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.
Tactic analysis is receiving more attention in sports video analysis for its assistance to coaches and players. This paper proposes an efficient key sub-trajectory feature representation of ball trajectory for tactic analysis. Ball trajectories are modeled with the generalized suffix tree where frequent sub-trajectory patterns are searched for. Key sub-trajectory patterns are extracted by further...
We describe a method for filtering object category from a large number of noisy images. This problem is particularly difficult due to the greater variation within object categories and lack of labeled object images. Our method deals with it by combining a co-training algorithm CoBoost with two features - 1st and 2nd order features, which define bag of words representation and spatial relationship...
Nearest neighbor search of feature vectors representing local features is often employed for specific object recognition. In such a method, it is required to store many feature vectors to match them by distance calculation. The number of feature vectors is, in general, so large that a huge amount of memory is needed for their storage. A way to solve this problem is to skip the distance calculation...
We study the problem of robust pedestrian detection. A new descriptor, Pyramidal Statistics of Oriented Filtering (PSOF), is proposed for shape representation. Unlike one-scale gradient-based methods, the PSOF descriptor constructs an image pyramid and uses a Gabor filter bank to obtain multi-scale pixel-level orientation information. Then, locally normalized pyramidal statistics of these Gabor responses...
Noise is inevitably introduced to medical images because of various factors in medical imaging. The noise in medical images degrades the quality of images, blurring boundaries and suppressing structural details, thus bring difficulties to medical diagnosis. Therefore, the key to medical image de-noising is to remove the noise while preserving important features. In this paper, we analyze and compare...
A data-driven technique is presented for automatically learning cortical folding patterns from MR brain images of different subjects. Cortical patterns are represented in terms of generic scale-invariant image features. Learning automatically identifies a set of features that occur with statistical regularity in appearance and geometry from a large set of MR volume renderings, based on a predescribed...
Selecting automatically feature points of an object appearing in images is a difficult but vital task for learning the feature point based representation of the object model. In this work we present an incremental Bayesian model that learns the feature points of an object from natural un-annotated images by matching the corresponding points. The training set is recursively expanded and the model parameters...
An image hashing provides a compact representation of an image that can be used for authenticating that image. This paper presents a new approach for generating an image hashing that is resilient to content-preserving modifications and at the same time, is capable of detecting malicious tampering. The invariant features are extracted via DWT and Radon transform followed by log mapping and then Fourier...
The feature matching is the first step of several computer vision duties. In this paper we provide a new feature detect and matching approach based on statistics of the gradients of the feature region. It is extension of the sift algorithm. The algorithm represented in this paper can be used to perform reliable matching to image sequence, which have larger change in 3D viewpoint and change in illumination...
This paper presents a texture image segmentation algorithm using spectral histogram and skeleton extracting. No need of selecting seed pixels or specifying or deciding the number of regions is its remarkable characteristic. Based on a local spatial/frequency representation, spectral histogram consists of marginal distributions of responses of a bank of filters and encodes implicitly the local structure...
This paper presents a novel algorithm for unsupervised texture segmentation. We incorporate a set of texture features under a segmentation framework, based on the active contour without edges model with level set representation and a connected component filtering strategy. The experiments performed show that, it can be used for segmentation of multiple-textured images, with a segmentation quality...
A new unsupervised filter-based feature selection method is introduced. Its principle consists in merging similar features into clusters using a distance measure derived from the correlation coefficient. Subsequently, only one representative feature is selected from each cluster. In experiments with real-world data, we show that the proposed method is benefical as a pre-filtering step for more sophisticated...
This paper presents a new Sobel-LBP, an extension of existing local binary pattern (LBP), for facial image representation. The face image is filtered by Sobel operator to enhance the edge information. Sobel-LBP feature distributions are then extracted and concatenated into a spatial histogram to be used as a face descriptor. The proposed method is compared with the original LBP on both gray-level...
In this paper we propose a novel vision-based global localization method based on a hybrid map representation. We employ PCA-SIFT features as visual landmarks and represent the environment with a hybrid map which consists of a global topological map and local metric maps. To localize where a mobile robot is placed, we extract visual features from the currently captured view and match them to the feature...
In the field of face recognition (FR), the techniques that can provide effective feature representation with enhanced discriminability are crucial. Although the separable wavelet transform has played an important role in image processing, it suffers from some shortcomings which badly affect its ability for feature generation. In this paper, we propose a novel FR system combining the dual-tree complex...
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a few discrete views. We propose instead to build 3D representations of object classes which allow to handle viewpoint changes and intra-class variability. Our approach extracts a set of pose and class discriminant features...
For speedy robust object recognition, our model builds on Serre’s standard model and modifies it by additional biological characteristics, such as introducing the manner of neuron firing, feature localization, and merging unit features in the higher layers. According to the four-layer architecture of standard model, we first apply Gabor filters on a higher intermediate frequency band of original image,...
In this paper, we propose an algorithm for face detection in 2D intensity images. The method has two steps: extracting face candidates and filtering out the false positives. In the first stage we provide a face model by combining intensity and edginess information of face image. The extracted features are fuzzified to overcome the problem of variations in imaging system. We provide a fuzzy model for...
Texture, a representation of the spatial relationship of gray levels in an image, is an important characteristic for the automated or semi-automated interpretation of digital images. Many previous analyses have shown how to discriminate texture images, which include gray level co-occurrence matrix (GLCM), Laws' texture energy (LAWS) and Gabor multi-channel filtering (GABOR) etc. We have devised a...
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.