arXiv subjects

Mahantapas Kundu

Publications and source records attributed to Mahantapas Kundu.

35 records · Page 2Linked to original sources

arXiv2011

High Performance Human Face Recognition using Independent High Intensity Gabor Wavelet Responses: A Statistical Approach

In this paper, we present a technique by which high-intensity feature vectors extracted from the Gabor wavelet transformation of frontal face images, is combined together with Independent Component Analysis (ICA) for enhanced face recognition. Firstly, the high-intensity feature vectors are automatically extracted using the local characteristics of each individual face from the Gabor transformed images. Then ICA is applied on these locally extracted high-intensity feature vectors of the facial images to obtain the independent high intensity feature (IHIF) vectors. These IHIF forms the basis of the work. Finally, the image classification is done using these IHIF vectors, which are considered as representatives of the images. The importance behind implementing ICA along with the high-intensity features of Gabor wavelet transformation is twofold. On the one hand, selecting peaks of the Gabor transformed face images exhibit strong characteristics of spatial locality, scale, and orientation selectivity. Thus these images produce salient local features that are most suitable for face recognition. On the other hand, as the ICA employs locally salient features from the high informative facial parts, it reduces redundancy and represents independent features explicitly. These independent features are most useful for subsequent facial discrimination and associative recall. The efficiency of IHIF method is demonstrated by the experiment on frontal facial images dataset, selected from the FERET, FRAV2D, and the ORL database.

cs.CV↗

arXiv2010

Face Synthesis (FASY) System for Determining the Characteristics of a Face Image

This paper aims at determining the characteristics of a face image by extracting its components. The FASY (FAce SYnthesis) System is a Face Database Retrieval and new Face generation System that is under development. One of its main features is the generation of the requested face when it is not found in the existing database, which allows a continuous growing of the database also. To generate the new face image, we need to store the face components in the database. So we have designed a new technique to extract the face components by a sophisticated method. After extraction of the facial feature points we have analyzed the components to determine their characteristics. After extraction and analysis we have stored the components along with their characteristics into the face database for later use during the face construction.

cs.CV↗

arXiv2010

Quotient Based Multiresolution Image Fusion of Thermal and Visual Images Using Daubechies Wavelet Transform for Human Face Recognition

This paper investigates the multiresolution level-1 and level-2 Quotient based Fusion of thermal and visual images. In the proposed system, the method-1 namely "Decompose then Quotient Fuse Level-1" and the method-2 namely "Decompose-Reconstruct then Quotient Fuse Level-2" both work on wavelet transformations of the visual and thermal face images. The wavelet transform is well-suited to manage different image resolution and allows the image decomposition in different kinds of coefficients, while preserving the image information without any loss. This approach is based on a definition of an illumination invariant signature image which enables an analytic generation of the image space with varying illumination. The quotient fused images are passed through Principal Component Analysis (PCA) for dimension reduction and then those images are classified using a multi-layer perceptron (MLP). The performances of both the methods have been evaluated using OTCBVS and IRIS databases. All the different classes have been tested separately, among them the maximum recognition result is 100%.

cs.CV↗

arXiv2010

Fusion of Daubechies Wavelet Coefficients for Human Face Recognition

In this paper fusion of visual and thermal images in wavelet transformed domain has been presented. Here, Daubechies wavelet transform, called as D2, coefficients from visual and corresponding coefficients computed in the same manner from thermal images are combined to get fused coefficients. After decomposition up to fifth level (Level 5) fusion of coefficients is done. Inverse Daubechies wavelet transform of those coefficients gives us fused face images. The main advantage of using wavelet transform is that it is well-suited to manage different image resolution and allows the image decomposition in different kinds of coefficients, while preserving the image information. Fused images thus found are passed through Principal Component Analysis (PCA) for reduction of dimensions and then those reduced fused images are classified using a multi-layer perceptron. For experiments IRIS Thermal/Visual Face Database was used. Experimental results show that the performance of the approach presented here achieves maximum success rate of 100% in many cases.

cs.CV↗

arXiv2010

Image Pixel Fusion for Human Face Recognition

In this paper we present a technique for fusion of optical and thermal face images based on image pixel fusion approach. Out of several factors, which affect face recognition performance in case of visual images, illumination changes are a significant factor that needs to be addressed. Thermal images are better in handling illumination conditions but not very consistent in capturing texture details of the faces. Other factors like sunglasses, beard, moustache etc also play active role in adding complicacies to the recognition process. Fusion of thermal and visual images is a solution to overcome the drawbacks present in the individual thermal and visual face images. Here fused images are projected into an eigenspace and the projected images are classified using a radial basis function (RBF) neural network and also by a multi-layer perceptron (MLP). In the experiments Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database benchmark for thermal and visual face images have been used. Comparison of experimental results show that the proposed approach performs significantly well in recognizing face images with a success rate of 96% and 95.07% for RBF Neural Network and MLP respectively.

cs.CV↗

arXiv2010

Classification of fused face images using multilayer perceptron neural network

This paper presents a concept of image pixel fusion of visual and thermal faces, which can significantly improve the overall performance of a face recognition system. Several factors affect face recognition performance including pose variations, facial expression changes, occlusions, and most importantly illumination changes. So, image pixel fusion of thermal and visual images is a solution to overcome the drawbacks present in the individual thermal and visual face images. Fused images are projected into eigenspace and finally classified using a multi-layer perceptron. In the experiments we have used Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database benchmark thermal and visual face images. Experimental results show that the proposed approach significantly improves the verification and identification performance and the success rate is 95.07%. The main objective of employing fusion is to produce a fused image that provides the most detailed and reliable information. Fusion of multiple images together produces a more efficient representation of the image.

cs.CV↗

arXiv2010

Classification of Log-Polar-Visual Eigenfaces using Multilayer Perceptron

In this paper we present a simple novel approach to tackle the challenges of scaling and rotation of face images in face recognition. The proposed approach registers the training and testing visual face images by log-polar transformation, which is capable to handle complicacies introduced by scaling and rotation. Log-polar images are projected into eigenspace and finally classified using an improved multi-layer perceptron. In the experiments we have used ORL face database and Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database for visual face images. Experimental results show that the proposed approach significantly improves the recognition performances from visual to log-polar-visual face images. In case of ORL face database, recognition rate for visual face images is 89.5% and that is increased to 97.5% for log-polar-visual face images whereas for OTCBVS face database recognition rate for visual images is 87.84% and 96.36% for log-polar-visual face images.

cs.CV↗

arXiv2010

Human Face Recognition using Line Features

In this work we investigate a novel approach to handle the challenges of face recognition, which includes rotation, scale, occlusion, illumination etc. Here, we have used thermal face images as those are capable to minimize the affect of illumination changes and occlusion due to moustache, beards, adornments etc. The proposed approach registers the training and testing thermal face images in polar coordinate, which is capable to handle complicacies introduced by scaling and rotation. Line features are extracted from thermal polar images and feature vectors are constructed using these line. Feature vectors thus obtained passes through principal component analysis (PCA) for the dimensionality reduction of feature vectors. Finally, the images projected into eigenspace are classified using a multi-layer perceptron. In the experiments we have used Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database. Experimental results show that the proposed approach significantly improves the verification and identification performance and the success rate is 99.25%.

cs.CV↗

arXiv2010

Multiple Classifier Combination for Off-line Handwritten Devnagari Character Recognition

This work presents the application of weighted majority voting technique for combination of classification decision obtained from three Multi_Layer Perceptron(MLP) based classifiers for Recognition of Handwritten Devnagari characters using three different feature sets. The features used are intersection, shadow feature and chain code histogram features. Shadow features are computed globally for character image while intersection features and chain code histogram features are computed by dividing the character image into different segments. On experimentation with a dataset of 4900 samples the overall recognition rate observed is 92.16% as we considered top five choices results. This method is compared with other recent methods for Handwritten Devnagari Character Recognition and it has been observed that this approach has better success rate than other methods.

cs.CV↗

arXiv2010

FPGA Based Assembling of Facial Components for Human Face Construction

This paper aims at VLSI realization for generation of a new face from textual description. The FASY (FAce SYnthesis) System is a Face Database Retrieval and new Face generation System that is under development. One of its main features is the generation of the requested face when it is not found in the existing database. The new face generation system works in three steps - searching phase, assembling phase and tuning phase. In this paper the tuning phase using hardware description language and its implementation in a Field Programmable Gate Array (FPGA) device is presented.

cs.CV↗

arXiv2010

Combining Multiple Feature Extraction Techniques for Handwritten Devnagari Character Recognition

In this paper we present an OCR for Handwritten Devnagari Characters. Basic symbols are recognized by neural classifier. We have used four feature extraction techniques namely, intersection, shadow feature, chain code histogram and straight line fitting features. Shadow features are computed globally for character image while intersection features, chain code histogram features and line fitting features are computed by dividing the character image into different segments. Weighted majority voting technique is used for combining the classification decision obtained from four Multi Layer Perceptron(MLP) based classifier. On experimentation with a dataset of 4900 samples the overall recognition rate observed is 92.80% as we considered top five choices results. This method is compared with other recent methods for Handwritten Devnagari Character Recognition and it has been observed that this approach has better success rate than other methods.

cs.CV↗

arXiv2010

Face Synthesis (FASY) System for Generation of a Face Image from Human Description

This paper aims at generating a new face based on the human like description using a new concept. The FASY (FAce SYnthesis) System is a Face Database Retrieval and new Face generation System that is under development. One of its main features is the generation of the requested face when it is not found in the existing database, which allows a continuous growing of the database also.

cs.CV↗

arXiv2010

Classification of Polar-Thermal Eigenfaces using Multilayer Perceptron for Human Face Recognition

This paper presents a novel approach to handle the challenges of face recognition. In this work thermal face images are considered, which minimizes the affect of illumination changes and occlusion due to moustache, beards, adornments etc. The proposed approach registers the training and testing thermal face images in polar coordinate, which is capable to handle complicacies introduced by scaling and rotation. Polar images are projected into eigenspace and finally classified using a multi-layer perceptron. In the experiments we have used Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database benchmark thermal face images. Experimental results show that the proposed approach significantly improves the verification and identification performance and the success rate is 97.05%.

cs.CV↗

arXiv2010

Text Region Extraction from Business Card Images for Mobile Devices

Designing a Business Card Reader (BCR) for mobile devices is a challenge to the researchers because of huge deformation in acquired images, multiplicity in nature of the business cards and most importantly the computational constraints of the mobile devices. This paper presents a text extraction method designed in our work towards developing a BCR for mobile devices. At first, the background of a camera captured image is eliminated at a coarse level. Then, various rule based techniques are applied on the Connected Components (CC) to filter out the noises and picture regions. The CCs identified as text are then binarized using an adaptive but light-weight binarization technique. Experiments show that the text extraction accuracy is around 98% for a wide range of resolutions with varying computation time and memory requirements. The optimum performance is achieved for the images of resolution 1024x768 pixels with text extraction accuracy of 98.54% and, space and time requirements as 1.1 MB and 0.16 seconds respectively.

cs.CV↗

arXiv2010

Binarizing Business Card Images for Mobile Devices

Business card images are of multiple natures as these often contain graphics, pictures and texts of various fonts and sizes both in background and foreground. So, the conventional binarization techniques designed for document images can not be directly applied on mobile devices. In this paper, we have presented a fast binarization technique for camera captured business card images. A card image is split into small blocks. Some of these blocks are classified as part of the background based on intensity variance. Then the non-text regions are eliminated and the text ones are skew corrected and binarized using a simple yet adaptive technique. Experiment shows that the technique is fast, efficient and applicable for the mobile devices.

cs.CV↗

arXiv2010

Handwritten Bangla Basic and Compound character recognition using MLP and SVM classifier

A novel approach for recognition of handwritten compound Bangla characters, along with the Basic characters of Bangla alphabet, is presented here. Compared to English like Roman script, one of the major stumbling blocks in Optical Character Recognition (OCR) of handwritten Bangla script is the large number of complex shaped character classes of Bangla alphabet. In addition to 50 basic character classes, there are nearly 160 complex shaped compound character classes in Bangla alphabet. Dealing with such a large varieties of handwritten characters with a suitably designed feature set is a challenging problem. Uncertainty and imprecision are inherent in handwritten script. Moreover, such a large varieties of complex shaped characters, some of which have close resemblance, makes the problem of OCR of handwritten Bangla characters more difficult. Considering the complexity of the problem, the present approach makes an attempt to identify compound character classes from most frequently to less frequently occurred ones, i.e., in order of importance. This is to develop a frame work for incrementally increasing the number of learned classes of compound characters from more frequently occurred ones to less frequently occurred ones along with Basic characters. On experimentation, the technique is observed produce an average recognition rate of 79.25 after three fold cross validation of data with future scope of improvement and extension.

cs.CV↗

arXiv2010

Word level Script Identification from Bangla and Devanagri Handwritten Texts mixed with Roman Script

India is a multi-lingual country where Roman script is often used alongside different Indic scripts in a text document. To develop a script specific handwritten Optical Character Recognition (OCR) system, it is therefore necessary to identify the scripts of handwritten text correctly. In this paper, we present a system, which automatically separates the scripts of handwritten words from a document, written in Bangla or Devanagri mixed with Roman scripts. In this script separation technique, we first, extract the text lines and words from document pages using a script independent Neighboring Component Analysis technique. Then we have designed a Multi Layer Perceptron (MLP) based classifier for script separation, trained with 8 different wordlevel holistic features. Two equal sized datasets, one with Bangla and Roman scripts and the other with Devanagri and Roman scripts, are prepared for the system evaluation. On respective independent text samples, word-level script identification accuracies of 99.29% and 98.43% are achieved.

cs.LG↗