Search

Multimedia security has become challenging due to large amount of content generation and its distribution over network. Copyright protection and content authentication are the major key factor that avoids illegal distribution of digital data. However, due to availability of high bandwidth network, copyright violation is very common and many copies of data can be illegally distributed over network. Thus, to ensure multimedia security, image watermarking methods have been introduced which is a kind of information hiding technique. Watermarking provides an effective way to ensure copyright protection and content authentication and can be implemented in spatial and transform domain. The use of wavelet transforms in watermarking increases the embedding capacity and enhances the imperceptibility of the watermarked image. Being motivated from the use of wavelet transforms in image watermarking, in this chapter, a hybrid combination of the wavelet transforms have been discussed for single and multiple image watermarking. The transforms, combined in this chapter, are nonsubsampled contourlet transform (NSCT), discrete cosine transform (DCT) and multiresolution singular value decomposition (MSVD). This hybrid combination will take advantage of the characteristics and NSCT, DCT and MSVD to build a robust watermarking system in wavelet domain against signal processing and geometrical attacks.

Fusion of multisensor images has shown a potential application in various application domains such as security, medical imaging etc. The recent developments in medical imaging sensors have been a great motivation for fusion due to their complementary nature. This chapter aims to address medical image fusion in complex wavelet domain and provides a detailed study of fusion methods. The wavelet transforms based fusion methods are ahead of other methods in terms of signal representation, complementary information and redundancy. These properties make wavelet transforms suitable for multisensory image fusion. The fusion experiments have been demonstrated over several sets of medical images for different fusion rules in complex wavelet domain. Visual and quantitative evaluation of the proposed fusion results with state-of-the-art fusion methods showed the effectiveness and goodness of the complex wavelet transform based fusion methods.

The large availability and access of video data for education, entertainment such as games and movies poses several challenges of copyright violation and illegal distribution of data. More specifically, pirated video distribution has been a key threat for such copyright violation. To handle these challenges, watermarking techniques can be used to provide copyright protection. The wide application of wavelet transform in the implementation of image watermarking techniques compelled to discuss wavelet domain video watermarking techniques in this chapter. The present chapter provides an overview of video watermarking techniques in wavelet domain and discusses various methods used for embedding and extraction of watermark. It also provides the description of various attacks and key characteristics of video watermarking techniques with comparative analysis of results for evaluation of the existing methods.

This chapter proposes a new method of camouflaged person identification that combines discrete wavelet coefficients with support vector machine (SVM) classifier. Multiresolution property of wavelet transform provides invariant person identification against camouflaged scenes and do not get affected by similar foreground and background objects. Flexibility of wavelet and SVM makes the proposed method robust while providing better efficiency. For evaluation of the proposed method, we have experimented it over CAMO_UOW dataset. From objective evaluation it is clear that proposed approach outperforms existing camouflaged person identification approaches. The proposed methodology is simple and does not depend on a specific special resolution. It is suitable for detecting camouflaged persons in the images or videos where foreground and background are almost similar.

The huge amount of multimedia data available over Internet compelled to adopt new methodologies day by day. It becomes extremely complex to process and filter data as per user requirements. Hence, new tools, technologies are being used one after another. In this era of artificial intelligence, where machine and deep learning has been evolved, there is a great requirement of intelligent multimedia processing to fulfill and meet the requirements of users. With this aim, this chapter discusses a few key challenges in the visual information processing that are directly related to the societal benefits. Its major components are healthcare, education, transportation and security. A methodological enhancement of the techniques are being discussed to provide future research directions to the multimedia applications in wavelet domain.

Wavelet transforms have become an important mathematical tool that has been widely explored for visual information processing. The wide range of wavelet transforms and their multiresolution analysis facilitate to solve complex problems ranging from simple to complex image and vision based problems. The present chapter aims to provide an overview of existing wavelet transforms ranging from classical to new generation wavelets. This chapter discusses the basics of the discrete wavelet transform (DWT) followed by new generation wavelet transforms and highlights their useful characteristics. Other than DWT, the present chapter provides a brief review on dual tree complex wavelet transform (DTCWT), curvelet transform (CVT), contourlet transform (CT), contourlet transform (CNT), nonsubsampled contourlet transform (NSCT) to provide fundamentals and understanding of the wavelet transforms.

This study demonstrates analysis of an advanced technique that enhances performance of facial expression recognition method. Face preprocessing is conducted by face cropping. These cropped faces are rescaled by using bilinear interpolation. Multi-scale wavelet is used for extraction of facial patterns. Extracted features are down-sampled using principal component analysis (PCA) to reduce execution time as well as misclassification. The approach reduced the image dimensions and preserved the perceptual quality of the original images. Downsampled features are classified using multiclass support vector machine (SVM) that has a one versus all architecture. This system is trained with benchmark JAFFE and CK+ facial expression datasets. Performance of wavelet is compared with other existing frequency domain techniques and wavelets are found better in terms of recognition rate.

This chapter analyses real world human activity recognition problem. It uses discrete wavelet transform and multiclass support vector machine (SVM) classifier for recognition. The experiments are done using Weizmann and KTH action datasets. Objective evaluation is done for nine activities walk, run, bend, gallop sideways, jumping jack, one handwave, two handwave, jump in place and skip from Weizmann dataset. Six activities that are considered from KTH dataset are handwaving, running, walking, boxing, jogging and handclapping. Results are shown qualitatively as well as quantitatively on two publicly available dataset Weizmann and KTH. Quantitative evaluations demonstrate better performance of the proposed method in comparison to the existing methods.

Facial expression recognition plays a significant role in human behavior detection. In this study, we present an efficient and fast facial expression recognition system. We introduce a new feature called W_HOG where W indicates discrete wavelet transform and HOG indicates histogram of oriented gradients feature. The proposed framework comprises of four stages: (i) Face processing, (ii) Domain transformation, (iii) Feature extraction and (iv) Expression recognition. Face processing is composed of face detection, cropping and normalization steps. In domain transformation, spatial domain features are transformed into the frequency domain by applying discrete wavelet transform (DWT). Feature extraction is performed by retrieving Histogram of Oriented Gradients (HOG) feature in DWT domain which is termed as W_HOG feature. For expression recognition, W_HOG feature is supplied to a well-designed tree based multiclass support vector machine (SVM) classifier with one-versus-all architecture. The proposed system is trained and tested with benchmark CK+, JAFFE and Yale facial expression datasets. Experimental results of the proposed method are effective towards facial expression recognition and outperforms existing methods.

Human behavior understanding techniques are proposed for several applications likewise object recognition, face detection, emotion detection, action detection, finger print identification, gait recognition, voice recognition, etc. Emotion and action recognition are the most popular applications among them. This chapter presents an analysis of recently developed deep learning techniques for emotion and activity recognition. Existing approaches are discussed that use deep learning as their core component. Experimental results are reported on benchmark datasets i.e. CK+ and SFEW datasets for emotion recognition, and Skoda and UCF 101 datasets for activity recognition. Experimentation shows that deep learning methods outperform other existing techniques in literature and demonstrate great performance.

Facial expressions are direct means of communication of human’s emotional state. Hence facial expression recognition (FER) has always been a topic of great interest of researchers specially for smart applications. Numerous approaches have been proposed for FER using Local binary patterns (LBP). This chapter presents an analysis of LBP feature descriptor for FER. State of the art approaches have been discussed that use LBP as their main component. Here, basic LBP operator along with several variants and their main properties are described that have been proved useful for FER. A general framework for FER is described which includes four consecutive modules. These modules are preprocessing, feature extraction, dimensionality reduction and classification. LBP based FER results have been reported on three benchmark datasets JAFFE, CK+ and Yale. Experimentation demonstrates usefulness of LBP in FER.

Computer vision techniques capable of detecting human behavior are gaining interest. Several researchers have provided their review on behavior detection, however most of the reviews are focused on activity recognition only, and reviews on gesture and facial expression recognition are very few. Therefore, all of them lack to cover complete human behavior analysis. In this study, we provide a comprehensive review of human behavior detection approaches. The framework of this review is based on activity, gesture and facial expression recognition since these are the most important cues for behavior detection. These three areas are further classified in existing computational approaches. One can easily recognize from this review that hidden Markov model is widely exploited for activity recognition while motion history image is still a developing area. Haar-like features can be a valid alternative for gesture recognition. For facial expression recognition, local binary patterns feature is a very popular choice. We have reviewed behavior detection techniques, mostly developed after year 2009. The explicit advantages of this review are: (1) it provides a deep analysis of computational approaches for activity, gesture and facial expression recognition. (2) It includes both types of techniques that include single human as well as multiple human activities. (3) It considers techniques developed in the last decade only pertaining to information about the most recent techniques. (4) It provides a brief description of popular datasets used for activity, gesture and facial expression recognition. (5) It discusses open issues to provide an insight for future also.

Computer vision techniques are capable of detecting human behavior from video sequences. Several state-of-the-art techniques have been proposed for human behavior detection and analysis. However, a collective framework is always required for intelligent human behavior analysis. Therefore, in this chapter, the authors provide a comprehensive understanding towards human behavior detection approaches. The framework of this chapter is based on human detection, human tracking, and human activity recognition, as these are the basic steps of human behavior detection process. The authors provide a detailed discussion over the human behavior detection framework and discuss the feature-descriptor-based approach. Furthermore, they have provided qualitative and quantitative analysis for the detection framework and demonstrate the results for human detection, human tracking, and human activity recognition.

In this study, we present a method for human activity recognition in video sequences. Human activities are often described by a holistic feature vector comprising of a set of local motion descriptors. Here, we use a novel local shape feature descriptor for human activity recognition which is an integration of moment invariants and uniform local binary patterns (MI_ULBP). This feature descriptor is passed to a binary support vector machine pattern classifier for classification of human activities. Activity recognition is achieved through probabilistic search of image feature database representing previously seen activities. Experiments are performed over four benchmark video datasets Weizmann, KTH, CASIA and Collective human activity. Visual results and quantitative comparisons with existing methods show that the proposed method gives better recognition of human activities in video sequences with varying backgrounds and viewpoints.

Human detection is a central problem in development of any surveillance application. In this study, we present a simple and efficient, multi-resolution gray scale invariant approach for multiple human detection. The multiresolution is important for objects of different size and gray scale invariance is important due to uneven illumination and within-class variability. The proposed method is based on integration of central moments upon multi-resolution gray scale invariant local binary patterns operator. Since, the local binary patterns operator is invariant against different resolutions of space scale and monotonic change in gray scale, therefore the proposed method is robust in terms of variations in space scale as well as gray scale. Another advantage is high computational accuracy of the method due to use of moment operator which enhances the efficiency of the proposed method. Moreover, the proposed method is simple, as these operations can be performed within a few steps in a small neighborhood and a lookup table. The proposed method is tested on multiple human images and experimentally found appropriate for multiple human detection. The proposed method has been evaluated over two datasets, one is our own created dataset and the other is standard INRIA human detection dataset. Experimental results obtained from the proposed method demonstrate that better discrimination can be achieved for human and non-human objects in real scenes.

Facial expression is an important cue for emotion recognition in human behavior analysis. In this work, we have improved the recognition accuracy of facial expression recognition and presented a system framework. The framework consists of three modules: image processing, facial features extraction, and facial expression recognition. The face preprocessing component is implemented by cropping the facial area from images. The detected face is downsampled by bilinear interpolation to reduce the feature extraction area and to enhance execution time. For extraction of local motion-based facial features, we have used rotation-invariant uniform local binary patterns (LBP). A hierarchical multiscale approach has been adopted for computation of LBP. The selected features were fed into a well-designed tree-based multiclass SVM classifier with one-versus-all architecture. The system is trained and tested with benchmark dataset from JAFFE facial expression database. The experimental results of the proposed techniques are effective toward facial expression recognition and outperform other methods.

Recognizing human activities is an important component of a context aware system. In this paper, we propose a classification based human activity recognition approach. This approach recognizes different human activities based on a local shape feature descriptor and pattern classifier. We have used a novel local shape feature descriptor which is integration of central moments and local binary patterns. Classifier used is flexible binary support vector machine. Experimental evaluations have been performed on standard Weizmann activity video dataset. Six different activities have been considered for evaluation of the proposed method. Two activities have been selected at a time with binary classifier. These are walk-run, bend-jump, and jack-skip pairs. Experimental results and comparisons with other methods, demonstrate that the proposed method performs well and it is capable of recognizing six different human activities in videos.

In this study, we advocate the importance of robust local features that allow object form to be distinguished from other objects for detection purpose. We start from the grid of Histogram of oriented gradients (HOG) and integrate Scale Invariant Feature Transform (SIFT) within them. In HOG features an object's appearance is detected by the distribution of local intensity gradients or edge directions for different cells. In the proposed method we have computed the SIFT despite of computing intensity gradients for these cells. In this way, the proposed approach does not only provide more significant information than just providing intensity gradients but also proves to deal with following challenges: (i) scale invariance; (ii) rotation invariance; (iii) change in illumination; and (iv) change in view points. With qualitative and quantitative experimental evaluation on standard INRIA dataset, we have compared the proposed method with other state of the art object detection methods and demonstrated better performance over them.

Moving object segmentation is an important step toward development of any computer vision systems. In the present work, we have proposed a new method for segmentation of moving objects, which is based on single change detection method applied on Contourlet coefficients of two consecutive frames. We have chosen contourlet transform as it has high directionality and represents salient features of image such as edges, curves and contours in better way as compared with wavelet transform. The proposed method is simple and does not require any other parameter except contourlet coefficients. Results after applying the proposed method for segmentation of moving objects are compared with other state-of-the-art methods in terms of visual as well as quantitative performance measures viz. Average difference, Normalized absolute error and Pixel classification based measure. The proposed method is found to be better than other methods.

In this paper, we describe a novel template matching based approach for recognition of different human activities in a video sequence. We model the background in the scene using a simple statistical model and extract the foreground objects present in a scene. The matching templates are constructed using the motion history images (MHI) and spatial silhouettes for recognizing activities like walking, standing, bending, sleeping and jogging in a video sequence. Experimental results demonstrate that the proposed method can recognize these activities accurately for standard KTH database as well as for our own database.

In this paper, we have proposed a new character recognition method for Oriya script which is based on curvelet transform. Multi font Oriya character recognition has not been attempted previously. Ten popular Oriya fonts have been used for the purpose of character recognition. The wavelet transform has widely been used for character recognition purpose, but it cannot well describe curve discontinuities. We have used curvelet transform for recognition which is done using curvelet coefficients. This method is suitable for Oriya character recognition as well as various other scripts’ recognition purpose also. The proposed method is simple and extracts effectively the features in target region, which characterizes better and represents more robustly the characters. The experimental results validate that the proposed method improves greatly the recognition accuracy and efficiency than other traditional methods.

In this paper, we have proposed a new object tracking method in video sequences which is based on curvelet transform. The wavelet transform has widely been used for object tracking purpose, but it cannot well describe curve discontinuities. We have used curvelet transform for tracking. Tracking is done using energy of curvelet coefficients in sequence of frames. This method is suitable for object tracking as well as human object tracking purpose also. The proposed method is simple and does not require any other parameter except curvelet coefficients. Experimental results demonstrate performance of this method.

This study provides an object tracking method in video sequences, which is based on curvelet transform. The wavelet transform has been widely used for object tracking purpose, but it cannot well describe curve discontinuities. We have used curvelet transform for tracking. Tracking is done using energy of curvelet coefficients in sequence of frames. The proposed method is simple and does not rely on any other parameter except curvelet coefficients. Compared with a number of schemes like Kalman filter, particle filter, Bayesian methods, template model, corrected background weighted histogram, joint colour texture histogram and covariance-based tracking methods, the proposed method extracts effectively the features in target region, which characterise better and represent more robustly the target. The experimental results validate that the proposed method improves greatly the tracking accuracy and efficiency than traditional methods.