International Journal of Image and Graphics

The aim of this study is to remotely measure cardiac activity (heart pulse, total cycle length and pulse width) from videos based on a head motion at different positions of the head (front, back and side). As the head motion resulting from the cardiac cycle of blood from the heart to the head via the carotid arteries is not visible to the naked eye and to preserve the signal strength in the video, we used wavelet decomposition and a Chebychev filter to develop a standard Eulerian video magnification in terms of noise removal and execution time. We used both magnification systems to measure cardiac activity and statistically compare the results using Bland–Altman method. Also, we proposed a new video quality system based on fuzzy interface system to select which magnification system has better magnification quality and gives better results for the heart pulse rate. The experimental results on several videos captured from 10 healthy subjects show that the proposed contactless system of heart pulse has an accuracy of 98.3% when magnified video based on the developing magnification system was used and an accuracy of 97.4% when magnified video based on Eulerian magnification system was used instead. The proposed system has low computational complexity, making it suitable for advancing health care applications, mobile health applications and telemedicine.

The objective of this paper is to develop a shot boundary detection system to detect shots from a given video. To meet this objective, it is proposed to use feature vector in the process of identifying cut transition and gradual transition. The proposed method analyzes each video frame with its immediate left and right neighbor frame and identifies shot transitions. For each frame comparison, it considers color, edge, motion, and texture features of left and right frames. The proposed method is evaluated on video sequences from the TRECVID video set. The experimental results of the proposed method are compared with the existing methods. It is observed that the proposed method is suitable to perform robust shot boundary detection.

Gaussian noise is an important problem in computer vision. The novel methods that become popular in recent years for Gaussian noise reduction are Bayesian techniques in wavelet domain. In wavelet domain, the Bayesian techniques require a prior distribution of wavelet coefficients. In general case, the wavelet coefficients might be better modeled by non-Gaussian density such as Laplacian, two-sided gamma, and Pearson type VII densities. However, statistical analysis of textural image is Gaussian model. So, we require flexible model between non-Gaussian and Gaussian models. Indeed, Gumbel density is a suitable model. So, we present new Bayesian estimator for Gumbel random vectors in AWGN (additive white Gaussian noise). The proposed method is applied to dual-tree complex wavelet transform (DT-CWT) as well as orthogonal discrete wavelet transform (DWT). The simulation results show that our proposed methods outperform the state-of-the-art methods qualitatively and quantitatively.

Logarithmic image processing (LIP) models provide a viable framework for image enhancement, particularly the color-based models. These techniques, due to their vector nature, avoid the problems of grayscale methods applied to RGB color image processing. Furthermore, the absence of multiply-accumulate (MAC) operations makes them amenable to hardware realization for faster operation when compared with spatial filter kernel-based approaches. However, details of image scenes are not always revealed after processing and homomorphic filters are still a popular low-complexity option for correction of images acquired under uneven illumination conditions, notwithstanding the fading that occurs when processing RGB color images. Though nonlinear color space converter hardware architectures have been implemented and reported in the literature for improving results from conventional illumination correction techniques, they add to the hardware complexity. The contributions of the work described in this paper includes original, practical, standard and logarithmic, multiplier-less high-speed architectures for a variant of the LIP model in addition to standard and log-hybrid architectures for a modified spatial homomorphic filter (MSDHF) to reduce color fading in RGB space. The modified homomorphic filter is able to enhance both faded/bright and dark low-contrast images, giving it an edge over standard illumination correction systems. A combined approach utilizing the MSDHF and simplified LIP algorithms enhances the strengths of the individual algorithms while minimizing their individual weaknesses. Comparisons of the developed systems are made with the standard homomorphic filter architecture and similar works from the literature.

A methodology for makeup invariant robust face recognition based on features from accelerated segment test and Eigen vectors is proposed. Makeup and cosmetic changes in face have been a major cause of security breaches since long time. It is not only difficult for human eyes to catch an imposter but also an equally daunting task for a face recognition system to correctly identify an individual owing to changes brought about in face due to makeup. As a crucial pre-processing step, the face is first divided into various segments centered on the eyes, nose, lips and cheeks. FAST algorithm is then applied over the face images. The features thus derived from the facial image act as the fiducial points for that face. Thereafter principal component analysis is applied over the set of fiducial points in each segment of every face image present in the data sets in order to compute the Eigen vectors and the Eigen values. The resultant principal component which is the Eigen vector with the highest Eigen value yields the direction of the features in that segment. The principal components thus obtained using fiducial points generated from FAST in each segment of the test and the training data are compared in order to get the best match or no match.

This work aims to enhance a classic method for rigid registration, the iterative closest point (ICP), modifying the closest point search in order to consider approximated information of local geometry combined to the Euclidean distance, originally used. For this, a preprocessing stage is applied, in which the local geometry is encoded in second-order orientation tensors. We define the CTSF, a similarity factor between tensors. Our method uses a strategy of weight variation between the CTSF and the Euclidean distance, in order to establish correspondences. Quantitative tests were made in point clouds with different geometric features, with variable levels of additive noise and outliers and in partial overlapping situations. Results show that the proposed modification increases the convergence probability of the method for higher angles, making the method comparable to state-of-art techniques.