Handwritten Numeral Strings Research Articles

Recognition of Two Connected Handwritten Digits Based on User-Defined Algorithm

The present paper proposes a model for recognizing unconstrained offline two connected handwritten Numeral digit strings. The Numeral strings are segmented and isolated numerals are obtained using sliding window approach with user defined algorithm. Hence the present paper proposes a segmentation-recognition system using the sliding window approach with user defined classifier. The sliding window is used for discovery the interconnection spots and optimal angle for cutting the adjacent digits at the same time and a minimum of 5 features are extracted from each isolated digit for classification. The exploratory outcomes directed on a recently gathered database of manually written digits and got promising results. The overall efficiency obtained using the proposed method is about 98.51%.

Unknown-Length Handwritten Numeral String Recognition Using Cascade of PCA-SVMNet Classifiers

Automatic recognition of handwritten digit string with unknown length has many potential real applications. The most challenging step in this problem is how to efficiently segment connected and/or overlapped digits exhibited in the input image. Most existing numeral string segmentation approaches combine several segmentation hypotheses to handle various types of connected digits. This paper proposes a new handwritten digit string recognition without applying any explicit segmentation techniques. The proposed method uses a new cascade of hybrid principal component analysis network (PCANet) and support vector machine (SVM) classifier called PCA-SVMNet. PCANet is an emerging unsupervised simple deep neural network typically with only two convolutional layers. The proposed PCA-SVMNet model adds a new fully connected layer trained separately using SVM optimization method. Cascaded stages of PCA-SVMNet classifiers are constructed and trained to recognize various types of isolated and connected digits. Every PCA-SVMNet classifier is trained separately using combinations of real and synthetic touching digits. The first 1D-PCA-SVMNet stage is trained to recognize isolated handwritten digits (0...9) while forwarding non-isolated digits to the next stages. Each of the following stages is designed to recognize a class of connected digits and forwards the higher class to its successor. Multiple stages can be added accordingly to classify more complex touching digits. The experimental results using NIST SD19 real dataset show that the cascade of PCA-SVMNet classifier efficiently recognizes unknown handwritten digit string without applying any sophisticated segmentation methods. The proposed method achieves state-of-the-art recognition accuracy compared to other segmentation-free techniques.

STATISTICAL CHARACTERISTICS OF SLANT ANGLES IN HANDWRITTEN NUMERAL STRINGS AND EFFECTS OF SLANT CORRECTION ON SEGMENTATION

A novel and efficient method for correction of slant angles in handwritten numeral strings is proposed. For the first time, the statistical distribution of slant angles in handwritten numerals is investigated and the effects of slant correction on the segmentation of handwritten numeral strings are shown. In our proposed slant correction method, utilizing geometric features, a Component Slant Angle (CSA) is estimated for each connected component independently. A weighted average is then used to compute the String Slant Angle (SSA), which is applied uniformly to correct the slant of all the components in numeral strings. Our experimental results have revealed novel statistics for slant angles of handwritten numeral strings, and also showed that slant correction can significantly improve extraction of segmentation features and segmentation accuracy of touching numerals. Comparison between our slant correction algorithm and similar algorithms in the literature show that our algorithm is more efficient, and on average it has a faster running time.

The segmentation algorithm for handwritten numeral strings in bank-check recognition

In this paper, an integrated system of segmenting unconstrained handwritten numeral strings with unknowing number of digits is proposed, which consists of the extraction of connected components based on vertical projection and isolated components analysis, the length estimation of connected components using syntax analysis and waveform analysis and the segmentation of unconstrained connected handwritten numeral strings using innovative reverse “drop-falling” algorithm. This segmentation system which has promising results is then incorporated into a complete bank check character recognition system.

A genetic framework using contextual knowledge for segmentation and recognition of handwritten numeral strings

For the first time, a genetic framework using contextual knowledge is proposed for segmentation and recognition of unconstrained handwritten numeral strings. New algorithms have been developed to locate feature points on the string image, and to generate possible segmentation hypotheses. A genetic representation scheme is utilized to show the space of all segmentation hypotheses (chromosomes). For the evaluation of segmentation hypotheses, a novel evaluation scheme is introduced, in order to improve the outlier resistance of the system. Our genetic algorithm tries to search and evolve the population of segmentation hypotheses, and to find the one with the highest segmentation/recognition confidence. The NIST NSTRING SD19 and CENPARMI databases were used to evaluate the performance of our proposed method. Our experiments showed that proper use of contextual knowledge in segmentation, evaluation and search greatly improves the overall performance of the system. On average, our system was able to obtain correct recognition rates of 95.28% and 96.42% on handwritten numeral strings using neural network and support vector classifiers, respectively. These results compare favorably with the ones reported in the literature.

Handwritten Numeral String Recognition: Effects of Character Normalization and Feature Extraction

The performance of integrated segmentation and recognition of handwritten numeral strings relies on the classification accuracy and the non-character resistance of the underlying character classifier, which is variable depending on the techniques of pattern normalization, feature extraction, and classifier structure. In this paper, we evaluate the effects of 12 normalization functions and four selected feature types on numeral string recognition. Slant correction (deslant) is combined with the normalization functions and features so as to create 96 feature vectors, which are classified using two classifier structures. In experiments on numeral string images of the NIST Special Database 19, the classifiers have yielded very high string recognition accuracies. We show the superiority of moment normalization with adaptive aspect ratio mapping and the gradient direction feature, and observed that slant correction is beneficial to string recognition when combined with good normalization methods.

Effects of classifier structures and training regimes on integrated segmentation and recognition of handwritten numeral strings

In integrated segmentation and recognition of character strings, the underlying classifier is trained to be resistant to noncharacters. We evaluate the performance of state-of-the-art pattern classifiers of this kind. First, we build a baseline numeral string recognition system with simple but effective presegmentation. The classification scores of the candidate patterns generated by presegmentation are combined to evaluate the segmentation paths and the optimal path is found using the beam search strategy. Three neural classifiers, two discriminative density models, and two support vector classifiers are evaluated. Each classifier has some variations depending on the training strategy: maximum likelihood, discriminative learning both with and without noncharacter samples. The string recognition performances are evaluated on the numeral string images of the NIST Special Database 19 and the zipcode images of the CEDAR CDROM-1. The results show that noncharacter training is crucial for neural classifiers and support vector classifiers, whereas, for the discriminative density models, the regularization of parameters is important. The string recognition results compare favorably to the best ones reported in the literature though we totally ignored the geometric context. The best results were obtained using a support vector classifier, but the neural classifiers and discriminative density models show better trade-off between accuracy and computational overhead.

The recognition of handwritten numeral strings using a two-stage HMM-based method

In this paper, a two-stage HMM-based recognition method allows us to compensate for the possible loss in terms of recognition performance caused by the necessary trade-off between segmentation and recognition in an implicit segmentation-based strategy. The first stage consists of an implicit segmentation process that takes into account some contextual information to provide multiple segmentation-recognition hypotheses for a given preprocessed string. These hypotheses are verified and re-ranked in a second stage by using an isolated digit classifier. This method enables the use of two sets of features and numeral models: one taking into account both the segmentation and recognition aspects in an implicit segmentation-based strategy, and the other considering just the recognition aspects of isolated digits. These two stages have been shown to be complementary, in the sense that the verification stage compensates for the loss in terms of recognition performance brought about by the necessary tradeoff between segmentation and recognition carried out in the first stage. The experiments on 12,802 handwritten numeral strings of different lengths have shown that the use of a two-stage recognition strategy is a promising idea. The verification stage brought about an average improvement of 9.9% on the string recognition rates. On touching digit pairs, the method achieved a recognition rate of 89.6%.

Segmentation of connected handwritten numeral strings

A new approach to separating single touching handwritten digit strings is presented. The image of the connected numerals is normalized, preprocessed and then thinned before feature points are detected. Potential segmentation points are determined based on decision line that is estimated from the deepest/highest valley/hill in the image. The partitioning path is determined precisely and then the numerals are separated before restoration is applied. Experimental results on the NIST Database 19, CEDAR CD-ROM and our own collection of images show that our algorithm can get a successful recognition rate of 96%, which compares favorably with those reported in the literature.

Impacts of verification on a numeral string recognition system

In this paper we discuss the use of high-level verification on handwritten numeral strings. First of all, we introduce the concept of levels of verification and present the baseline system used to carry out the experiments. Two different strategies were developed: absolute and one-to-one verifiers. A thorough error analysis is also presented in order to identify under which conditions high-level verification is more appropriate. Experimental results are presented on NIST SD19 database.

Segmentation of single- or multiple-touching handwritten numeral string using background and foreground analysis

An approach of segmenting a single- or multiple-touching handwritten numeral string (two-digits) is proposed. Most algorithms for segmenting connected digits mainly focus on the analysis of foreground pixels. Some concentrated on the analysis of background pixels only and others are based on a recognizer. We combine background and foreground analysis to segment single- or multiple-touching handwritten numeral strings. Thinning of both foreground and background regions are first processed on the image of connected numeral strings and the feature points on foreground and background skeletons are extracted. Several possible segmentation paths are then constructed and useless strokes are removed. Finally, the parameters of geometric properties of each possible segmentation paths are determined and these parameters are analyzed by the mixture Gaussian probability function to decide the best segmentation path or reject it. Experimental results on NIST special database 19 (an update of NIST special database 3) and some other images collected by ourselves show that our algorithm can get a correct rate of 96 percent with rejection rate of 7.8 percent, which compares favorably with those reported in the literature.

Construction of partitioning paths for touching handwritten characters

In this paper we propose a new approach to the determination of the partitioning paths for handwritten numeral strings. The average stroke width of the connected numerals is estimated first, and then three algorithms are developed to deal with three different situations. Instead of using one partitioning path for each area of contact, we use two partitioning paths to ensure that the recovered strokes have at least the average stroke width. Experiments show that by using this new approach, the strokes can be recovered satisfactorily.

Separation of single- and double-touching handwritten numeral strings based on structural analysis

We develop a new method to separate touching handwritten numeral pairs using structural analysis. The string is preprocessed with an efficient algorithm for smoothing, linearization, and detection of structural points of image contours. The structural region of the string is determined. Some left- or right-side numerals of the string are recognized. The property of each hole contour in a string is detected. The touching model of a string is determined, whether single- or double-touching. For double-touching, the touching hole contour is determined. For the two touching models, the touching point is preselected, its position is corrected, and the corresponding match touching point is found. The string is separated based on all touching points. All processing procedures are based on morphological structural analyses. We have tested our method on image samples taken from the U.S. National Institute of Science and Technology (NIST) database. We used 500 sample images to design the required models. For 3287 test samples the correct-separation rate was 97.2% for single-touching strings, and 97% for double-touching strings.

SEPARATION OF SINGLE-TOUCHING HANDWRITTEN NUMERAL STRINGS BASED ON STRUCTURAL FEATURES

In this paper, we develop a new method to separate single-touching handwritten numeral strings with two numerals using structural features. A binary image of a single-touching handwritten numeral string is preprocessed with an efficient algorithm for smoothing, linearization and detection of structural points of image contours. The touching region of a single-touching handwritten numeral string is determined based on distribution of the structural points in the handwritten numeral string. A candidate touching point is preselected based on the geometrical information of a special structural point in the touching region. In some cases, the left or right lateral numeral of a single-touching handwritten numeral string can be recognized. The recognition information can be utilized to correct the position of the candidate touching point. We have tested our method on image samples taken from the U.S. National Institute of Science and Technology (NIST) database. We used 500 sample images for training and obtained a correct separation rate of 99.1%. For 3287 test samples not used for training the correct separation rate was 97.2%.

A Model-Based Segmentation Method for Handwritten Numeral Strings

Segmentation of handwritten touching characters is an important task in optical character recognition (OCR). A new model-based segmentation algorithm is proposed for handwritten numeral strings. This method is based on the boundary analysis of the numeral strings, where a set of new features are extracted. These features can be used for global interpretation of the boundary structures. Various models are then constructed for the common touching patterns, which can increase the reliability of the segmentation and reduce the segmentation time. While we concentrate on the description of the segmentation method for two single-touching digits in this paper, our method can be extended to segmentation of touching digits in other situations.

Off-line handwritten numeral string recognition by combining segmentation-based and segmentation-free methods

We propose an off-line system for the recognition of handwritten numeral strings. The system is built upon four main components. A presegmentation module divides the input numeral string into independent groups of digits which are processed by a cascade of two recognition methods. The digit detection module identifies and recognizes groups containing isolated digits and a segmentation-free module recognizes the remaining groups containing an arbitrary number of digits. The global decision module merges all results and makes an accept/reject decision. Experimental results on data from both the CEDAR and NIST SD3 database compare favorably to other published methods.

Segmentation and recognition of connected handwritten numeral strings

A new segmentation method for segmenting connected handwritten digit strings is presented. Unlike traditional methods where segmentation points are uniquely determined to cut the piece of stroke joining the connected numerals, our approach is one of identifying regions which serve as potential segmentation points. The regions are identified by a thorough analysis of the trajectory of strokes.

A Fault-Tolerant Chinese Check Recognition System

In this paper, a complete fault-tolerant check recognition system is proposed which has no check substitution error under the secret code verification. The fault-tolerant recognition method proposed in this paper creates all possible candidates for verification under the limited fault-tolerant rate, and with three classifiers of high isolated digit recognition rate, the system can always find out the correct recognition results of checks if there exist the correct labels of all the digits. Since the three classifiers are designed independently by different methods and they extract different features of handwritten digits, they can compensate each other when confusing digits are met. The segmentation stage combines the three most popular strategies, and gives out a way for segmenting unconstrained handwritten numeral strings on Chinese checks.

Separation of single- and double-touching handwritten numeral strings

To improve overall separation and classification performance for touching handwritten numeral strings, we have to deal with double-touching problems, which occur particularly for some combinations of digits. We propose a strategy to separate single- and double-touching numerical strings. The proposed technique includes: using two-cut links to deal with double-touching problems; using weighted geometric-property measures to rank both one- and two-cut links; and using a rejection scheme to reject poor links at both ranking and recognition stages. Two-cut link pairs that join the high-curvature points in inner contour(s) to those in the external contour are considered when all one-cut links that join the upper and the lower external contours fail to separate them. All combinations of one- and two-cut links are ranked according to weighted geometric-property measures, and the top links are chosen and tested by the recognition system. Experimental results on the National Institute of Standards and Technology database show that our system for solving both single- and double-touching problems compares favorably with the other techniques tested.

Vertex directed segmentation of handwritten numerals

A new algorithm is described for segmenting handwritten numeral strings that contain pairs of simply connected numerals. The algorithm identifies the location of a connection through analysis of the vertices that are formed by the convergence of vertically oriented edges of adjacent strokes. The connected numerals are then partitioned by a cut based at the vertices associated with the connection. A complete partitioning path is constructed by extending the cut to the top and bottom of the numerals. The algorithm has proved to be fast, effective, and relatively insensitive to the presence of dropouts and variations of size and baseline.