[go: up one dir, main page]

WO1993018483A1 - Procede et appareil de reconnaissance d'image - Google Patents

Procede et appareil de reconnaissance d'image Download PDF

Info

Publication number
WO1993018483A1
WO1993018483A1 PCT/US1993/001843 US9301843W WO9318483A1 WO 1993018483 A1 WO1993018483 A1 WO 1993018483A1 US 9301843 W US9301843 W US 9301843W WO 9318483 A1 WO9318483 A1 WO 9318483A1
Authority
WO
WIPO (PCT)
Prior art keywords
level
hidden markov
dimensional
state
pixel
Prior art date
Application number
PCT/US1993/001843
Other languages
English (en)
Inventor
Esther Levin
Roberto Pieraccini
Original Assignee
American Telephone And Telegraph Company
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by American Telephone And Telegraph Company filed Critical American Telephone And Telegraph Company
Publication of WO1993018483A1 publication Critical patent/WO1993018483A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models

Definitions

  • the present invention relates generally to the field of image recognition, and specifically to pattern based image recognition.
  • Signal recognition systems operate to label, classify, or otherwise recognize an unknown signal. Signal recognition may be performed by comparing characteristics or features of unknown signals to those of known signals.
  • Features or characteristics of known signals are determined by a process known as training. Through training, one or more samples of known signals are examined and their features or characteristics recorded as reference patterns in a database of a signal recognizer.
  • a signal recognizer extracts features from the signal to characterize it.
  • the features of the unknown signal are referred to as the test pattern.
  • the recognizer compares each reference pattern in the database to the test pattern of the unknown signal.
  • a scoring technique is used to provide a relative measure of how well each reference pattern matches the test pattern.
  • the unknown signal is recognized as the reference pattern which most closely matches the unknown signal.
  • DTW dynamic time warping
  • DTW provides an optimal time alignment between reference and test patterns by locally shrinking or expanding the time axis of one pattern until that pattern optimally matches the other.
  • DTW scoring reflects an overall distance between two optimally aligned reference and test patterns. The reference pattern having the lowest score (i.e, the shortest distance between itself and the test pattern) identifies the test pattern.
  • HMM recognizers are trained using both first and second order statistics (i.e., means and variances) of known signal samples to build reference patterns. Each reference pattern is an N-state statistical model incorporating these means and variances.
  • An HMM is characterized by a state transition matrix, A (which provides a statistical description of how new states may be reached from old states), and an observation probability matrix, B (which provides a description of which spectral features are likely to be observed at a given state). Scoring of a test pattern reflects the probability of the sequence of features in the pattern given a model (i.e., given a reference pattern). Scoring across all models may be provided by conventional dynamic programming techniques, such as Viterbi scoring well known in the art. The HMM which indicates the highest probability of the sequence of features in the test pattern identifies the test pattern.
  • Pattern-based signal recognition techniques such as DTW and HMMs have been applied in the past to the one-dimensional problem of speech recognition, where unknown signals to be recognized are speech, signals and the one dimension is time. It has been a problem of some interest to provide for multi- dimensional signals, such as two-dimensional image signals, a set of general tools analogous to those available for one-dimensional signal recognition.
  • the present invention provides a method and apparatus for multi-dimensional signal recognition.
  • the invention accomplishes recognition through multi-dimensional reference pattern scoring techniques.
  • An illustrative embodiment of the present invention provides a two-dimensional image recognizer for optical character recognition.
  • the recognizer is based on planar hidden Markov models (PHMMs) with constrained transition probabilities.
  • PHMMs planar hidden Markov models
  • Each PHMM comprises a one-dimensional shape-level hidden Markov model and represents a single image reference pattern.
  • a shape-level HMM comprises one or more pixel-level hidden Markov models, each of which represents a localized portion of a shape-level HMM.
  • the embodiment operates to determine, for a given PHMM and a given sequence of pixels in an unknown character image, a local Viterbi score for each of one or more pixel-level HMMs in a shape-level HMM.
  • the embodiment operates to determine a global Viterbi score for a shape-level HMM based on the plurality of local Viterbi scores. Character images are recognized based on the global Viterbi scores. A global Viterbi score is provided for each PHMM (i.e., each shape-level HMM) reference pattern.
  • Figure 1 presents illustrative groupings of pixel-level hidden Markov model states.
  • Figure 2 presents the illustrative groupings of pixel-level hidden Markov model states from Figure 1 associated with the shape-level states of a shape-level hidden Markov model.
  • Figure 3 presents a shape-level hidden Markov model comprising the shape-level states presented in Figure 2.
  • Figure 4 presents an illustrative optical character recognition -system according to the present invention.
  • Figure 5 presents components of the two-dimensional pattern matcher presented in Figure 4.
  • Figure 6 presents an image of a scanned character, T, comprising a plurality of linear pixel sequences.
  • An illustrative optical character recognition system includes a plurality of two-dimensional (or planar) hidden Markov models to represent images to be recognized.
  • Each planar hidden Markov model is defined by:
  • Each two-dimensional hidden Markov model may be represented as a set of shape-level states .
  • Each shape-level state, G j corresponds
  • N G The number of groups of shape-level states, is a polynomial function of the number of pixel-level states X ⁇ Y.
  • transition probabilities should fulfill the two following conditions:
  • FIG. 1 An example ofthe application of these conditions (a-d) is presented in Figures 1 - 3.
  • seven shape-level states, G 1 to G 7 are shown with reference to a 4 ⁇ 4 matrix of pixel-level states.
  • each shapelevel state, G j corresponds to a one-dimensional pixel-level hidden Markov model comprising four pixel-level states.
  • each shape-level state, G j is but one state in a shape-level hidden Markov model, as shown in Figure 3.
  • the arrows between states in the HMM of Figure 3 indicate legal state transitions within the constraints of conditions c and d, above.
  • transition probability A (i,j),(k,l),(m,n) can be represented as:
  • ⁇ rp P( s(x,y) ⁇ G P
  • (5) defines the transition probabilities between pixel-level states in a one-dimensional pixel-level HMM (such as, e.g., any of those appearing in Figure 2, and (6) defines the transition probabilities between shape-level states in a one-dimensional shape-level HMM.
  • a general two-dimensional (or planar) HMM for use in image recognition is provided. Note that the pixel-level state observation probabilities are not affected by the grouping of states.
  • Illustrative embodiment of the present invention is presented as comprising individual functional blocks (including functional blocks labeled as "processors"). The functions these blocks represent may be provided through the use of either shared or dedicated hardware, including, but not limited to, hardware capable of executing software. (Use of the term "processor” should not be construed to refer exclusively to hardware capable of executing software.) Illustrative embodiments may comprise digital signal processor (DSP) hardware, such as the AT&T DSP 16 or DSP32C, and software performing the operations discussed below. Very large scale integration (VLSI) hardware embodiments of the present invention, as well as hybrid DSP/VLSI embodiments, may also be provided.
  • DSP digital signal processor
  • VLSI Very large scale integration
  • Figure 4 presents an illustrative optical character recognition system according to the present invention.
  • the system comprises a conventional image scanner 10, a two-dimensional pattern matcher 20, control switches R and T, a decision processor 30, a state image memory 35, a probability estimation processor 45, and a planar hidden Markov model memory 40.
  • the conventional image scanner 10 receives a physical image of a character and scans it to generate as output a matrix signal, g(x,y). This signal represents the intensity of the physical image at each pixel location, x,y, within the image.
  • PHMMs developed through a training process discussed below, are stored in the PHMM memory 40. Each PHMM in memory 40 represents a character to be recognized in an optical character application.
  • the matrix signal for the image, g(x,y), is processed by the two-dimensional pattern matcher 20 to generate, for each PHMM, a global Viterbi score 1 resulting from the comparison of the PHMM and the signal g(x,y).
  • a state image, s (x,y ), is also generated to represent the index of the PHMM state corresponding to pixel, x,y.
  • the two-dimensional pattern matcher 20 is presented in Figure 5.
  • Pattern matcher 20 comprises a windowing processor 5, a pixel- level Viterbi processor 6, a local-level score memory 7, and a shape-level Viterbi processor 8.
  • the windowing processor 5 receives the matrix signal, g(x,y), and extracts therefrom successive sequences of pixels, L 1 , L 2 , . . . , L M . As shown illustratively in the example of Figure 6, these sequences may be linear sequences of pixels.
  • the pixel-level Viterbi processor 6 determines for each pixel sequence Li and each group G j (comprising a pixel-level HMM) a local state score d ij . This is done by computing the Viterbi score of the linear sequence of pixels, L i , with the pixel-level linear HMM, G j .
  • An ⁇ G ⁇ M matrix of the local-level state scores is stored in memory 7.
  • the shape-level Viterbi processor 8 computes a global score for a given PHMM as the Viterbi score of a linear shape-level hidden Markov model using the sequence L i as the observation sequence and dy as the local state score for each shape-level state G j and each observation L i . Also, the state image, s (x,y), is computed using conventional backtracking methods for hidden Markov models.
  • the operations performed by the two-dimensional pattern matcher 20 are repeated for each PHMM in the PHMM memory 40.
  • recognition mode i.e., when switch R is closed and switch T is open
  • the decision processor 30 recognizes the scanned image as the character corresponding to the PHMM with the highest score, l h .
  • switch T is closed and switch R is open.
  • the training mode operation of the embodiment involves conventional Viterbi training of a linear hidden Markov model.
  • Known samples of all characters to be recognized are provided sequentially as input to scanner 10.
  • a state image s (x,y) is determined by the two-dimensional pattern matcher 20 as described above, using only the PHMM corresponding to the known sample. All known samples for the character are processed in this fashion, with each state image s (x,y ) stored in state image memory 35.
  • the probability estimation processor 45 estimates new transition and observation probabilities for the PHMM (as frequency counts) in conventional fashion taking into account the conditions c and d described above for the state transition probabilities.
  • Template matching is one of the many possible ways to solve this problem. According to this approach, each class is represented by a template (a reference pattern), and a new pattern is classified by selecting the class C k for which the distance D k between the new pattern and the class representative template is minimal, i.e.
  • the difficulty in the pattern recognition task arises because of the intra-class variability of the patterns. Methods have to be developed to reduce such variability, thereby building up some invariance properties for the classifier. This intra-class variability is sometimes caused by non-linear distortions during the generation process of the patterns. In speech recognition this problem is known as the 'time alignment' problem, and its source is the temporal variability of the spoken utterances.
  • the DTW procedure described below attempts to reduce the magnitude of this problem. The purpose of the procedure is to time-align the test and the reference patterns by stretching and contracting the test pattern to optimally match it to the reference, by minimizing a measure of the spectral distance D k between the time-aligned patterns, temporal distortions.
  • Z + is the set of positive integers
  • R" is the n-dimensional real space.
  • the goal of DTW is to find a mapping function that maps the test time scale to the reference time scale, such that the distortion
  • the procedure of finding the optimal mapping has an exponential complexity since there are O(T T R ) possible mappings in f. These mappings are shown as a set of paths in a time-time grid (Fig.1), where each path is a monotonically increasing curve that starts at point and ends at poin .
  • the DTW algorithm finds the optimal alignment curve among all possible paths in polynomial time, using the dynamical programming optimality principle.
  • the optimality principle is based on the fact that the optimal alignment curve (i.e., the one with the minimal distortion along the path) connecting point A to point B through point C is found among all curves that optimally connect A and C. This basic principle leads to an efficient iterative procedure for finding the optimal curve connecting A and B.
  • G ⁇ g(x,y):x ⁇ Z + ,y ⁇ Z + , (x,y) ⁇ L X,Y , g( ⁇ , ⁇ ) ⁇ G ⁇ R" ⁇ .
  • an (x,y) pair describes pixel location by horizontal and vertical coordinates
  • L N,M denotes a rectangular discrete lattice, i.e., a set of pixels .
  • Figure 2 shows a simple example of G R and G. This
  • planar warping is to map the test lattice to the reference one through a mapping function F: such that the distortion
  • ⁇ 0 is the empty set.
  • ⁇ is the empty set.
  • ⁇ n are pixels of the n-th row.
  • ⁇ to be a set of admissible warping sequences , where ⁇ i is a sequence of X reference pixels that meets the
  • This definition of the set ⁇ depends on the particular choice of the set ⁇ and the constraints (11a),(11b) and (12a). ⁇ is constructed to contain all possible warping sequences of each ⁇ n that satisfy the constraints.
  • N ⁇ O((X R Y R ) X ).
  • Each sequence ⁇ i ⁇ ⁇ determines a subset ⁇ i ⁇ of sequences
  • ⁇ i a candidate warping sequence for the n-th row of the test image
  • the preceding (n-1)-th row can be matched only with a warping sequence in ⁇ i in order to meet the vertical monotonicity condition (12b).
  • Figure 3 shows the concepts defined above, applied to the example of figure 2.
  • the set ⁇ is shown.
  • the set ⁇ includes in this case 16 sequences, shown in figure 3b.
  • the corresponding ⁇ i for each ⁇ i ⁇ ⁇ is also given.
  • F i,n a set of sub-mapping functions from the n-th test rectangle ⁇ n , 1 ⁇ n ⁇ N T , that satisfy the monotonicity conditions (12a) and (12b), boundary conditions (11a) , (11b) and (11c), and match the n-th row of the test ⁇ n with ⁇ i : for any
  • the optimal mapping F j,n is
  • the optimal warping of the n-th test rectangle has to be found for every warping sequence ⁇ j ⁇ ⁇ , thus requiring N ⁇ X operations.
  • the idea here is to limit the number of admissible warping sequences in ⁇ , or, equivalently, constrain the class of admissible mappings F in such a way that an optimal solution to the constrained problem can be found in polynomial time.
  • the additional constraints used are not arbitrary, but instead reflect the geometric properties of the specific set of images being compared. For example, we can constrain the possible mappings to be of the form
  • N ⁇ O(X X R Y)
  • the admissible warping sequences ⁇ ⁇ are naturally grouped into Y R subsets.
  • the second term of (25), is the distortion
  • the restricted formulation of the problem should reflect the geometry of the application.
  • the restriction (23) discussed here is only one among many possibilities.
  • the criterion that yields the minimal classification error is maximum a posteriori probability decoding: an unclassified pattern G is assigned to the class C k according to
  • G) can be rewritten as where P(G) is independent of C n and therefore can be ignored.
  • the prior class probability P(C n ) is generally attributed to higher level knowledge (e.g., syntactic knowledge). If such knowledge is not readily available, we usually assume a uniform class probability . Then the classification problem is that of maximizing
  • the i-th state, i ⁇ s is characterized by its probability distribution over G, P i (g). At each time t only one of the states is active, emitting the observable g(t).
  • a state sequence S defines a mapping from the observation time scale 1 ⁇ t ⁇ T to the active state at time t, 1 ⁇ s(t) ⁇ T R , that corresponds to the reference time scale 7 in the DTW approach.
  • the first term in provides a distortion measure, as in (2). For example, for a
  • Equation (3) and (4) of DTW A particular case of this model, called a left-to-right HMM, is especially useful for speech modeling and recognition.
  • the minimization (35) is, in effect, performed only among those state sequences that correspond to mappings satisfying conditions that are equivalent to (3) and (4).
  • the only difference between the minimization problem defined by (2), (3) and (4) and this one is the non-zero penalty term in (35).
  • the optimality principle can be applied to the minimization (35) in a manner similar to DTW as described in section 2.1.2.
  • Each state in s is a stochastic source characterized by its probability density over the space of observations g ⁇ G. It is convenient to think of the states of the model as being located on a rectangular lattice
  • the distortion measure D of DPW The second term, C, generalizes constraints (11), (12), and (23). In particular, by restricting the PHMM parameter values to be
  • the active state matrix S that minimizes (38) must satisfy conditions equivalent to (11), (12a) and (12c).
  • the PHMM constrained by (40) can be referred to as the left-to-right bottom-up PHMM, since it doesn't allow for "foldovers" in the state images.
  • the other boundary conditions (12b) and (12d) can be imposed on ⁇ by restricting the values of s (x,Y), 1 ⁇ x ⁇ X and s (X,y), 1 ⁇ y ⁇ Y,
  • the number of subsets, N G should be polynomial in the dimensions of the model X R , Y R .
  • the probabilities ⁇ A (i,j),(k,l),(m,n) ⁇ should satisfy the two following constraints with respect to such grouping: A (i,j),(k,l),(m,n) ⁇ 0 only if there exists p, 1 ⁇ p ⁇ N G, such that (i,j), (m,n) ⁇ ⁇ p . (42)
  • Condition (42) means that die the left neighbor of the state (m,n) in the state matrix S must be a member of the same group ⁇ p as (m,n).
  • the second constraint is:
  • the condition (43) makes the penalty term C independent of the horizontal warping.
  • Each subset ⁇ p of PHMM can be considered as a
  • one-dimensional HMM comprising the states , with transition
  • l ⁇ x ⁇ X R , y p ⁇ , 1 ⁇ p ⁇ Y r , then the constraints (42),(43) transform to
  • constraints (42) and (43) can be trivially changed by applying a coordinate transformation.
  • the PHMM approach was tested on a writer-independent isolated handwritten digit recognition application.
  • the data we used in our experiments was collected from 12 subjects (6 for training and 6 for test). The subjects were each asked to write 10 samples of each digit. Each sample was written in a fixed-size box, therefore the samples were naturally size-normalized and centered.
  • Figure 11 shows the 100 samples written by one of the subjects.
  • Each sample in the database was represented by a 16 ⁇ 16 binary image.
  • Each character class (digit) was represented by a single PHMM, satisfying (49) and (50).
  • Each PHMM had a strictly left-to-right bottom-up structure, where the state matrix 5 was restricted to contain every state of the model, i.e., states could not be skipped. All models had die same number of states.
  • Each state was represented by its own binary probability distribution, i.e., the probability of a pixel being 1 (black) or 0 (white).
  • Each iteration of the algorithm consisted of two stages: first, the samples were aligned with the corresponding model, by finding the best state matrix ⁇ . Then, a new frequency count for each state was used to update P i (1), according to the obtained alignment.
  • the recognition was performed as explained in section 3: The test sample was assigned to die class k for which was maximal.
  • Figure 12 shows three sets of models with different numbers of states.
  • the (6 ⁇ 6) state models have a very coarse representation of the digits, because the number of states is so small.
  • the (10 ⁇ 10) state models appear much sharper than the (16 ⁇ 16) state models, due to their ability to align the training samples.
  • a statistical model (the planar hidden Markov model - PHMM) was developed to provide a probabilistic formulation to the planar warping problem.
  • This model on one hand, generalizes the single-dimensional HMM to die planar case, and on the other extends the DPW approach.
  • the restricted formulation of the warping problem corresponds to PHMM with constrained transition probabilities.
  • the PHMM approach was tested on an isolated, hand-written digit recognition application, yielding 95% digit recognition. Further analysis of the results indicate that even in a simple case of isolated characters, the elimination of planar distortions enhances recognition performance significantly. We expect that the advantage of this approach will be even more valuable in harder tasks, such as cursive writing recognition/spotting, for which an effective solution using the current available techniques has not yet been found.
  • Figure 1 Time-time grid. Abscissa: test time scale l ⁇ r ⁇ T. Ordinate: reference time scale 1 ⁇ t ⁇ T R . Any monotonically increasing curve connecting point A to point B corresponds to a mapping f ⁇ f .
  • FIG. 2 Example of warping problem.
  • G R is a 2 ⁇ 2 reference image, and G is a 3 ⁇ 3 test image. Inside each pixels are shown its 9x,y) coordinates. The value of the image g( ⁇ ,y) is encoded by texture, as shown.
  • Figure 3 Illustration of the definitions of ⁇ , ⁇ ,and ⁇ for the example of figure 2.
  • Figure 4 Illustration of the two-dimensional warping algorithm on the example of figure 2.
  • the table shows the values of D i,n for 1 ⁇ i ⁇ 16 and 1 ⁇ n ⁇ 3, calculated according to the DPW algorithm.
  • Figure 5 Illustration of the constrained DPW algorithm for the example of. figure 2.
  • the table shows the values of for 1 ⁇ k ⁇ 2 and 1 ⁇ n ⁇ 3. In this case the obtained solution is the same as in figure 4.
  • Figure 6 Example of a test image G for which the optimal mapping obtained according to the general DPW formulation differs from the one obtained according to the restricted formulation.
  • Figure 7 Illustration of the planar Markov property. The probability of a state in the light grey pixel given the states of all the dark grey pixels in (a) equals the probability of a state in the light grey pixel given the states of only two dark pixels in (b).
  • Figure 8 two groupings of the 4 ⁇ 4 PHMM states into subsets.
  • Figure 9 Equivalent representation of constrained PHMM, for the grouping of figure 8a.
  • Figure 10 Illustration of the algorithm for the case of figure 8a.
  • Figure 11 The 100 samples of the digits from one subject.
  • Figure 12 The digit models obtained by training, for different number of states.
  • N G mutually exclusive subsets

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

L'invention se rapporte à un procédé de reconnaissance d'image, qui consiste à mémoriser une multiplicité de modèles de Markov (60) cachés bidimensionnels, dont chacun comprend un modèle de Markov de niveau de forme caché et à une dimension, présentant un ou plusieurs états de niveau de forme, chaque état de niveau de forme comprenant un modèle de Markov de niveau de pixel caché et à une dimension, lequel présente un ou plusieurs états de niveau de pixel. Une image est balayée pour produire au moins une séquence de pixels. Pour un modèle de Markov caché et bidimensionnel mémorisé, des scores de Viterbi locaux pour une multiplicité de modèles de Markov de niveau de pixel cachés bidimensionnels sont déterminés en ce qui concerne chaque séquence de pixels (6). Un score de Viterbi global d'un modèle de Markov de niveau de forme caché est déterminé en fonction d'une multiplicité de scores de Viterbi locaux et des séquences de pixels. L'image balayée est reconnue en fonction d'un ou plusieurs scores de Viterbi globaux.
PCT/US1993/001843 1992-03-02 1993-03-02 Procede et appareil de reconnaissance d'image WO1993018483A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US84481092A 1992-03-02 1992-03-02
US07/844,810 1992-03-02

Publications (1)

Publication Number Publication Date
WO1993018483A1 true WO1993018483A1 (fr) 1993-09-16

Family

ID=25293690

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US1993/001843 WO1993018483A1 (fr) 1992-03-02 1993-03-02 Procede et appareil de reconnaissance d'image

Country Status (1)

Country Link
WO (1) WO1993018483A1 (fr)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5933525A (en) * 1996-04-10 1999-08-03 Bbn Corporation Language-independent and segmentation-free optical character recognition system and method
WO1999052074A1 (fr) * 1998-04-03 1999-10-14 The University Of Queensland Procede de segmentation non dirigee de noyaux cellulaires
AU748081B2 (en) * 1998-04-03 2002-05-30 Cea Technologies Pty Limited Method of unsupervised cell nuclei segmentation
US7327883B2 (en) 2002-03-11 2008-02-05 Imds Software Inc. Character recognition system and method
US7890539B2 (en) 2007-10-10 2011-02-15 Raytheon Bbn Technologies Corp. Semantic matching using predicate-argument structure
US8280719B2 (en) 2005-05-05 2012-10-02 Ramp, Inc. Methods and systems relating to information extraction
US8326087B2 (en) 2008-11-25 2012-12-04 Xerox Corporation Synchronizing image sequences
CN109002821A (zh) * 2018-07-19 2018-12-14 武汉科技大学 一种基于连通域和切线斜率的网银盾数字识别方法
US11163993B2 (en) 2017-07-07 2021-11-02 Hewlett-Packard Development Company, L.P. Image alignments via optical character recognition

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4593367A (en) * 1984-01-16 1986-06-03 Itt Corporation Probabilistic learning element
US4599692A (en) * 1984-01-16 1986-07-08 Itt Corporation Probabilistic learning element employing context drive searching
US4599693A (en) * 1984-01-16 1986-07-08 Itt Corporation Probabilistic learning system
US4620286A (en) * 1984-01-16 1986-10-28 Itt Corporation Probabilistic learning element

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4593367A (en) * 1984-01-16 1986-06-03 Itt Corporation Probabilistic learning element
US4599692A (en) * 1984-01-16 1986-07-08 Itt Corporation Probabilistic learning element employing context drive searching
US4599693A (en) * 1984-01-16 1986-07-08 Itt Corporation Probabilistic learning system
US4620286A (en) * 1984-01-16 1986-10-28 Itt Corporation Probabilistic learning element

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5933525A (en) * 1996-04-10 1999-08-03 Bbn Corporation Language-independent and segmentation-free optical character recognition system and method
WO1999052074A1 (fr) * 1998-04-03 1999-10-14 The University Of Queensland Procede de segmentation non dirigee de noyaux cellulaires
AU748081B2 (en) * 1998-04-03 2002-05-30 Cea Technologies Pty Limited Method of unsupervised cell nuclei segmentation
US6681035B1 (en) 1998-04-03 2004-01-20 Cssip (Cooperative Research Centre For Sensor Signal And Information Processing) Method of unsupervised cell nuclei segmentation
US7327883B2 (en) 2002-03-11 2008-02-05 Imds Software Inc. Character recognition system and method
US8280719B2 (en) 2005-05-05 2012-10-02 Ramp, Inc. Methods and systems relating to information extraction
US7890539B2 (en) 2007-10-10 2011-02-15 Raytheon Bbn Technologies Corp. Semantic matching using predicate-argument structure
US8326087B2 (en) 2008-11-25 2012-12-04 Xerox Corporation Synchronizing image sequences
US11163993B2 (en) 2017-07-07 2021-11-02 Hewlett-Packard Development Company, L.P. Image alignments via optical character recognition
CN109002821A (zh) * 2018-07-19 2018-12-14 武汉科技大学 一种基于连通域和切线斜率的网银盾数字识别方法
CN109002821B (zh) * 2018-07-19 2021-11-02 武汉科技大学 一种基于连通域和切线斜率的网银盾数字识别方法

Similar Documents

Publication Publication Date Title
Cai et al. Integration of structural and statistical information for unconstrained handwritten numeral recognition
Hu et al. Writer independent on-line handwriting recognition using an HMM approach
Nefian et al. Face detection and recognition using hidden Markov models
US5343537A (en) Statistical mixture approach to automatic handwriting recognition
US7697760B2 (en) Handwritten word recognition using nearest neighbor techniques that allow adaptive learning
US5075896A (en) Character and phoneme recognition based on probability clustering
EP0605099B1 (fr) Reconnaissance de texte utilisant des modèles stochastiques bi-dimensionnels
Kosmala et al. On-line handwritten formula recognition using statistical methods
Rabi et al. Recognition of cursive Arabic handwritten text using embedded training based on hidden Markov models
Wong et al. Off-line handwritten Chinese character recognition as a compound Bayes decision problem
WO1993018483A1 (fr) Procede et appareil de reconnaissance d'image
Retsinas et al. An alternative deep feature approach to line level keyword spotting
Kim et al. Off-line recognition of handwritten Korean and alphanumeric characters using hidden Markov models
Perronnin et al. A probabilistic model of face mapping with local transformations and its application to person recognition
Kumar et al. Bayesian background models for keyword spotting in handwritten documents
Zhu et al. Online handwritten Chinese/Japanese character recognition
Xiong et al. A discrete contextual stochastic model for the off-line recognition of handwritten Chinese characters
Schukat-Talamazzini et al. Optimal linear feature transformations for semi-continuous hidden Markov models
Nopsuwanchai et al. Maximization of mutual information for offline Thai handwriting recognition
Kumar et al. A Bayesian approach to script independent multilingual keyword spotting
Levin et al. Planar Hidden Markov modeling: from speech to optical character recognition
Lee et al. Hybrid simulated annealing and its application to optimization of hidden Markov models for visual speech recognition
Uchida et al. Handwritten character recognition using monotonic and continuous two-dimensional warping
Kosmala et al. Recognition of on-line handwritten formulas
Biem Minimum classification error training of hidden Markov models for handwriting recognition

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): CA JP US

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): DE FR GB IT

CFP Corrected version of a pamphlet front page
CR1 Correction of entry in section i

Free format text: PAT.BUL.22/93 "AMERICAN TELEPHONE AND TELEGRAPH COMPANY" SHOULD APPEAR UNDER INID (71) APPLICANT AND "ERREUR CODE DEPOSANT BFG" SHOULD BE DELETED;LEVIN,ESTHER AND PIERACCINI ROBERTO SHOULD APPEAR UNDER INID (72) INVENTORS AND "ERREUR CODE DEPOSANT BFG" SHOULD BE DELETED;UNDER INID (81) DESIGNATED STATES DELETE "US"

122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase

Ref country code: CA