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.
Moving vehicle segmentation in traffic videos is a challenging work because of complex background and variety objects. In this paper, we focus on detecting vehicles that are running through crossroads using the up-to-date spatiotemporal saliency model. The current saliency detection methods aim at detecting the most salient objects, novel but stationary target will be easily classified as foreground,...
This paper proposed a moving vehicles segmentation approach combined two kinds of classifiers which are Gaussian mixture model and spatiotemporal saliency map. We extracted new spatial and temporal saliency features and improved spatiotemporal consistency optimization model to calculate more exact saliency map and to speed up the processing. Because misclassification appears when Gaussian background...
Accurate prostate localization is the key to the success of radiotherapy. It remains a difficult problem for CT images due to the low image contrast, the prostate motion, and the uncertain presence of rectum gas. In this paper, a learning based framework is proposed to improve the accuracy of prostate detection in CT. It adaptively determines distinctive feature types at distinctive image regions,...
In this paper two novel methods are proposed for recognizing B-mode ultrasound (US) imaging of common carotid artery (CCA) in longitude. In the single frame method, the US is segmented by k-means fuzzy clustering algorithm. Then a series points are extracted based on geometric features. Thirdly, the feature points are selected according to our new cluster method. Then curve fitting is applied by feature...
Handwriting identification is one of the most important branches of computer vision and pattern recognition, and an effective means of identification that is important for surveillance and security, telecommunications, digital libraries, video meeting, and human-computer intelligent interactions. A deep research on pre-processing of Chinese handwriting identification is conducted in this paper. Computer...
In this paper, a new image fusion algorithm based on wavelet packet analysis (WPA) and pulse-coupled neural networks (PCNN) is presented. Firstly a multi-scale decomposition of each source image is performed by wavelet packet transform (WPT), and then the PCNN is used to make an intelligent fusion decision to obtain the fusion coefficients in all wavelet packet fields. Finally an inverse WPT based...
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.