Nabeel A. Murshed

Advances in Pattern Recognition — ICAPR 2001

Two novel concepts in structural pattern recognition are discussed in this paper. The rst, median of a set of graphs, can be used to characterize a set of graphs by just a single prototype. Such a characterization is needed in various tasks, for example, in clustering. The second novel concept is weighted mean of a pair of graphs. It can be used to synthesize a graph that has a speci ed degree of similarity, or distance, to each of a pair of given graphs. Such an operation is needed in many machine learning tasks. It is argued that with these new concepts various well-established techniques from statistical pattern recognition become applicable in the structural domain, particularly to graph representations. Concrete examples include k-means clustering, vector quantization, and Kohonen maps.

A cognitive approach to off-line signature verification

This paper presents an Off-line Signature Verification System for identifying random forgeries aimed at banking application. The cognitive information learning process in the proposed system is inspired by some characteristics of human learning. Four features distinguish the proposed system from those proposed thus far. First, the verification task is accomplished without a priori knowledge of the class of random forgeries. Second, no explicit modeling or making geometrical measurements are used to represent the signature. Third, the decision of the system is made throughout the use of two-stage verification process by which a global and/or local analysis are performed on the unknown signature. The global analysis is concerned with the overall shape of the unknown signature, whereas, the local analysis is concerned with the local features composing the unknown signature. Fourth, these analysis are performed at the boundary or within a predefined search region called the identity grid designed for each writer in the system. The proposed system is evaluated with a data base of 800 signatures.

Off-line signature verification, without a priori knowledge of class /spl omega//sub 2/. A new approach

This work proposes a new approach to signature verification. It is inspired by the human learning and the approach adopted by the expert examiner of signatures, in which an a priori knowledge of the class of forgeries is not required in order to perform the verification task. Based on this approach, we present a Fuzzy ARTMAP based system for the elimination of random forgeries. Compared to the conventional systems proposed thus far, the presented system is trained with genuine signatures only. Six experiments have been performed on a data base of 200 signatures taken from five writers (40 signatures/writer). Evaluation of the system was measured using different numbers of training signatures.

Off-line signature verification using fuzzy ARTMAP neural network

This work presents a fuzzy ARTMAP based off-line signature verification system. Compared to the conventional systems proposed thus far, the presented system is trained with genuine signatures only. Six experiments have been performed on a database of 200 signatures taken from five writers (40 signatures/writer). Evaluation of the system was measured using different numbers of training signatures (3, 6, 9, 12, 15 and 18).

A fuzzy ARTMAP-based classification system for detecting cancerous cells, based on the one-class problem approach

This work investigates the use of a fuzzy ARTMAP neural network for detecting cancerous cells, based on the one-class problem approach. This approach is inspired by the way human beings perform pattern recognition. We all know that children and adults alike are capable of detecting patterns belonging to a certain class, by learning the features of these patterns only. Moreover, a child or an adult is capable of detecting an unknown pattern belonging to another class without an a priori knowledge of the features in these patterns. Based on this approach, a fuzzy ARTMAPs-based system is developed for detecting cancerous cells by training the fuzzy ARTMAPs with the features belonging to the class of cancerous cells only. This is different from the two-class problem approach which requires that the classifier must be trained with features from the class of cancerous cells and the class of noncancerous cells. Experimental analysis were conducted using a set of 542 patterns taken from a sample of breast cancer. Training was performed with 383 cancerous cells. System performance was evaluated using 54 cancerous cells and 159 noncancerous cells. Evaluation results show 98% correct identification of cancerous cells and 95% correct identification of noncancerous cells.

Binary image compression using Identity-Mapping Backpropagation Neural Network

This work proposes a method for using an identity-mapping backpropagation (IMBKP) neural network for binary image compression, aimed at reducing the dimension of the feature vector in a NN-based pattern recognition system. In the proposed method, the IMBKP network was trained with the objective of achieving good reconstruction quality and a reasonable amount of image compression. This criteria is very important, when using binary images as feature vectors. Evaluation of the proposed network was performed using 800 images of handwritten signatures. The lowest and highest reconstruction errors were, respectively, 3.05 multiplied by 10-3% and 0.01%. The proposed network can be used to reduce the dimension of the input vector to a NN-based pattern recognition system without almost and degradation and, yet, with a good reduction in the number of input neurons.

Recognition of printed Arabic words with fuzzy ARTMAP neural network

This paper presents a new method for the recognition of Arabic text using global features and fuzzy ARTMAP neural network. The method is divided into three major steps. The first step is digitization and pre-processing to create connected component. The second step is concerned with feature extraction, where global features of the input word are used to extract features such as number of subwords, number of peaks within the subword, number and position of the complementary character, etc., to avoid the difficulty of segmentation stage. The third step is the classification and is composed of a single fuzzy ARTMAP. The method was evaluated with 3255 images of 217 Arabic words with different fonts (each word has 15 samples), and the mean correct classification rate was 95.25%.

A neural network structure for detecting straight line segments

A new method for detecting one-pixel wide vertical, horizontal and diagonal line segments in binary images, is presented. It is based on using four slabs of neural networks, each of which is composed of a set layers. Each layer consists of a number of neurons that is determined by the slab type. The whole image is used as input to each slab, and the information processing in each slab occurs in parallel, decreasing, therefore, computation time and allowing hardware implementation. The method was tested with various types of binary images and the obtained results were satisfactory. In addition, the method was robust against random noise, such as straight lines impeded in a cloud of points.

Off-Line Handwritten Chinese Character Recognition Based on Structural Features and Fuzzy Artmap

Recognition of printed and handwritten text (characters and digits) has been a challenge for many researchers in the field of Document Image Analysis for almost thirty years. Many existing pattern recognition methods have been used and new ones have been proposed. Despite the satisfactory results obtained in recognizing printed text, recognition of handwritten text is still an open research. This paper presents a method for off-line recognition of handwritten Chinese characters. Each character is described by six structural features extracted using the dominant point method. The goodness of each feature is determined by a method called stroke probability. The classification was performed by the Fuzzy ARTMAP neural network within the context of the one-class problem approach. Evaluation of the proposed method was determined using database of 900 characters (an average of 40 samples/character). The average mean recognition rate was approximately 94%.

Classification of cancerous cells based on the one-class problem approach

One of the most important factors in reducing the effect of cancerous diseases is the early diagnosis, which requires a good and a robust method. With the advancement of computer technologies and digital image processing, the development of a computer-based system has become feasible. In this paper, we introduce a new approach for the detection of cancerous cells. This approach is based on the one-class problem approach, through which the classification system need only be trained with patterns of cancerous cells. This reduces the burden of the training task by about 50%. Based on this approach, a computer-based classification system is developed, based on the Fuzzy ARTMAP neural networks. Experimental results were performed using a set of 542 patterns taken from a sample of breast cancer. Results of the experiment show 98% correct identification of cancerous cells and 95% correct identification of non-cancerous cells.