Mahantapas Kundu

Animesh Singh, Sandip Saha, Ritesh Sarkhel et al.

Deep neural network-based architectures give promising results in various domains including pattern recognition. Finding the optimal combination of the hyper-parameters of such a large-sized architecture is tedious and requires a large number of laboratory experiments. But, identifying the optimal combination of a hyper-parameter or appropriate kernel size for a given architecture of deep learning is always a challenging and tedious task. Here, we introduced a genetic algorithm-based technique to reduce the efforts of finding the optimal combination of a hyper-parameter (kernel size) of a convolutional neural network-based architecture. The method is evaluated on three popular datasets of different handwritten Bangla characters and digits. The implementation of the proposed methodology can be found in the following link: https://github.com/DeepQn/GA-Based-Kernel-Size.

Shuvayan Ghosh Dastidar, Kalpita Dutta, Nibaran Das et al.

Multi-lingual script identification is a difficult task consisting of different language with complex backgrounds in scene text images. According to the current research scenario, deep neural networks are employed as teacher models to train a smaller student network by utilizing the teacher model's predictions. This process is known as dark knowledge transfer. It has been quite successful in many domains where the final result obtained is unachievable through directly training the student network with a simple architecture. In this paper, we explore dark knowledge transfer approach using long short-term memory(LSTM) and CNN based assistant model and various deep neural networks as the teacher model, with a simple CNN based student network, in this domain of multi-script identification from natural scene text images. We explore the performance of different teacher models and their ability to transfer knowledge to a student network. Although the small student network's limited size, our approach obtains satisfactory results on a well-known script identification dataset CVSI-2015.

Animesh Singh, Ritesh Sarkhel, Nibaran Das et al.

Finding local invariant patterns in handwrit-ten characters and/or digits for optical character recognition is a difficult task. Variations in writing styles from one person to another make this task challenging. We have proposed a non-explicit feature extraction method using a multi-scale multi-column skip convolutional neural network in this work. Local and global features extracted from different layers of the proposed architecture are combined to derive the final feature descriptor encoding a character or digit image. Our method is evaluated on four publicly available datasets of isolated handwritten Bangla characters and digits. Exhaustive comparative analysis against contemporary methods establishes the efficacy of our proposed approach.

Saikat Roy, Nibaran Das, Mahantapas Kundu et al.

In this work, a novel deep learning technique for the recognition of handwritten Bangla isolated compound character is presented and a new benchmark of recognition accuracy on the CMATERdb 3.1.3.3 dataset is reported. Greedy layer wise training of Deep Neural Network has helped to make significant strides in various pattern recognition problems. We employ layerwise training to Deep Convolutional Neural Networks (DCNN) in a supervised fashion and augment the training process with the RMSProp algorithm to achieve faster convergence. We compare results with those obtained from standard shallow learning methods with predefined features, as well as standard DCNNs. Supervised layerwise trained DCNNs are found to outperform standard shallow learning models such as Support Vector Machines as well as regular DCNNs of similar architecture by achieving error rate of 9.67% thereby setting a new benchmark on the CMATERdb 3.1.3.3 with recognition accuracy of 90.33%, representing an improvement of nearly 10%.

Nibaran Das, Subhadip Basu, Ram Sarkar et al.

Appropriate feature set for representation of pattern classes is one of the most important aspects of handwritten character recognition. The effectiveness of features depends on the discriminating power of the features chosen to represent patterns of different classes. However, discriminatory features are not easily measurable. Investigative experimentation is necessary for identifying discriminatory features. In the present work we have identified a new variation of feature set which significantly outperforms on handwritten Bangla alphabet from the previously used feature set. 132 number of features in all viz. modified shadow features, octant and centroid features, distance based features, quad tree based longest run features are used here. Using this feature set the recognition performance increases sharply from the 75.05% observed in our previous work [7], to 85.40% on 50 character classes with MLP based classifier on the same dataset.

Nibaran Das, Subhadip Basu, Punam Kumar Saha et al.

Soft computing approaches are mainly designed to address the real world ill-defined, imprecisely formulated problems, combining different kind of novel models of computation, such as neural networks, genetic algorithms (GAs. Handwritten digit recognition is a typical example of one such problem. In the current work we have developed a two-pass approach where the first pass classifier performs a coarse classification, based on some global features of the input pattern by restricting the possibility of classification decisions within a group of classes, smaller than the number of classes considered initially. In the second pass, the group specific classifiers concentrate on the features extracted from the selected local regions, and refine the earlier decision by combining the local and the global features for selecting the true class of the input pattern from the group of candidate classes selected in the first pass. To optimize the selection of local regions a GA based approach has been developed here. The maximum recognition performance on Bangla digit samples as achieved on the test set, during the first pass of the two pass approach is 93.35%. After combining the results of the two stage classifiers, an overall success rate of 95.25% is achieved.

Nibaran Das, Sandip Pramanik, Subhadip Basu et al.

In this paper, convex hull based features are used for recognition of isolated Roman numerals using a Multi Layer Perceptron (MLP) based classifier. Experiments of convex hull based features for handwritten character recognition are few in numbers. Convex hull of a pattern and the centroid of the convex hull both are affine invariant attributes. In this work, 25 features are extracted based on different bays attributes of the convex hull of the digit patterns. Then these patterns are divided into four sub-images with respect to the centroid of the convex hull boundary. From each such sub-image 25 bays features are also calculated. In all 125 convex hull based features are extracted for each numeric digit patterns under the current experiment. The performance of the designed feature set is tested on the standard MNIST data set, consisting of 60000 training and 10000 test images of handwritten Roman using an MLP based classifier a maximum success rate of 97.44% is achieved on the test data.

Subhadip Basu, Mahantapas Kundu, Mita Nasipuri et al.

The work presents an extension of the fuzzy approach to 2-D shape recognition [1] through refinement of initial or coarse classification decisions under a two pass approach. In this approach, an unknown pattern is classified by refining possible classification decisions obtained through coarse classification of the same. To build a fuzzy model of a pattern class horizontal and vertical fuzzy partitions on the sample images of the class are optimized using genetic algorithm. To make coarse classification decisions about an unknown pattern, the fuzzy representation of the pattern is compared with models of all pattern classes through a specially designed similarity measure. Coarse classification decisions are refined in the second pass to obtain the final classification decision of the unknown pattern. To do so, optimized horizontal and vertical fuzzy partitions are again created on certain regions of the image frame, specific to each group of similar type of pattern classes. It is observed through experiments that the technique improves the overall recognition rate from 86.2%, in the first pass, to 90.4% after the second pass, with 500 training samples of handwritten digits.

Nibaran Das, Sandip Pramanik, Subhadip Basu et al.

In dealing with the problem of recognition of handwritten character patterns of varying shapes and sizes, selection of a proper feature set is important to achieve high recognition performance. The current research aims to evaluate the performance of the convex hull based feature set, i.e. 125 features in all computed over different bays attributes of the convex hull of a pattern, for effective recognition of isolated handwritten Bangla basic characters and digits. On experimentation with a database of 10000 samples, the maximum recognition rate of 76.86% is observed for handwritten Bangla characters. For Bangla numerals the maximum success rate of 99.45%. is achieved on a database of 12000 sample. The current work validates the usefulness of a new kind of feature set for recognition of handwritten Bangla basic characters and numerals.

Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu et al.

In this paper, we present a novel Gabor wavelet based Kernel Entropy Component Analysis (KECA) method by integrating the Gabor wavelet transformation (GWT) of facial images with the KECA method for enhanced face recognition performance. Firstly, from the Gabor wavelet transformed images the most important discriminative desirable facial features characterized by spatial frequency, spatial locality and orientation selectivity to cope with the variations due to illumination and facial expression changes were derived. After that KECA, relating to the Renyi entropy is extended to include cosine kernel function. The KECA with the cosine kernels is then applied on the extracted most important discriminating feature vectors of facial images to obtain only those real kernel ECA eigenvectors that are associated with eigenvalues having positive entropy contribution. Finally, these real KECA features are used for image classification using the L1, L2 distance measures; the Mahalanobis distance measure and the cosine similarity measure. The feasibility of the Gabor based KECA method with the cosine kernel has been successfully tested on both frontal and pose-angled face recognition, using datasets from the ORL, FRAV2D and the FERET database.

Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu et al.

This paper exploits the feature extraction capabilities of the discrete cosine transform (DCT) together with an illumination normalization approach in the logarithm domain that increase its robustness to variations in facial geometry and illumination. Secondly in the same domain the entropy measures are applied on the DCT coefficients so that maximum entropy preserving pixels can be extracted as the feature vector. Thus the informative features of a face can be extracted in a low dimensional space. Finally, the kernel entropy component analysis (KECA) with an extension of arc cosine kernels is applied on the extracted DCT coefficients that contribute most to the entropy estimate to obtain only those real kernel ECA eigenvectors that are associated with eigenvalues having high positive entropy contribution. The resulting system was successfully tested on real image sequences and is robust to significant partial occlusion and illumination changes, validated with the experiments on the FERET, AR, FRAV2D and ORL face databases. Experimental comparison is demonstrated to prove the superiority of the proposed approach in respect to recognition accuracy. Using specificity and sensitivity we find that the best is achieved when Renyi entropy is applied on the DCT coefficients. Extensive experimental comparison is demonstrated to prove the superiority of the proposed approach in respect to recognition accuracy. Moreover, the proposed approach is very simple, computationally fast and can be implemented in any real-time face recognition system.

Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu et al.

This paper introduces a novel methodology that combines the multi-resolution feature of the Gabor wavelet transformation (GWT) with the local interactions of the facial structures expressed through the Pseudo Hidden Markov model (PHMM). Unlike the traditional zigzag scanning method for feature extraction a continuous scanning method from top-left corner to right then top-down and right to left and so on until right-bottom of the image i.e. a spiral scanning technique has been proposed for better feature selection. Unlike traditional HMMs, the proposed PHMM does not perform the state conditional independence of the visible observation sequence assumption. This is achieved via the concept of local structures introduced by the PHMM used to extract facial bands and automatically select the most informative features of a face image. Thus, the long-range dependency problem inherent to traditional HMMs has been drastically reduced. Again with the use of most informative pixels rather than the whole image makes the proposed method reasonably faster for face recognition. This method has been successfully tested on frontal face images from the ORL, FRAV2D and FERET face databases where the images vary in pose, illumination, expression, and scale. The FERET data set contains 2200 frontal face images of 200 subjects, while the FRAV2D data set consists of 1100 images of 100 subjects and the full ORL database is considered. The results reported in this application are far better than the recent and most referred systems.

Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu et al.

In this paper a nonlinear Gabor Wavelet Transform (GWT) discriminant feature extraction approach for enhanced face recognition is proposed. Firstly, the low-energized blocks from Gabor wavelet transformed images are extracted. Secondly, the nonlinear discriminating features are analyzed and extracted from the selected low-energized blocks by the generalized Kernel Discriminative Common Vector (KDCV) method. The KDCV method is extended to include cosine kernel function in the discriminating method. The KDCV with the cosine kernels is then applied on the extracted low energized discriminating feature vectors to obtain the real component of a complex quantity for face recognition. In order to derive positive kernel discriminative vectors; we apply only those kernel discriminative eigenvectors that are associated with non-zero eigenvalues. The feasibility of the low energized Gabor block based generalized KDCV method with cosine kernel function models has been successfully tested for image classification using the L1, L2 distance measures; and the cosine similarity measure on both frontal and pose-angled face recognition. Experimental results on the FRAV2D and the FERET database demonstrate the effectiveness of this new approach.

Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu et al.

This paper proposes a new technique for automatic face recognition using integrated peaks of the Hough transformed significant blocks of the binary gradient image. In this approach firstly the gradient of an image is calculated and a threshold is set to obtain a binary gradient image, which is less sensitive to noise and illumination changes. Secondly, significant blocks are extracted from the absolute gradient image, to extract pertinent information with the idea of dimension reduction. Finally the best fitted Hough peaks are extracted from the Hough transformed significant blocks for efficient face recognition. Then these Hough peaks are concatenated together, which are used as feature in classification process. The efficiency of the proposed method is demonstrated by the experiment on 1100 images from the FRAV2D face database, 2200 images from the FERET database, where the images vary in pose, expression, illumination and scale and 400 images from the ORL face database, where the images slightly vary in pose. Our method has shown 93.3%, 88.5% and 99% recognition accuracy for the FRAV2D, FERET and the ORL database respectively.

Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu et al.

This paper proposes a technique for automatic face recognition using integrated multiple feature sets extracted from the significant blocks of a gradient image. We discuss about the use of novel morphological, local directional pattern (LDP) and gray-level co-occurrence matrix GLCM based feature extraction technique to recognize human faces. Firstly, the new morphological features i.e., features based on number of runs of pixels in four directions (N,NE,E,NW) are extracted, together with the GLCM based statistical features and LDP features that are less sensitive to the noise and non-monotonic illumination changes, are extracted from the significant blocks of the gradient image. Then these features are concatenated together. We integrate the above mentioned methods to take full advantage of the three approaches. Extraction of the significant blocks from the absolute gradient image and hence from the original image to extract pertinent information with the idea of dimension reduction forms the basis of the work. The efficiency of our method is demonstrated by the experiment on 1100 images from the FRAV2D face database, 2200 images from the FERET database, where the images vary in pose, expression, illumination and scale and 400 images from the ORL face database, where the images slightly vary in pose. Our method has shown 90.3%, 93% and 98.75% recognition accuracy for the FRAV2D, FERET and the ORL database respectively.

Subhadip Basu, Nibaran Das, Ram Sarkar et al.

The work presented here involves the design of a Multi Layer Perceptron (MLP) based classifier for recognition of handwritten Bangla alphabet using a 76 element feature set Bangla is the second most popular script and language in the Indian subcontinent and the fifth most popular language in the world. The feature set developed for representing handwritten characters of Bangla alphabet includes 24 shadow features, 16 centroid features and 36 longest-run features. Recognition performances of the MLP designed to work with this feature set are experimentally observed as 86.46% and 75.05% on the samples of the training and the test sets respectively. The work has useful application in the development of a complete OCR system for handwritten Bangla text.

Subhadip Basu, Nibaran Das, Ram Sarkar et al.

The work presented here involves the design of a Multi Layer Perceptron (MLP) based pattern classifier for recognition of handwritten Bangla digits using a 76 element feature vector. Bangla is the second most popular script and language in the Indian subcontinent and the fifth most popular language in the world. The feature set developed for representing handwritten Bangla numerals here includes 24 shadow features, 16 centroid features and 36 longest-run features. On experimentation with a database of 6000 samples, the technique yields an average recognition rate of 96.67% evaluated after three-fold cross validation of results. It is useful for applications related to OCR of handwritten Bangla Digit and can also be extended to include OCR of handwritten characters of Bangla alphabet.

Subhadip Basu, Chitrita Chaudhuri, Mahantapas Kundu et al.

Character segmentation has long been one of the most critical areas of optical character recognition process. Through this operation, an image of a sequence of characters, which may be connected in some cases, is decomposed into sub-images of individual alphabetic symbols. In this paper, segmentation of cursive handwritten script of world's fourth popular language, Bengali, is considered. Unlike English script, Bengali handwritten characters and its components often encircle the main character, making the conventional segmentation methodologies inapplicable. Experimental results, using the proposed segmentation technique, on sample cursive handwritten data containing 218 ideal segmentation points show a success rate of 97.7%. Further feature-analysis on these segments may lead to actual recognition of handwritten cursive Bengali script.