Handprinted Characters Research Articles

Hand Printed Characters Recognition Using Wavelet Features and Neural Networks.(Dept.E)

Simplifying automatic recognition algorithms for hand-printed characters attracted immense research efforts [1-3]. Character recognition systems can improve the interaction between man and machine in many applications, including office automation, business and data entry applications. This paper introduces the use of bi-dimensional wavelet as features extractor that is feed to Artificial Neural Networks (ANNs) for recognition Latin hand-printed characters. An experiment to verify the efficiency of the system was performed. The proposed technique can be divided into three major steps: the first step is pre-processing in which the original image is transformed into a digitized image utilizing a 300 dpi scanner. Second, feature extraction using wavelets Finally, multilayer artificial neural network is used for characters recognition.

Hybrid Wavelet based Technique for Text Extraction from Images

This paper reviews the current state of the art in handwriting recognition research. The paper deals with issues such as hand-printed character and cursive handwritten word recognition. It describes recent achievements, difficulties, successes and challenges in all aspects of handwriting recognition.

Character recognition based on non-linear multi-projection profiles measure

In this paper, we study a method for isolated handwritten or hand-printed character recognition using dynamic programming for matching the non-linear multi-projection profiles that are produced from the Radon transform. The idea is to use dynamic time warping (DTW) algorithm to match corresponding pairs of the Radon features for all possible projections. By using DTW, we can avoid compressing feature matrix into a single vector which may miss information. It can handle character images in different shapes and sizes that are usually happened in natural handwriting in addition to difficulties such as multi-class similarities, deformations and possible defects. Besides, a comprehensive study is made by taking a major set of state-of-the-art shape descriptors over several character and numeral datasets from different scripts such as Roman, Devanagari, Oriya, Bangla and Japanese-Katakana including symbol. For all scripts, the method shows a generic behaviour by providing optimal recognition rates but, with high computational cost.

Improving Various Offline Techniques used for Handwritten Character Recognition : A Review

character recognition is always an advanced area of research in the field of image processing and pattern recognition and there is a large demand for OCR on offline hand written documents. Even though, sufficient studies have performed from history to this era, paper describes the techniques for converting textual content from a paper document into machine readable form. The computer actually recognizes the characters in the document through a revolutionizing technique called Optical Character Recognition (OCR). There are many paper deals with issues such as hand-printed character and cursive handwritten word recognition which describes recent achievements, difficulties, successes and challenges in all aspects of handwriting recognition. Their many papers present a new approach which improves current handwriting recognition systems. Some experimental results are included. Selection of a relevant feature extraction method is probably the single most important factor in achieving high recognition performance with much better accuracy in character recognition systemsn this paper, we describe the formatting guidelines for IJCA Journal Submission.

Structural Description to Recognizing Hand-Printed Arabic Characters Using Decision Tree Learning Techniques

Character recognition systems can contribute tremendously to the advancement of the automation process and can improve the interaction between man and machine in many applications, including office automation, cheque verification, and a large variety of banking, business, and data entry applications. The main theme of this paper is the automatic recognition of hand-printed Arabic characters using machine learning. Conventional methods have re-lied on hand-constructed dictionaries that are tedious to construct and difficult to make tolerant to variation in writing styles. The advantages of machine learning are that it can generalize over the large degree of variation between writing styles and recognition rules can be constructed by example. The system was tested on a sample of handwritten characters from several individuals whose writing quality ranged from acceptable to poor. The average recognition rate obtained using cross-validation was 87.23%.

Off-line isolated handwritten Thai OCR using island-based projection with n-gram model and hidden Markov models

Many traditional works on off-line Thai handwritten character recognition used a set of local features including circles, concavity, endpoints and lines to recognize hand-printed characters. However, in natural handwriting, these local features are often missing due to rough or quick writing, resulting in dramatic reduction of recognition accuracy. Instead of using such local features, this paper presents a method called multi-directional island-based projection to extract global features from handwritten characters. As the recognition model, two statistical approaches, namely interpolated n-gram model ( n-gram) and hidden Markov model (HMM), are proposed. The experimental results indicate that the proposed scheme achieves high accuracy in the recognition of naturally-written Thai characters with numerous variations, compared to some common previous feature extraction techniques. Another experiment with English characters also displays quite promising results.

Recognition of hand-printed characters based on structural description and inductive logic programming

Character recognition systems can contribute tremendously to the advancement of the automation process and can improve the interaction between man and machine in many applications, including office automation, cheque verification and a large variety of banking, business and data entry applications. The main theme of this paper is the automatic recognition of hand-printed Arabic characters using machine learning . Conventional methods have relied on hand-constructed dictionaries which are tedious to construct and difficult to make tolerant to variation in writing styles. The advantages of machine learning are that it can generalize over the large degree of variation between writing styles and recognition rules can be constructed by example. The system was tested on a sample of handwritten characters from several individuals whose writing ranged from acceptable to poor in quality and the average correct recognitions rate obtained using cross-validation was 86.65%.

Pattern classification by a condensed neural network

Neural networks have come to the fore as potent pattern classifiers. More amenable to parallel computation, they are much faster than the nearest neighbor classifier (NN), which, however, has distinctly outperformed them in several applications. The purpose of this study is to investigate a condensed neural network that combines the classification speed of neural networks and the low error rate of the nearest neighbor classifier. This condensed network is a fast, accurate classifier of simple architecture and function: it consists of a set of generalized perceptrons that draw maximal hyperspherical boundaries centered on patterns of memory units, each circumscribing reference patterns of a single category. The generalized perceptrons carry out classification, assisted by sporadic nearest neighbor matching to patterns of a small reference set. We compare the condensed network to a high performance neural network pattern classifier (Kohonen) and to NN in experiments on hand-printed character recognition.

A fuzzy approach to 2D-shape recognition

This paper describes a method for fuzzy classification and recognition of 2D shapes, such as handwritten characters, image contours, etc. A fuzzy model is derived for each considered shape from a fuzzy description of a set of instances of this shape. A fuzzy description of a shape instance, in its turn, exploits appropriate fuzzy partitions of the two dimensions of the shape. These fuzzy partitions allow us to identify, and automatically associate an importance degree with the relevant shape zones for classification and recognition purposes. Two significant applications of the method are described, namely, recognition of olfactory signals and recognition of isolated, handwritten characters. In the former case, results are shown concerning the recognition of three different types of waste waters, collected in three different dilutions. In the latter case, results are shown concerning the application of the method to a NIST database, containing the segmented handprinted characters of 500 writers.

RECOGNITION OF HAND-PRINTED LATIN CHARACTERS BASED ON GENERALIZED HOUGH TRANSFORM AND DECISION TREE LEARNING TECHNIQUES

This paper presents a new technique for the recognition of hand-printed Latin characters using machine learning. Conventional methods have relied on manually constructed dictionaries which are not only tedious to construct but also difficult to make tolerant to variation in writing styles. The advantages of machine learning are that it can generalize over a large degree of variation between writing styles, and recognition rules can be constructed by example. Characters are scanned into the computer and preprocessing techniques transform the bit-map representation of the characters into a set of primitives which can be represented in an attribute base form. A set of such representations for each character is then input to C4.5 which produces a decision tree for classifying each character.

Design of an interface on PDA for Korean

We present an on-line recognition system of cursive Korean character on a PDA. Because of the limited storage capacity and small size of the PDA, a more compact and more convenient design is needed in an embedded user interface, like the on-line character recognition system. To make a convenient interface, the character recognition system has to recognize the cursive type of Korean characters. We define a cursive type of Korean characters as the connection of primitive strokes. We use the path discriminant HMM (PDHMM). The initial structure of the PDHMM is designed from the hand-printed characters and then it is expanded to the cursive case. When new strokes for the cursive type are defined, we can easily extend the PDHMM by inserting proper edges. To save the storage space of the PDA, character recognition is done simply with traversing a single PDHMM. We make smaller states for the PDHMM than the ones for other HMMs. We implemented it on a handheld PC (HPC) and got a good recognition rate.

Prototyping structural description using an inductive learning program

Character recognition systems can contribute tremendously to the advancement of the automation process and can improve the interaction between man and machine in many applications, including office automation, check verification and a large variety of banking, business and data entry applications. The main theme of the paper is the automatic recognition of hand-printed Arabic characters using machine learning. Conventional methods have relied on hand-constructed dictionaries which are tedious to construct and difficult to make tolerant to variation in writing styles. The advantages of machine learning are that it can generalize over the large degree of variation between writing styles and recognition rules can be constructed by example. The system was tested on a sample of handwritten characters from several individuals whose writing ranged from acceptable to poor in quality and the correct average recognition rate obtained using cross-validation was 89.65%.

An analytic approach for generation of artificial hand-printed character database from given generative models

A large database which incorporates every possible variations, is required for training/testing of any handwritten character recognition system. Collecting natural samples is not convenient in many cases. This necessitates generation of characters artificially in such a way that the various instances of the characters generated resemble natural samples, and the variation distribution conforms to that of human writings. In this paper, we describe an analytic approach for character generation from given generative models. A character is split into several lines and arcs. A set of equations and parameters describing these lines and arcs, completely defines the character. These parameters are specified as the average of them derived from a collection of natural samples. The parameter values are randomly modulated to create variations in the structure of the character. The pattern is then subjected to affine transform and dilation by different transform matrices and structuring elements, respectively. Thus, the size, aspect ratio, orientation, position and thickness are varied from instance to instance. A test comparing the nature of distribution of the samples generated by this approach to that of natural samples shows a close agreement between them. This validates the utility of the proposed character generation technique.

Winner-Take-All Network Utilising Pseudoinverse Reconstruction Subnets Demonstrates Robustness on the Handprinted Character Recognition Problem

Wittmeyer’s pseudoinverse iterative algorithm is formulated as a dynamic connectionist Data Compression and Reconstruction (DCR) network, and subnets of this type are supplemented by the winner-take-all paradigm. The winner is selected upon the goodness-of-fit of the input reconstruction. The network can be characterised as a competitive-cooper-ative-competitive architecture by virtue of the contrast enhancing properties of the pseudoinverse subnets. The network is capable of fast learning. The adopted learning method gives rise to increased sampling in the vicinity of dubious boundary regions that resembles the phenomenon of categorical perception. The generalising abilities of the scheme allow one to utilise single bit connection strengths. The network is robust against input noise and contrast levels, shows little sensitivity to imprecise connection strengths, and is promising for mixed VLSI implementation with on-chip learning properties. The features of the DCR network are demonstrated on the NIST database of handprinted characters.

Neural Network Recognition of Hand-printed Characters

Character recognition systems can contribute tremendously to the advancement of the automation process, and can improve the interaction between man and machine in many applications, including office automation, cheque verification and a large variety of banking, business and data entry applications.The main theme of this paper is the automatic recognition of hand-printed Latin characters using artificial neural networks in combination with conventional techniques. This approach has a number of advantages: it combines rule-based (structural) approach for feature extraction and non-linea classification tests for recognition; it is more efficient for large and complex data sets; feature extraction is inexpensive and execution time is independent of handwriting style and size. The technique can be divided into three major steps: The first step is pre-processing in which the original image is transformed into a binary image utilising a 300 dpi scanner and then thinned using a parallel thinning algorithm. Second, the image-skeleton is traced from left to right in order to build a binary tree. Some primitives, such as Straight lines, Curves and Loops, are extracted from the binary tree. Finally, a three layer artificial neural network is used for character classification. The system was tested on a sample of handwritten characters from several individuals whose writing ranged from acceptable to poor in quality and the correct average recognition rate obtained using cross-validation was 86%.

Selective feature-to-feature adhesion for recognition of cursive handprinted characters

A structural-feature-to-structural-feature configuration is naturally constructed using a set of sampled features from a cursive pattern. These features are sampled by maximally fitting bent ellipses in local strokes. This configuration is transformed into an undirected graph to resolve the asymmetric difficulty. The compatibility associated with the graph is further formulated into a devised Hopfield network, where both interfeature and interlink similarities are incorporated into the compatibility. We operate this network to recognize a radical as a whole in a handprinted pattern to accomplish the selective attention task.

A performance comparison of two handwriting recognizers

An experiment is described comparing two commercial handwriting recognizers with discrete hand-printed characters. Each recognizer was tested at two levels of constraint, one using lowercase letters (which were the only symbols included in the input text) and the other using both uppercase and lowercase letters. Two factors—recognizer and constraint—with two levels each, resulted in four test conditions. A total of 32 subjects performed text-entry tasks for each condition. Recognition accuracy differed significantly among conditions. Furthermore, the accuracy observed (87%–93%) was below the walk-up accuracy claimed by the developers of the recognizers. Entry speed was affected not only by recognition conditions but by users' adaptation to the idiosyncrasies of the recognizers. In an extensive error analysis, numerous weaknesses of the recognizers are revealed, in that certain characters are error prone and are misrecognized in a predictable way. This analysis, and the procedure for such, is a useful tool for designers of handwriting-recognition systems. User satisfaction results showed that recognition accuracy greatly affects the impression of walk-up users.

Dual classifier system for handprinted alphanumeric character recognition

This paper presents a dual classifier handprinted character recognition system that is implemented using Radial Basis Function (RBF) networks. Each classifier in the system extracts a different set of features from the input character and makes its own indpendent classification decision. The features used are the diagonal and partitioned radial projections, and the four-directional edge maps of the mage. The system then combines these decisions before giving a final classification output. Several different methods of desinging the combiner are examined. The proposed system is tested on a database of handprinted alphanumeric characters, and the results are fourd to be very promising.

Recognition of hand-printed Chinese characters using decision trees/machine learning C4.5 system

Recognition of Chinese characters has been an area of major interest for many years, and a large number of research papers and reports have already been published in this area. There are several major problems with Chinese character recognition: Chinese characters are distinct and ideographic, the character size is very large and a lot of structurally similar characters exist in the character set. Thus, classification criteria are difficult to generate. This paper presents a new technique for the recognition of hand-printed Chinese characters using the C4.5 machine learning system. Conventional methods have relied on hand-constructed dictionaries which are tedious to construct and difficult to make tolerant to variation in writing styles. The paper discusses Chinese character recognition using theHough transform for feature extraction and C4.5 system. The system was tested with 900 characters written by different writers from poor to acceptable quality (each character has 40 samples) and the rate of recognition obtained was 84%.

Adaptive recognition of Chinese characters: imitation of psychological process in machine recognition

This paper is focused on imitation of human psychological process in machine recognition of Chinese characters. Some results of research on human Chinese character recognition have been discussed and unified into a compound mechanism with an adaptive and self-developing nature. A machine imitation model has been proposed for Chinese character recognition with different routines. By some simplification but with the crucial feature of the model being retained, an experimental system for handprinted Chinese character recognition based on the novel concept has been built. Experimental results have shown that the associated routines continuously improve their performance during their work even after supervised training is halted. The routine of the global pattern approach eventually learns most of the classes and the recognition process gradually shifts from the subpattern approach to the global pattern approach.