Ezzeddine Zagrouba

Are Existing Procedures Enough? Image and Video Quality Assessment: Review of Subjective and Objective Metrics

Images and videos are subject to a wide variety of distortions during acquisition, digitizing, processing, restoration, compression, storage, transmission and reproduction, any of which may result in degradation in visual quality. That is why image quality assessment plays a major role in many image processing applications. Image and video quality metrics can be classified by using a number of criteria such as the type of the application domain, the predicted distortion (noise, blur, etc.) and the type of information needed to assess the quality (original image, distorted image, etc.). In the literature, the most reliable way of assessing the quality of an image or of a video is subjective evaluation [1], because human beings are the ultimate receivers in most applications. The subjective quality metric, obtained from a number of human observers, has been regarded for many years as the most reliable form of quality measurement. However, this approach is too cumbersome, slow and expensive for most applications [2]. So, in recent years a great effort has been made towards the development of quantitative measures. The objective quality evaluation is automated, done in real time and needs no user interaction. But ideally, such a quality assessment system would perceive and measure image or video impairments just like a human being [3]. The quality assessment is so important and is still an active and evolving research topic because it is a central issue in the design, implementation, and performance testing of all systems [4, 5]. Usually, the relevant literature and the related work present only a state of the art of metrics that are limited to a specific application domain. The major goal of this paper is to present a wider state of the art of the most used metrics in several application domains such as compression [6], restoration [7], etc. In this paper, we review the basic concepts and methods in subjective and objective image/video quality assessment research and we discuss their performances and drawbacks in each application domain. We show that if in some domains a lot of work has been done and several metrics were developed, on the other hand, in some other domains a lot of work has to be done and specific metrics need to be developed.

Advanced tree species identification using multiple leaf parts image queries

There has recently been increasing interest in using advanced computer vision techniques for automatic plant identification. Most of the approaches proposed are based on an analysis of leaf characteristics. Nevertheless, two aspects have still not been well exploited: (1) domain-specific or botanical knowledge (2) the extraction of meaningful and relevant leaf parts. In this paper, we describe a new automated technique for leaf image retrieval that attempts to take these particularities into account. The proposed method is based on local representation of leaf parts. The part-based decomposition is defined and usually used by botanists. The global image query is a combination of part sub-images queries. Experiments carried out on real world leaf images, the Pl@ntLeaves scan images (3070 images totalling 70 species), show an increase in performance compared to global leaf representation.

Abnormal behavior recognition for intelligent video surveillance systems

Different levels of an intelligent video surveillance system (IVVS) are studied in this review.Existing approaches for abnormal behavior recognition relative to each level of an IVVS are extensively reviewed.Challenging datasets for IVVS evaluation are presented.Limitations of the abnormal behavior recognition area are discussed. With the increasing number of surveillance cameras in both indoor and outdoor locations, there is a grown demand for an intelligent system that detects abnormal events. Although human action recognition is a highly reached topic in computer vision, abnormal behavior detection is lately attracting more research attention. Indeed, several systems are proposed in order to ensure human safety. In this paper, we are interested in the study of the two main steps composing a video surveillance system which are the behavior representation and the behavior modeling. Techniques related to feature extraction and description for behavior representation are reviewed. Classification methods and frameworks for behavior modeling are also provided. Moreover, available datasets and metrics for performance evaluation are presented. Finally, examples of existing video surveillance systems used in real world are described.

Video Action Classification: A New Approach Combining Spatio-temporal Krawtchouk Moments and Laplacian Eigenmaps

Action classification and recognition is a challenging research area that has significant applications in computer vision domain including robotics, video surveillance, human-computer interaction and multimedia retrieval. Action classification domain uses a large variety of approaches. This paper proposes a new approach for video actions classification based on extension of Krawtchouk moments in spatio-temporal domain. In fact, Krawtchouk moments have interesting properties for describing structural and temporal information of a time varying video sequence. The proposed approach is composed of three main steps. First, the original video is transformed into a spatiotemporal volume of images. Then, silhouettes of human in movement are extracted from these images to define a 3D shape. In the third step, higher order spatio-temporal Krawtchouk moments are applied to the obtained 3D shapes and Laplacian eigenmaps is used to achieve dimension reduction for different moments vectors. Finally, we use SVM algorithm and computed descriptors to classify actions in videos. This new approach has been validated on the two video datasets Weizmann and KTH. Experimental results show a good classification rate compared to other approaches using different descriptors.

A New Approach of Mesh Watermarking Based on Maximally Stable Meshes Detection

Watermarking 3D meshes is very important in many areas of activity including digital cinematography, virtual reality as well as in CAD design. Due to the complexity of 3D meshes, mesh watermarking schemes are far from the maturity of watermarking algorithms dedicated to audio, image or video watermarking. According to our knowledge, no existing scheme is robust against all attacks. To verify a good trade-off between invisibility and robustness, a new approach of 3D mesh watermarking algorithm based on MSMs detection is proposed in this paper. In this algorithm, only invariant regions are marked. These invariant regions are called Maximally Stable Meshes (MSMs) and they present an extension of the well-known Maximally Stable Extremal Regions (MSER) detected for 2D images. First, an efficient way to detect MSMs in 3D meshes by using curvature measures of vertices is presented. Then, obtained MSMs are marked with a geometric watermarking scheme. The experimentations show that this new watermarking is robust against numerous attacks including rotation, zooming, translation, cropping, simplification, and remeshing. Moreover, it gives a good invisibility and a blind extraction.

ReviewAbnormal behavior recognition for intelligent video surveillance systems: A review

Different levels of an intelligent video surveillance system (IVVS) are studied in this review.Existing approaches for abnormal behavior recognition relative to each level of an IVVS are extensively reviewed.Challenging datasets for IVVS evaluation are presented.Limitations of the abnormal behavior recognition area are discussed. With the increasing number of surveillance cameras in both indoor and outdoor locations, there is a grown demand for an intelligent system that detects abnormal events. Although human action recognition is a highly reached topic in computer vision, abnormal behavior detection is lately attracting more research attention. Indeed, several systems are proposed in order to ensure human safety. In this paper, we are interested in the study of the two main steps composing a video surveillance system which are the behavior representation and the behavior modeling. Techniques related to feature extraction and description for behavior representation are reviewed. Classification methods and frameworks for behavior modeling are also provided. Moreover, available datasets and metrics for performance evaluation are presented. Finally, examples of existing video surveillance systems used in real world are described.

Automated semantic leaf image categorization by geometric analysis

Unravelling mysteries of the diversity of the plant community is a crucial issue both for the development of many botanical industries as well as for the conservation of ecosystem biodiversity. Traditionally, botanists have proposed detailed dichotomous key descriptions (called also characters or concepts) about the morphology of plants and particularly of leaves that allow them to construct relationships between different plants and between plants and their environment. However, extracting these concepts is complicated, painstaking and can only be carried out by experts. One way to accelerate and broaden the use of these concepts is to automatically extract them directly from images. In this paper, we focus on one of the most basic and important concepts: the leaf arrangement. According to this concept, leaves are divided into four categories: simple, pinnnately compound, palmately compound and compound trifoliate. To accomplish this task, we follow a hierarchical scheme, reducing ambiguity between categories from the most different shapes to the most similar ones. The choice of appropriate features is performed based on botanical observations and validated by a statistical study. The method was tested on real world leaf images (the Pl@ntLeaves scans). Experimental results show its robustness for a high number of leaf species (70 species) and even in the presence of some distortions (such as rotation and partial leaf overlapping).

No-reference Image Semantic Quality Approach using Neural Network

Assessment for image quality traditionally needs its original image as a reference but the most of time it is not the case. So, No-Reference (NR) Image Quality Assessment (IQA) seeks to assign quality scores that are consistent with human perception but without an explicit comparison with the reference image. Unfortunately, the field of NR IQA has been largely unexplored. This paper presents a new NR Image Semantic Quality Approach (NR-ISQA) that employs adaptive Neural Networks (NN) to assess the semantic quality of image color. This NN measures the quality of an image by predicting the mean opinion score (MOS) of human observer, using a set of proposed key features especially to describe color. This challenging issues aim at emulating judgment and replacing very complex and time-consuming subjective quality assessment. Two variants of our approach are proposed: the direct and the progressive of the overall quality image. The results show the performances of the proposed approach compared with the human performances.

A New PSO Based Kernel Clustering Method for Image Segmentation

In this paper a novel kernel clustering method is proposed. The application of the proposed clustering algorithm to the problem of unsupervised classification and image segmentation task is investigated. The proposed method provides a new scheme for classifying objects of one data set without any prior knowledge on the number of naturally occurring regions in the data or an assumption on clusters shapes. Its based on the use of Particle Swarm Optimization (PSO) algorithm and the use of core set concept which is commonly used to resolve the Minimum Enclosing Ball (MEB) problem. The performance of the proposed method has been compared with a few state of the art kernel clustering methods over a test of artificial data and the Berkeley image segmentation dataset.

Semantic-based automatic structuring of leaf images for advanced plant species identification

Structuring the search space based on domain-specific vocabulary (or concepts) is capital for enhanced image retrieval. In this paper, we study the opportunities and the impact of exploiting such a strategy in a particular problem which is the leaf species identification. We believe that such a solution is promising to reduce the effect of the high variability across and within species and define more specific and relevant leaf image representations. Among botanical concepts that describe leaves (and particularly their architecture), we focus mainly on three of the most basic and commonly-used concepts: the leaf arrangement, lobation and partition. These concepts define two different structuring types: (1) One is a coarse categorisation of leaf datasets into three subsets, namely simple lobed, simple not lobed and compound (2) The other is a decomposition of the entire leaf images into semantic regions (or parts). We perform the whole structuring process automatically by defining simple geometric parameters (extracted from the leaf contour) based on the analysis of botanical definitions. A fine recognition process is then established in order to determine the species identity. It is defined, typically, using standard (texture or contour) descriptors followed by a KNN classifier. Enriched by the proposed structuring process, the search for species candidates will be restricted to the correspondent category of the query and based on a fusion of each part responses. Experiments carried out on the Scan Pictures of the ImageCLEF 2011 dataset (3070 images totalling 70 species) have shown an increase in performances for different descriptor configurations compared to global leaf representations as well as to some recent related studies.