Virendra P. Vishwakarma

A Novel Approach for Face Recognition Using DCT Coefficients Re-scaling for Illumination Normalization

A novel approach for illumination normalization is proposed by exploiting the correlation of discrete cosine transform (DCT) low-frequency coefficients to illumination variations. The input image contrast is stretched using full image histogram equalization. Then the low-frequency DCT coefficients (except first) are re-scaled to lower value to compensate the illumination variations. The first (DC) coefficient is scaled to higher value for further contrast enhancement. The experiments are performed on the Yale B database and the results show that the performance of the proposed approach is better for the images with large illumination variations. The proposed technique is computationally efficient and can easily be implemented for real time face recognition system.

Robust image watermarking scheme in lifting wavelet domain using GA-LSVR hybridization

This paper presents an imperceptible, robust, secure and efficient image watermarking scheme in lifting wavelet domain using combination of genetic algorithm (GA) and Lagrangian support vector regression (LSVR). First, four subbands low–low (LL), low–high (LH), high–low (HL) and high–high (HH) are obtained by decomposing the host image from spatial domain to frequency domain using one level lifting wavelet transform. Second, the approximate image (LL subband) is divided into non overlapping blocks and the selected blocks based on the fuzzy entropy are used to embed the binary watermark. Third, based on the correlation property of each transformed selected block, significant lifting wavelet coefficient act as target to LSVR and its neighboring coefficients (called feature vector) are set as input to LSVR to find optimal regression function. This optimal regression function is used to embed and extract the scrambled watermark. In the proposed scheme, GA is used to solve the problem of optimal watermark embedding strength, based on the noise sensitivity of each selected block, in order to increase the imperceptibility of the watermark. Due to the good learning capability and high generalization property of LSVR against noisy datasets, high degree of robustness is achieved and is well suited for copyright protection applications. Experimental results on standard and real world images show that proposed scheme not only efficient in terms of computational cost and memory requirement but also achieve good imperceptibility and robustness against geometric and non geometric attacks like JPEG compression, median filtering, average filtering, addition of noise, sharpening, scaling, cropping and rotation compared with the state-of-art techniques.

A robust and efficient image watermarking scheme based on Lagrangian SVR and lifting wavelet transform

In this paper, an efficient image watermarking scheme based on Lagrangian support vector regression (LSVR) and lifting wavelet transform (LWT) is proposed to balance the trade-off between imperceptibility and robustness. LWT is faster and efficient implementation of traditional wavelet transform and LSVR has faster learning speed and high generalization capability compared to classical support vector regression. Combination of LWT and LSVR based image watermarking not only show imperceptibility and robustness but also reduces the time complexity. First the image is decomposed into four subbands using one level LWT and low frequency subband (approximate image) is partitioned into non overlapping blocks. Selected blocks based on correlation of wavelet coefficients are used to embed the binary watermark logo. For each selected block, significant wavelet coefficient is used as target to LSVR and its neighboring coefficients (feature vector) act as input to LSVR. The security of the watermark is achieved by applying Arnold transformation to original watermark. The scrambled watermark bit is embedded by comparing the output (predicted value) of LSVR of each selected block and the actual target value. The good learning capability and high generalization property of LSVR against noisy datasets provides the successful extraction of watermark against several image processing attacks: median filtering, average filtering, addition of Gaussian noise, salt and pepper noise, contrast enhancement, blurring, scaling, cropping and rotation. Experimental results show that the proposed scheme gives significant improvement in imperceptibility and robustness compared to the state-of-art techniques.

LWT- QR decomposition based robust and efficient image watermarking scheme using Lagrangian SVR

In this paper, an efficient and robust image watermarking scheme based on lifting wavelet transform (LWT) and QR decomposition using Lagrangian support vector regression (LSVR) is presented. After performing one level decomposition of host image using LWT, the low frequency subband is divided into 4 × 4 non-overlapping blocks. Based on the correlation property of lifting wavelet coefficients, each selected block is followed by QR decomposition. The significant element of first row of R matrix of each block is set as target to LSVR for embedding the watermark. The remaining elements (called feature vector) of upper triangular matrix R act as input to LSVR. The security of the watermark is achieved by applying Arnold transformation to original watermark to get its scrambled image. This scrambled image is embedded into the output (predicted value) of LSVR compared with the target value using optimal scaling factor to reduce the tradeoff between imperceptibility and robustness. Experimental results show that proposed scheme not only efficient in terms of computational cost and memory requirement but also achieve good imperceptibility and robustness against image processing operations compared to the state-of-art techniques.

Fuzzy based Pixel wise Information Extraction for Face Recognition

This paper brings out a new approach of information extraction based on fuzzy logic, which can be used for robust face recognition system. We have applied a fuzzification operation to extract the pixel wise association of face images to different classes. The fuzzification operation uses  membership function to obtain the degree of belonging of a particular pixel to all classes. Further nearest neighbor classification using correlation coefficient and principal component analysis are used to obtain the classification error over AT&T face database. The results clearly confirmed the superiority of proposed approach.

Lagrangian twin support vector regression and genetic algorithm based robust grayscale image watermarking

A novel imperceptible, secure and robust grayscale image watermarking scheme using Lagrangian twin support vector regression (LTSVR) and genetic algorithm (GA) in discrete Cosine transform (DCT) domain is presented in this manuscript. Fuzzy entropy is used to select the relevant blocks for embedding the watermark. Selected number of blocks based on fuzzy entropy not only reduces the dimensionality of the watermarking problem but also discards redundant and irrelevant blocks. Significant DCT coefficients having high energy compaction property of each selected block are used to form the image dataset to train LTSVR to find the non-linear regression function between the input and target vector. The adaptive watermark strength, different for each selected block, is decided by the GA process based on well defined fitness function. Due to good learning capability of image characteristics and high generalization property of LTSVR, watermark is successfully extracted from the watermarked images against a series of image processing operations. From the experimental and comparison results performed on standard and real world images, it is inferred that the proposed method is suitable for copyright protection applications where high degree of robustness is desirable.

Adaptive Image Watermarking Scheme Using Fuzzy Entropy and GA-ELM Hybridization in DCT Domain for Copyright Protection

A novel semi-blind image watermarking scheme based on fuzzy entropy and genetic algorithm (GA)—extreme learning machine (ELM) hybridization in discrete Cosine transform (DCT) domain for copyright protection is proposed in this paper. The selection of non overlapping blocks to embed the binary watermark is based on fuzzy entropy. As fuzzy entropy is able to discriminate data distribution under noise corrupted and redundant condition, feature extraction is more robust against various attacks. Each selected block is followed by 2-D DCT to transform it from spatial to frequency domain. Low frequency coefficients have good energy compactness and are robust to image processing attacks. As addition of noise corresponds to high frequency coefficients, these are not considered to embed the watermark in the proposed approach. The optimal scaling factor used to control the strength of watermark for each selected block of the image based on its noise sensitivity and tolerance limit is determined using GA optimization process. ELM is used to find an optimal regression function between the input feature vector (low frequency DCT coefficients) and corresponding target vector (in which the watermark bits are embedded) of each selected block. Then watermark embedding and extraction is performed intelligently by the regression function obtained by the trained ELM. The experimental results show that the proposed scheme is highly imperceptible and robust to geometric and non geometric attacks such as JPEG compression, filtering, noise addition, sharpening, gamma correction, scaling and cropping etc. To demonstrate the effectiveness of the proposed scheme, comparison with the state-of-art techniques clearly exhibits its applications for copyright protection.

Face recognition using Symlet, PCA and cosine angle distance measure

In this paper an approach for face recognition is proposed using Symlet, PCA and Cosine angle distance measure. The recognition rate and computational cost of proposed approach is examined against different wavelet families and Euclidean distance measure. Feature extraction is performed using Discrete wavelet transform and Principal component analysis (DWT-PCA). In order to explore best features, experiments are carried out for DWT subband selection and for DWT wavelet selection on Symlet family and on four other different wavelet families (Daubechies, Coiflets, Discrete Meyer and Biorthogonal wavelet family). This also includes their members that vary in terms of orthogonality, symmetry, support size, vanishing moments and filter order. After generating feature vectors, classification is done by Cosine angle distance measure based nearest neighbor classifier (NNC) and its results are compared with Euclidean distance measure. As test dataset, AT&T database of 400 images of 40 people is used to establish the performance by proposed approach. Experimental results on Symlet-6 with Cosine angle distance measure based nearest neighbor classifier shows highest percentage recognition rate of 98.33 for randomly generated 120 image training set.

Efficient feature extraction using DCT for gender classification

In this paper, a new technique for constructing feature vector from DCT coefficients for gender classification has been presented. Firstly, images are divided into 8 × 8 sub images. DCT coefficients are calculated for each block in image. New technique is used for constructing the feature vector from DCT coefficients. Finally, SVM with Rbf kernel is used for classifying the images into male and female. Using 2-Fold cross validation, optimal value for SVM parameters are found. Images of AT@T, FACES94 and Georgia Tech face database images are used for evaluation of proposed technique and it is found that the proposed technique is better in terms of generalization performance and computational cost than that of other state-of-art techniques.

Gender classification using KPCA and SVM

A new technique to construct feature vector for gender classification is proposed in this paper. Here, new feature reduction technique is used to remove the irrelevant features of images. Feature reduction also helps in reducing the over fitting problem of the dataset. KPCA is a kernel based PCA which maps data from original space to non-linear feature space. Kernel trick helps in reducing the expensive computation of mapping data to higher dimensional space. Optimal parameter of SVM C and Ύ are learned using cross validation dataset. Features obtained using KPCA are used to classify images into male or female using SVM. Images of different databases i.e. AT@T, Faces94 and Georgia Tech have been used to validate the efficiency of the proposed technique. Proposed technique has better generalization performance as compare to other existing techniques.