B. B. Chaudhuri

Texture segmentation using fractal dimension

This paper deals with the problem of recognizing and segmenting textures in images. For this purpose the authors employ a technique based on the fractal dimension (FD) and the multi-fractal concept. Six FD features are based on the original image, the above average/high gray level image, the below average/low gray level image, the horizontally smoothed image, the vertically smoothed image, and the multi-fractal dimension of order two. A modified box-counting approach is proposed to estimate the FD, in combination with feature smoothing in order to reduce spurious regions. To segment a scene into the desired number of classes, an unsupervised K-means like clustering approach is used. Mosaics of various natural textures from the Brodatz album as well as microphotographs of thin sections of natural rocks are considered, and the segmentation results to show the efficiency of the technique. Supervised techniques such as minimum-distance and k-nearest neighbor classification are also considered. The results are compared with other techniques. >

An efficient differential box-counting approach to compute fractal dimension of image

Fractal dimension is an interesting feature proposed to characterize roughness and self-similarity in a picture. This feature has been used in texture segmentation and classification, shape analysis and other problems. An efficient differential box-counting approach to estimate fractal dimension is proposed in this note. By comparison with four other methods, it has been shown that the authors, method is both efficient and accurate. Practical results on artificial and natural textured images are presented. >

Indian script character recognition : a survey

Abstract Intensive research has been done on optical character recognition (OCR) and a large number of articles have been published on this topic during the last few decades. Many commercial OCR systems are now available in the market. But most of these systems work for Roman, Chinese, Japanese and Arabic characters. There are no sufficient number of work on Indian language character recognition although there are 12 major scripts in India. In this paper, we present a review of the OCR work done on Indian language scripts. The review is organized into 5 sections. Sections 1 and 2 cover introduction and properties on Indian scripts. In Section 3, we discuss different methodologies in OCR development as well as research work done on Indian scripts recognition. In Section 4, we discuss the scope of future work and further steps needed for Indian script OCR development. In Section 5 we conclude the paper.

A complete printed Bangla OCR system

A complete Optical Character Recognition (OCR) system for printed Bangla, the fourth most popular script in the world, is presented. This is the first OCR system among all script forms used in the Indian sub-continent. The problem is difficult because (i) there are about 300 basic, modified and compound character shapes in the script, (ii) the characters in a word are topologically connected and (iii) Bangla is an inflectional language. In our system the document image captured by Flat-bed scanner is subject to skew correction, text graphics separation, line segmentation, zone detection, word and character segmentation using some conventional and some newly developed techniques. From zonal information and shape characteristics, the basic, modified and compound characters are separated for the convenience of classification. The basic and modified characters which are about 75 in number and which occupy about 96% of the text corpus, are recognized by a structural-feature-based tree classifier. The compound characters are recognized by a tree classifier followed by template-matching approach. The feature detection is simple and robust where preprocessing like thinning and pruning are avoided. The character unigram statistics is used to make the tree classifier efficient. Several heuristics are also used to speed up the template matching approach. A dictionary-based error-correction scheme has been used where separate dictionaries are compiled for root word and suffixes that contain morpho-syntactic informations as well. For single font clear documents 95.50% word level (which is equivalent to 99.10% character level) recognition accuracy has been obtained. Extension of the work to Devnagari, the third most popular script in the world, is also discussed.

An efficient approach to estimate fractal dimension of textural images

Abstract Fractal dimension is an interesting parameter to characterize roughness in an image. It can be used in texture segmentation, estimation of three-dimensional (3D) shape and other information. A new method is proposed to estimate fractal dimension in a two-dimensional (2D) image which can readily be extended to a 3D image as well. The method has been compared with other existing methods to show that our method is both efficient and accurate.

Detection of 3-D simple points for topology preserving transformations with application to thinning

The problems of 3-D digital topology preservation under binary transformations and 3-D object thinning are considered in this correspondence. First, the authors establish the conditions under which transformation of an object voxel to a non-object voxel, or its inverse does not affect the image topology. An efficient algorithm to detect a simple point has been proposed on the basis of those conditions. In this connection, some other interesting properties of 3-D digital geometry are also discussed. Using these properties and the simple point detection algorithm, the authors have proposed an algorithm to generate a surface-skeleton so that the topology of the original image is preserved, the shape of the image is maintained as much as possible, and the results are less affected by noise. >

Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals

This article primarily concerns the problem of isolated handwritten numeral recognition of major Indian scripts. The principal contributions presented here are (a) pioneering development of two databases for handwritten numerals of two most popular Indian scripts, (b) a multistage cascaded recognition scheme using wavelet based multiresolution representations and multilayer perceptron classifiers and (c) application of (b) for the recognition of mixed handwritten numerals of three Indian scripts Devanagari, Bangla and English. The present databases include respectively 22,556 and 23,392 handwritten isolated numeral samples of Devanagari and Bangla collected from real-life situations and these can be made available free of cost to researchers of other academic Institutions. In the proposed scheme, a numeral is subjected to three multilayer perceptron classifiers corresponding to three coarse-to-fine resolution levels in a cascaded manner. If rejection occurred even at the highest resolution, another multilayer perceptron is used as the final attempt to recognize the input numeral by combining the outputs of three classifiers of the previous stages. This scheme has been extended to the situation when the script of a document is not known a priori or the numerals written on a document belong to different scripts. Handwritten numerals in mixed scripts are frequently found in Indian postal mails and table-form documents.

3D Digital Topology under Binary Transformation with Applications

In this paper we study 3D digital topology under the transformation of an object point to a nonobject point and vice versa. As a result of such a transformation, an object component in the 3 × 3 × 3 neighborhood of the affected point may vanish or split into two or more components or more than one object components may merge into one. Also, cavities or tunnels in the 3 × 3 × 3 neighborhood may be destroyed or created. One of the goals of this paper is to develop an efficient algorithm (topo_para) to compute the change in the numbers of object components, tunnels and cavities in the 3 × 3 × 3 neighborhood of the transformed point. Another important contribution is the classification of different types of points (e.g., arc inner point, arc edge point, surface inner point, surface edge point) and detection of different types of junction points (e.g., junction between arcs, junction between surfaces and arcs, junction between surfaces) on the surface skeleton representation of a 3D digital image. Using these junction points it is possible to segment a 3D digital surface topologically into meaningful parts. Also, we describe an efficient algorithm for computing the Euler number of a 3D digital image using the topological parameters computed bytopo_para.

A new shape preserving parallel thinning algorithm for 3D digital images

This paper is concerned with a new parallel thinning algorithm for three-dimensional digital images that preserves the topology and maintains their shape. We introduce an approach of selecting shape points and outer-layer used for erosion during each iteration. The approach produces good skeleton for different types of corners. The concept of using two image versions in thinning is introduced and its necessity in parallel thinning is justified. The robustness of the algorithm under pseudo-random noise as well as rotation with respect to shape properties is studied and the results are found to be satisfactory.

Efficient training and improved performance of multilayer perceptron in pattern classification

Abstract In pattern recognition problems, the convergence of backpropagation training algorithm of a multilayer perceptron is slow if the concerned classes have complex decision boundary. To improve the performance, we propose a technique, which at first cleverly picks up samples near the decision boundary without actually knowing the position of decision boundary. To choose the training samples, a larger set of data with known class label is considered. For each datum, its k-neighbours are found. If the datum is near the decision boundary, then all of these k-neighbours would not come from the same class. A training set, generated using this idea, results in quick and better convergence of the training algorithm. To get more symmetric neighbours, the nearest centroid neighbourhood (Chaudhuri, Pattern Recognition Lett. 17 (1996) 11–17) is used. The performance of the technique has been tested on synthetic data as well as speech vowel data in two Indian languages.