scispace - formally typeset
Search or ask a question
Author

Bidyut B. Chaudhuri

Bio: Bidyut B. Chaudhuri is an academic researcher from Indian Statistical Institute. The author has contributed to research in topics: Optical character recognition & Handwriting recognition. The author has an hindex of 51, co-authored 368 publications receiving 11368 citations. Previous affiliations of Bidyut B. Chaudhuri include University of Calcutta & Wellcome Trust Centre for Human Genetics.


Papers
More filters
Journal ArticleDOI
TL;DR: A hybrid spectral CNN (HybridSN) for HSI classification is proposed that reduces the complexity of the model compared to the use of 3-D-CNN alone and is compared with the state-of-the-art hand-crafted as well as end-to-end deep learning-based methods.
Abstract: Hyperspectral image (HSI) classification is widely used for the analysis of remotely sensed images. Hyperspectral imagery includes varying bands of images. Convolutional neural network (CNN) is one of the most frequently used deep learning-based methods for visual data processing. The use of CNN for HSI classification is also visible in recent works. These approaches are mostly based on 2-D CNN. On the other hand, the HSI classification performance is highly dependent on both spatial and spectral information. Very few methods have used the 3-D-CNN because of increased computational complexity. This letter proposes a hybrid spectral CNN (HybridSN) for HSI classification. In general, the HybridSN is a spectral–spatial 3-D-CNN followed by spatial 2-D-CNN. The 3-D-CNN facilitates the joint spatial–spectral feature representation from a stack of spectral bands. The 2-D-CNN on top of the 3-D-CNN further learns more abstract-level spatial representation. Moreover, the use of hybrid CNNs reduces the complexity of the model compared to the use of 3-D-CNN alone. To test the performance of this hybrid approach, very rigorous HSI classification experiments are performed over Indian Pines, University of Pavia, and Salinas Scene remote sensing data sets. The results are compared with the state-of-the-art hand-crafted as well as end-to-end deep learning-based methods. A very satisfactory performance is obtained using the proposed HybridSN for HSI classification. The source code can be found at https://github.com/gokriznastic/HybridSN .

775 citations

Journal ArticleDOI
TL;DR: An efficient differential box-counting approach to estimate fractal dimension is proposed and by comparison with four other methods, it has been shown that the method is both efficient and accurate.
Abstract: 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. >

767 citations

Journal ArticleDOI
TL;DR: A modified box-counting approach is proposed to estimate the FD, in combination with feature smoothing in order to reduce spurious regions and to segment a scene into the desired number of classes, an unsupervised K-means like clustering approach is used.
Abstract: 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. >

650 citations

Journal ArticleDOI
TL;DR: A survey of Hough Transform and its variants, their limitations and the modifications made to overcome them, the implementation issues in software and hardware, and applications in various fields is done.

646 citations

Journal ArticleDOI
TL;DR: A review of the OCR work done on Indian language scripts and the scope of future work and further steps needed for Indian script OCR development is presented.

592 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: Attempts have been made to cover both fuzzy and non-fuzzy techniques including color image segmentation and neural network based approaches, which addresses the issue of quantitative evaluation of segmentation results.

3,527 citations

Reference EntryDOI
15 Oct 2004

2,118 citations

01 Jan 2000
TL;DR: In this paper, a general segmentation algorithm based on homogeneity definitions in combination with local and global optimization techniques is proposed for object oriented image processing, which aims for an universal high-quality solution applicable and adaptable to many problems and data types.
Abstract: A necessary prerequisite for object oriented image processing is successful image segmentation. The approach presented in this paper aims for an universal high-quality solution applicable and adaptable to many problems and data types. As each image analysis problem deals with structures of a certain spatial scale, the average image objects size must be free adaptable to the scale of interest. This is achieved by a general segmentation algorithm based on homogeneity definitions in combination with local and global optimization techniques. A scale parameter is used to control the average image object size. Different homogeneity criteria for image objects based on spectral and/or spatial information are developed and compared.

1,672 citations

Book
25 Nov 1996
TL;DR: Algorithms for Image Processing and Computer Vision, 2nd Edition provides the tools to speed development of image processing applications.
Abstract: A cookbook of algorithms for common image processing applicationsThanks to advances in computer hardware and software, algorithms have been developed that support sophisticated image processing without requiring an extensive background in mathematics This bestselling book has been fully updated with the newest of these, including 2D vision methods in content-based searches and the use of graphics cards as image processing computational aids Its an ideal reference for software engineers and developers, advanced programmers, graphics programmers, scientists, and other specialists who require highly specialized image processingAlgorithms now exist for a wide variety of sophisticated image processing applications required by software engineers and developers, advanced programmers, graphics programmers, scientists, and related specialistsThis bestselling book has been completely updated to include the latest algorithms, including 2D vision methods in content-based searches, details on modern classifier methods, and graphics cards used as image processing computational aidsSaves hours of mathematical calculating by using distributed processing and GPU programming, and gives non-mathematicians the shortcuts needed to program relatively sophisticated applicationsAlgorithms for Image Processing and Computer Vision, 2nd Edition provides the tools to speed development of image processing applications

1,517 citations