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.
Object detection is an important part of computer vision research, which directly affects the follow-on object identification and tracking, analysis and understanding of the scene. In this paper, based on scale space theory and the SIFT feature matching algorithm, we propose a method to create a SIFT vector field. Through four different application scenarios we demonstrate the value of building a...
In this paper, we present a robust and fast object tracking algorithm based on sub-region classifiers and compressive tracking. Compared with the original CT algorithm, the tracker can improve the robustness to occlusion, especially long-term occlusion. Firstly, the target region is divided into four sub-regions in a fixed mode. Then a simple but feasible classification and update strategy is used...
In this paper, we propose to use acoustic feature based submodular function optimization to select a subset of untranscribed data for manual transcription, and retrain the initial acoustic model with the additional transcribed data. The acoustic features are obtained from an unsupervised Gaussian mixture model. We also integrate the acoustic features with the phonetic features, which are obtained...
Over the last few decades, multiple-instance learning (MIL) has been successfully utilized to solve the content-based image/video retrieval (CBIR/CBVR) problem, in which a bag corresponds to a video scene and an instance corresponds to a frame caption. However, existing feature representation schemes are not effective enough to use MIL to detect video caption frames from news video, which hinders...
Over the last few decades, Content-based image/video retrieval (CBIR/CBVR) problem have developed a new height. As one of the most impartment methods of CBVR, video caption extraction obtained more and more application. A large number of techniques have been proposed to address this problem, we summarized most of the video caption extraction methods, analyzed the advantage and disadvantage of the...
To improve the performance of multi-pose face detection, the AdaboostSVM algorithm based on multi-feature fusion is proposed in this paper. Firstly, the Haar-like features and the triangular integral features are introduced and the edge-orientation field features based on morphological gradient are presented. Then, the AdaboostSVM Algorithm based on the above three kinds of features is proposed. The...
The purpose of this paper is to research the image semantic auto-annotation method, which proposes an image semantic annotation method adopted ontology description and the image regional objects reasoning. First, the image semantic regional description model was build, and then the similar features of the region to achieve the similar semantics were annotated. Second, the algorithm focuses on the...
The proposed null Foley-Sammon transform (NFST) method based on the Gram-Schmidt orthogonalization successfully overcomes the so-called small sample size problem with high performance in terms of recognition accuracy and low computation cost, however, the NFST method is still a linear technique in nature, so a new nonlinear feature extraction method called kernel null Foley-Sammon transform (KNFST)...
The image semantic classification is new focus in the image classification field, the traditional classification algorithm is based on the low level visual features, but there is an enormous semantic gap problem between the low-level visual features and high-level semantic information of images. An image semantic classification approach is proposed based on Kernel PCA Support Vector Machines (KPCA...
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.