The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A variety of flexible models have been proposed to detect objects in challenging real world scenes. Motivated by some of the most successful techniques, we propose a hierarchical multi-feature representation and automatically learn flexible hierarchical object models for a wide variety of object classes. To that end we not only rely on automatic selection of relevant individual features, but go beyond...
Self-localization is one of the key technologies in soccer robot system. However in the soccer robot system based on the omni-vision, it is hard to match the features extracted from the image to the real features existing in the world due to the large distortion in omni-vision images. This has become the main obstacle to precise self-localization based on the omni-vision. To solve this problem, a...
In this paper, the algorithm for 2D shape matching and retrieval is developed by using Fisher Barycenter Contour (FBcC). First, the shape is represented into 3D format using the signed enclosed area at each scale level of Barycenter Contour (BcC). Because of high dimension of the feature representation, the eigen Barycenter Contour (EBcC) is applied for dimensionality reduction. Then, the Fisher Barycenter...
This paper presents a method for accurately segmenting and classifying 3D range data into particular object classes. Object classification of input images is necessary for applications including robot navigation and automation, in particular with respect to path planning. To achieve robust object classification, we propose the idea of an object feature which represents a distribution of neighboring...
Latent semantic indexing (LSI), as a popular textual information retrieval approach, has been used heavily for many years. However, the use of the approach in image retrieval has been limited. In this paper, a method of using LSI in combination with the salient image representation based on a saliency-based bottom-up visual attention computational model (VACM) motivated by visual physiological experimental...
In this paper, we propose a local feature-based human motion analysis framework. Instead of using traditional analysis methods to characterize the global structure of human motion, we extract features directly from local regions that contain motion. To implement the above concept, we adopt the rules of visual attention theory, which assert that a human motion can be described simply by a set of local...
Object-based attention theory posits that attention is directed towards one object at a time. This paper attempts to simulate top-down influences. Five components of top-down influences are modeled: structure of object representation for long-term memory (LTM), learning of object representations, deduction of task-relevant features, estimation of top-down biases, mediation between bottom-up and top-down...
We present a novel classification scheme which uses partial object information that is selected adaptively using modified distance transform and represented as moment invariants (Hu moments) to compensate for scale, translation and rotational transformation(s). The moment invariants of different parts of an object are learned using AdaBoost algorithm [1]. The classifier obtained using the proposed...
We present an image based approach for coin classification. Gabor wavelets are used to extract features for local texture representation. To achieve rotation-invariance, concentric ring structure is used to divide the coin image into a number of small sections. Statistics of Gabor coefficients within each section is then concatenated into a feature vector for whole image representation. Matching between...
The context of this study is 3D video. Starting from a sequence of multi-view video plus depth (MVD) data, the proposed quad-based representation takes into account, in a unified manner, different issues such as compactness, compression, and intermediate view synthesis. The representation is obtained into two steps. Firstly, a set of 3D quads is extracted by using a quadtree decomposition of the depth...
The representation of human perception has become one of the most active research topics in image retrieval. This paper proposes a novel search result clustering based relevance feedback mechanism for image retrieval, in which the value of image co-occurrence is used for mining the association of images and then the tolerance rough class is adapt to capturing the relationship among images in image...
Monitoring urbanization is an important problem in remote sensing. Very high resolution satellite images provide valuable information to solve this problem. However, these images are not sufficient alone for two main reasons. First, a human expert should analyze very large images. There may always be some errors in operation. Second, urban regions are dynamic. Therefore, monitoring urbanization should...
In this work, 3-D representation of human faces is obtained in a computer using a DLP projection device and a high resolution camera. Calibration of the system is carried out automatically using an image frame that is taken employing a calibration pattern. Depth information is obtained utilizing color patterns that have been used widely in recent times instead of a gray-scale pattern. Experimental...
This paper presents a novel multiscale classification likelihood (MCL) estimation method using hierarchical wavelet-domain hidden Markov tree(WDHMT) model. The key idea is that with inter-scale communication and intra-scale interaction of the WDHMT model, we can capture hierarchical classification information of the pixels at the vicinity of the weak boundary. Our framework consists of the following...
It has been shown by researchers that using a multimodality approach can help in identifying better clusters in an image collection. The multimodal image features include low-level image features and available text annotations. This approach helps in identifying inherent relationships among different types of features associated with an image. In our approach, we divide images into small tiles and...
This paper presents a novel face recognition method based on the contourlet for facial features representation and using an new kernel based algorithm, for discriminating purposes, namely kernel relevance weighted discriminant analysis (KRWDA). This nonlinear reduction dimension algorithm has several interesting characteristics. First, using kernel theory, it handles nonlinearity efficiently. Second,...
We propose a hierarchical-grid (HG) feature analysis framework for representing images in automatic image annotation (AIA). We explore the properties of codebooks constructed with different-sized grids in image sub-blocks, and co-occurrence relationship between VQ codewords constructed from different grid systems. The proposed HG approach is evaluated on the TRECVID 2005 data set using classifiers...
We develop a new approach for gender recognition. In this paper, our approach uses the rectangle feature vector (RFV) as a representation to identify humans' gender from their faces. The RFV is computationally fast and effective to encode intensity variations of local regions of human face. By only using few rectangle features learned by AdaBoost, we present a gender identifier. We then use nonlinear...
Periodicity attracts special attention in human cognition. Hence it is important to consider that in automatic analysis of motion events. This paper presents a method for representing periodic events with which events can be compared irrespective of their duration. The effectiveness of such a representation is verified with event classification.
Many computer vision systems try to infer semantic information about a video scene content by looking at the time series of the silhouettes of the moving objects. This paper proposes a new inter-frame feature set (signature) based on piecewise surfacic descriptions of binary silhouettes. It captures the dynamics of moving objects and compacts it into a robust set of features suitable for classification...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.