method according to the present invention can more accurately divide different sub-images, the effect of the binarized image processing can be effectively improved, and the processed image can be made clearer and improved. When the background pattern of the image is more complicated or the color is darker, there will be a large abnormal black area.

The features and spirit of the present invention will be more apparent from the detailed description of the preferred embodiments. On the contrary, the intention is to cover various modifications and equivalents within the scope of the invention as claimed.

S1~S6. . . Process step

10. . . Image processing device

12. . . Detection module

14. . . Partition module

15. . . Computing module

16. . . Judging module

18. . . Adjustment module

20, 30. . . image

22, 24, 26. . . Sub-image edge

A, B, C, D. . . Sub-image area

1 is a functional block diagram of an image processing apparatus according to a first embodiment of the present invention.

Figure 2 and Figure 3 each show an example of an image.

4 is a flow chart showing an image processing method according to a second embodiment of the present invention.

10. . . Image processing device

12. . . Detection module

14. . . Partition module

15. . . Computing module

16. . . Judging module

18. . . Adjustment module

Claims (8)

An image processing device includes: a detection module for detecting at least one sub-image boundary in an image; and a division module electrically connected to the detection module for deriving according to the at least one sub-image boundary Dividing the image into a plurality of sub-image regions, each sub-image region respectively comprising a plurality of pixels; a computing module electrically connected to the dividing module for analyzing a plurality of pixels included in each sub-image region a brightness threshold for calculating a brightness threshold value corresponding to each of the sub-image areas; a determination module electrically connected to the division module and the calculation module for determining one of the target sub-image areas in the sub-image areas Whether a brightness of a pixel including the pixels is greater than a brightness threshold corresponding to the target sub-image area; and an adjustment module electrically connected to the determination module, if the judgment result of the determination module is Yes, the adjustment module increases the brightness of the pixel. The image processing device of claim 1, wherein the adjustment module reduces the brightness of the pixel if the determination result of the determination module is negative. The image processing device of claim 1, wherein the sub-image areas comprise a text and/or a pattern. The image processing device of claim 1, wherein the at least one sub-image boundary comprises a text edge and/or a pattern edge. An image processing method includes the following steps: (a) detecting at least one sub-image boundary in an image; (b) dividing the image into a plurality of sub-image regions according to the at least one sub-image boundary, each sub-image region respectively Include a plurality of pixels; (c) calculating a brightness threshold corresponding to each sub-image area according to a plurality of pixels included in each sub-image area; (d) determining one of the target sub-images in the sub-images Whether a brightness including one pixel is greater than the brightness threshold corresponding to the target sub-image area; and (e) if the determination result of the step (d) is YES, increasing the brightness of the pixel. The image processing method according to claim 5, further comprising the following steps: (f) if the judgment result of the step (d) is negative, reducing the brightness of the pixel. The image processing method of claim 5, wherein the sub-image areas comprise a text and/or a pattern. The image processing method of claim 5, wherein the at least one sub-image boundary comprises a text edge and/or a pattern edge.