Brijesh Verma

A novel feature extraction technique for the recognition of segmented handwritten characters

High accuracy character recognition techniques can provide useful information for segmentation-based handwritten word recognition systems. This research describes neural network-based techniques for segmented character recognition that may be applied to the segmentation and recognition components of an off-line handwritten word recognition system. Two neural architectures along with two different feature extraction techniques were investigated. A novel technique for character feature extraction is discussed and compared with others in the literature. Recognition results above 80% are reported using characters automatically segmented from the CEDAR benchmark database as well as standard CEDAR alphanumerics.

Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection

Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas containing benign and malignant microcalcifications. However, it is very difficult to distinguish benign and malignant microcalcifications. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists in assessment of microcalcifications. The research in this paper proposes and investigates a neural-genetic algorithm for feature selection in conjunction with neural and statistical classifiers to classify microcalcification patterns in digital mammograms. The obtained results show that the proposed approach is able to find an appropriate feature subset and neural classifier achieves better results than two statistical models.

A modified direction feature for cursive character recognition

This paper describes a neural network-based technique for cursive character recognition applicable to segmentation-based word recognition systems. The proposed research builds on a novel feature extraction technique that extracts direction information from the structure of character contours. This principal is extended so that the direction information is integrated with a technique for detecting transitions between background and foreground pixels in the character image. The proposed technique is compared with the standard direction feature extraction technique, providing promising results using segmented characters from the CEDAR benchmark database.

Fast training of multilayer perceptrons

Training a multilayer perceptron by an error backpropagation algorithm is slow and uncertain. This paper describes a new approach which is much faster and certain than error backpropagation. The proposed approach is based on combined iterative and direct solution methods. In this approach, we use an inverse transformation for linearization of nonlinear output activation functions, direct solution matrix methods for training the weights of the output layer; and gradient descent, the delta rule, and other proposed techniques for training the weights of the hidden layers. The approach has been implemented and tested on many problems. Experimental results, including training times and recognition accuracy, are given. Generally, the approach achieves accuracy as good as or better than perceptrons trained using error backpropagation, and the training process is much faster than the error backpropagation algorithm and also avoids local minima and paralysis.

A novel neural-genetic algorithm to find the most significant combination of features in digital mammograms

Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas containing benign and malignant microcalcifications. However, it is very difficult to distinguish benign and malignant microcalcifications. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists in assessment of microcalcifications. The research in this paper proposes a neural-genetic algorithm for feature selection to classify microcalcification patterns in digital mammograms. It aims to develop a step-wise algorithm to find the best feature set and a suitable neural architecture for microcalcification classification. The obtained results show that the proposed algorithm is able to find an appropriate feature subset, which also produces a high classification rate.

Classification of benign and malignant patterns in digital mammograms for the diagnosis of breast cancer

The classification of benign and malignant patterns in digital mammograms is one of most important and significant processes during the diagnosis of breast cancer as it helps detecting the disease at its early stage which saves many lives. Breast abnormalities are often embedded in and camouflaged by various breast tissue structures. It is a very challenging and difficult task for radiologists to correctly classify suspicious areas (benign and malignant patterns) in digital mammograms. In the early stage, the visual clues are subtle and varied in appearance, making diagnosis difficult; challenging even for specialists. Therefore, an intelligent classifier is required which can help radiologists in classifying suspicious areas and diagnosing breast cancer. This paper investigates a novel soft clustered based direct learning classifier which creates soft clusters within a class and learns using direct calculation of weights. The feature space for suspicious areas in digital mammograms from same class patterns can have multiple clusters and the proposed classifier uses this fact and introduces a novel idea to create soft clusters for each available class and applies them to form sub-classes within benign and malignant classes. A novel learning process based on direct learning is introduced. The experiments using the proposed classifier have been conducted on a benchmark database. The results have been analysed using ANOVA test which showed that the results are statistically significant.

Novel Layered Clustering-Based Approach for Generating Ensemble of Classifiers

This paper introduces a novel concept for creating an ensemble of classifiers. The concept is based on generating an ensemble of classifiers through clustering of data at multiple layers. The ensemble classifier model generates a set of alternative clustering of a dataset at different layers by randomly initializing the clustering parameters and trains a set of base classifiers on the patterns at different clusters in different layers. A test pattern is classified by first finding the appropriate cluster at each layer and then using the corresponding base classifier. The decisions obtained at different layers are fused into a final verdict using majority voting. As the base classifiers are trained on overlapping patterns at different layers, the proposed approach achieves diversity among the individual classifiers. Identification of difficult-to-classify patterns through clustering as well as achievement of diversity through layering leads to better classification results as evidenced from the experimental results.

An investigation of the modified direction feature for cursive character recognition

This paper describes and analyses the performance of a novel feature extraction technique for the recognition of segmented/cursive characters that may be used in the context of a segmentation-based handwritten word recognition system. The modified direction feature (MDF) extraction technique builds upon the direction feature (DF) technique proposed previously that extracts direction information from the structure of character contours. This principal was extended so that the direction information is integrated with a technique for detecting transitions between background and foreground pixels in the character image. In order to improve on the DF extraction technique, a number of modifications were undertaken. With a view to describe the character contour more effectively, a re-design of the direction number determination technique was performed. Also, an additional global feature was introduced to improve the recognition accuracy for those characters that were most frequently confused with patterns of similar appearance. MDF was tested using a neural network-based classifier and compared to the DF and transition feature (TF) extraction techniques. MDF outperformed both DF and TF techniques using a benchmark dataset and compared favourably with the top results in the literature. A recognition accuracy of above 89% is reported on characters from the CEDAR dataset.

Cluster-Oriented Ensemble Classifier: Impact of Multicluster Characterization on Ensemble Classifier Learning

This paper presents a novel cluster-oriented ensemble classifier. The proposed ensemble classifier is based on original concepts such as learning of cluster boundaries by the base classifiers and mapping of cluster confidences to class decision using a fusion classifier. The categorized data set is characterized into multiple clusters and fed to a number of distinctive base classifiers. The base classifiers learn cluster boundaries and produce cluster confidence vectors. A second level fusion classifier combines the cluster confidences and maps to class decisions. The proposed ensemble classifier modifies the learning domain for the base classifiers and facilitates efficient learning. The proposed approach is evaluated on benchmark data sets from UCI machine learning repository to identify the impact of multicluster boundaries on classifier learning and classification accuracy. The experimental results and two-tailed sign test demonstrate the superiority of the proposed cluster-oriented ensemble classifier over existing ensemble classifiers published in the literature.

Fuzzy logic based texture queries for CBIR

This paper presents a novel fuzzy logic based approach for the interpretation of texture queries. Tamura feature extraction technique is used to extract each texture feature of an image in the database. A term set on each Tamura feature is generated by a fuzzy clustering algorithm to pose a query in terms of natural language. The query can be expressed as a logic combination of natural language terms and tamura feature values. The performance of the technique was evaluated on Brodatz texture benchmark database. Experimental results show that the proposed technique is effective and the retrieved images indicate that those images are suitable for the specific queries.