Object Extraction Using Topological Models from Complex Scene Image

Efficient and effective object recognition from a multimedia data are very complex. Automatic object segmentation is usually very hard for natural images; interactive schemes with a few simple markers provide feasible solutions. In this chapter, we propose topological model based region merging. In this work, we will focus on topological models like, Relative Neighbourhood Graph (RNG) and Gabriel graph (GG), etc. From the Initial segmented image, we constructed a neighbourhood graph represented different regions as the node of graph and weight of the edges are the value of dissimilarity measures function for their colour histogram vectors. A method of similarity based region merging mechanism (supervised and unsupervised) is proposed to guide the merging process with the help of markers. The region merging process is adaptive to the image content and it does not need to set the similarity threshold in advance. To the validation of proposed method extensive experiments are performed and the result shows that the proposed method extracts the object contour from the complex background.

Invariant Model Combining Geometry and Appearance for Facial Detection and Gender Classification From Arbitrary Viewpoints

In this chapter, we tackle in the same process the problems of face detection and gender classification, where the faces present a wide range of the intra-class appearance are taken from arbitrary viewpoints. We try to develop complete probabilistic model to represent and learn appearance of facial objects in both shape and geometry with respect to a landmark in the image, and then to be able to predict presence and position of the appearance of the studied object class in new scene. After have predicted the facial appearance and the geometry of invariants, geometric hierarchical clustering combines different prediction of positions of face invariant. Then, the algorithm of cluster selection with a best appearance localizes faces in the image. Using a probabilistic classification, each facial feature retained in the detection step will be weighted by a probability to be male or female. This set of features contributes to determine the gender associated to a detected face. This model has a good performance in presence of viewpoint changes and a large appearance variability of faces.

Cross-Domain Usage in Real-Time Video-Based Tracking

This chapter emphasizes on the approach to include information from different type of sensors into the visible domain real time tracking. Since any individual sensor is not able to retrieve the complete information, so it is better to use information from distinct category of sensors. The chapter firstly enlightens the significance of introducing the cross-domain treatment into video based tracking. Following this, some previous work in the literature related to this idea is briefed. The chapter introduces the categorization of the cross-domain activity usage for real time object tracking and then each category is separately discussed in detail. The advantages as well as the limitations of each type of supplemented cross domain activity will be discussed. Finally, the recommendation and concluding remarks from the authors in lieu of future development of this cutting-edge field will be presented.

Computed Tomography Brain Images Semantic Segmentation

In this paper we applianced an approach for segmenting brain tumour regions in a computed tomography images by proposing a multi-level fuzzy technique with quantization and minimum computed Euclidean distance applied to morphologically divided skull part. Since the edges identified with closed contours and further improved by adding minimum Euclidean distance, that is why the numerous results that are analyzed are very assuring and algorithm poses following advantages like less cost, global analysis of image, reduced time, more specificity and positive predictive value.

Radial Moments for Image Retrieval

Images have always been considered an effective medium for presenting visual data in numerous applications ranging from industry to academia. Consequently, managing and indexing of images become essential in order to retrieve relevant images effectively and efficiently. Therefore, the proposed chapter aims to elaborate one of the advanced concepts of image processing, i.e., Content Based Image Retrieval (CBIR) and image feature extraction using advanced methods known as radial moments. In this chapter, various radial moments are discussed with their properties. Besides, performance measures and various similarity measures are elaborated in depth. The performance of radial moments is evaluated through an extensive set of experiments on benchmark databases such as Kimia-99, MPEG-7, COIL-100, etc.

Medical Image Fusion in Spatial and Transform Domain

Nowadays, there are a lot of medical images and their numbers are increasing day by day. These medical images are stored in the large database. To minimize the redundancy and optimize the storage capacity of images, medical image fusion is used. The main aim of medical image fusion is to combine complementary information from multiple imaging modalities (e.g. CT, MRI, PET, etc.) of the same scene. After performing medical image fusion, the resultant image is more informative and suitable for patient diagnosis. There are some fusion techniques which are described in this chapter to obtain fused image. This chapter presents two approaches to image fusion, namely spatial domain Fusion technique and transforms domain Fusion technique. This chapter describes Techniques such as Principal Component Analysis which is spatial domain technique and Discrete Wavelet Transform and Stationary Wavelet Transform which are Transform domain techniques. Performance metrics are implemented to evaluate the performance of image fusion algorithm.

Image Retrieval Techniques Using Content-Based Local Binary Descriptors

In this chapter authors introduces content-based image retrieval systems and compares them over a common database. For this, four different content-based local binary descriptors are described with and without Gabor transform in brief. Further Nth derivative descriptor is calculated using (N-1)th derivative, based on rotational and multiscale feature extraction. At last the distance based query image matching is used to find the similarity with database. The performance in terms of average precision, average retrieval rate, different orders of derivatives in the form of average retrieval rate, and length of feature vector v/s performance in terms of time have been calculated. For this work a comparative experiment has been conducted using the Ponce Group images on seven classes (each class have 100 images). In addition, the performance of the all descriptors have been analyzed by combining these with the Gabor transform.

Moving Object Classification in a Video Sequence Using Invariant Feature Extraction

Object recognition and classification (human beings, animals, buildings, vehicles) has become important in a surveillance video situated at prominent areas such as airports, banks, military installations etc., Outdoor environments are more challenging for moving object classification because of incomplete appearance details of moving objects due to occlusions and large distance between the camera and moving objects. As such, there is a need to monitor and classify the moving objects by considering the challenges of video in the real time. Training the classifiers using feature based is easier and faster than pixel-based approaches in object classification. Extraction of a set of features from the object of interest is most important for classification. Textural features, color features and structural features can be chosen for classifying the object. But in real time video, object poses are not always the same. Zernike moments have been shown to be rotation invariant and noise robust due to Orthogonality property.

Electrical Impedance Tomography

Presently, non-invasive techniques are in vogue and preferred standard clinical approach because of its limitless advantages in monitoring real time phenomenon occurring within our human body without much interference. Many techniques such as ultrasound, magnetocardiography, CT scan, MRI etc., are used for real time monitoring but are generally not recommended for continuous monitoring. The limitations created by above used techniques are overcome by a proposed technique called non-invasive bio-impedance technique such as Electrical Impedance Technique (EIT). EIT imaging technique is based on internal electrical conductivity distribution of the body. The reconstruction of cross sectional image of resistivity required sufficient data collection by finite element method using MATLAB software. The EIT technique offers some benefits over other imaging modalities. It is economical, non-invasive, user friendly and emits no radiation thus appears to be one of the best fit technology for mass health care to be used by the basic health worker at a community level.

Recognition of Face Biometrics

In the proposed chapter, a novel, effective, and efficient approach to face recognition is presented. It is a fusion of both global and local features of images, which significantly achieves higher recognition. Initially, the global features of images are determined using polar cosine transforms (PCTs), which exhibit very less computation complexity as compared to other global feature extractors. For local features, the rotation invariant local ternary patterns are used rather than using the existing ones, which help improving the recognition rate and are in alignment with the rotation invariant property of PCTs. The fusion of both acquired global and local features is performed by mapping their features into a common domain. Finally, the proposed hybrid approach provides a robust feature set for face recognition. The experiments are performed on benchmark face databases, representing various expressions of facial images. The results of extensive set of experiments reveal the supremacy of the proposed method over other approaches in terms of efficiency and recognition results.