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.
In view of problem that it usually lacks of fusion depth to combine moment invariants with other extraction technology on local invariant features, this article proposes the moment invariants based on SUSAN initial edge response, which provides a sort of organic integration for moment invariants and SUSAN edge detection algorithm. The combination point is to treat SUSAN initial edge response matrix...
For which low frequency discrete cosine transform (DCT) coefficients retransforming based on contrast limiting adaptive histogram equalization (CLAHE) is proposed. Firstly, original images are divided into several non-overlapping blocks and CLAHE is used to do local contrast stretching so as to reduce noise. Then, illustration variation of face image is removed by reducing suit numbers of low frequency...
Image saliency detection, which is aiming at locating meaningful objects in image and extracting the corresponding saliency map, has been attracting considerable attention. Most of existing saliency detection algorithms are dealing with uncompressed images, while numerous images are distributed and stored in JPEG format over Internet. Thus, this paper proposes a novel image saliency detection method...
Recognizing human actions in video has gradually attracted much attention in computer vision community, however, it also faces many realistic challenges caused by background clutter, viewpoint changes, variation of actors appearance. These challenges reflect the difficulty of obtaining a clean and discriminative video representation for classification. Recently, VLAD (Vector of Locally Aggregated...
Serial number is an important component to paper money. It is an important identifier to every piece of paper money. This paper presents an effective method on segmentation and recognition of RMB serial number. This methodology can be classified as three stages: preprocessing stage, Serial number segmentation stage and serial number recognition stage. The original serial number image is greylized...
A case-based pattern design method is proposed to translate an image into a pattern of certain style. The method has two phases. Pattern style and knowledge are learned in case-learning phase, case mapping database and rule database are results of this phase and will serve as memory unit and logical unit respectively. In design phase, user designates the objects in an input image, visual features...
Lip-reading technology was introduced in this paper, including the development course, technical methods and application direction. Lip-reading technology mainly includes the lip detection and localization, feature extraction and recognition method and fusion method, the classification of the mouth and the corpus. This paper do a detailed comparative analysis for traditional methods and new technology,...
The crucial problem of multisensor remote sensing image registration is how to establish the reliable correspondences between the features extracted from two images. The feature similarity based methods fail when similar local regions exist, and the spatial relationship methods fail to match small portion of pair wise correspondences out of the total number of features. In this paper, we proposed...
Gabor filters are used to extract holistic feature in facial expression recognition. However, local subtle features can't be extracted effectively and it results in large amounts of data redundancy. In this paper, we proposed a novel facial expression recognition method based on the selection of local Gabor features and the extended nearest neighbor algorithm. The Gabor filter and radial encode is...
Text feature acquiring is the key to construct the classifier to classify the text, According to the problem that the text dimension of the original feature vector is reduced and accurate, put forward a text feature acquiring algorithm based on co evolution, the algorithm uses genetic algorithm optimization performance and co evolution can implement multiple population mutual evaluation and competition,...
The web reviews contain a lot of features of the evaluation object and express the viewpoints or attitudes of the reviewers. Therefore, analyzing them and identifying the sentiment polarity will be significantly important and valuable. This paper uses the appearing-frequency of noun words to extract the aspect words and uses some semantic rules to extract opinion words to form the aspect -- opinion...
This paper presents an improved vision-based algorithm for detecting and recognizing vehicle logos in images captured by road surveillance cameras. Vehicle logo recognition is quite a challenging task considering the low resolution of the logos, the wide range of variability in illumination and the interference of the air-intake grille. However, our system, assessed on a set of 1386 vehicle images...
With the rapid development of highway, the distribution of surveillance cameras has become increasingly intensive, which brings important significance to traffic safety by detecting visibility of fog using surveillance video. In this paper, a fog level detection method based on grayscale features is proposed. Sometimes there is no proper calibration template in highway. In order to meet the requirement...
In order to improve the recognition rate of palm vein recognition algorithm, a recognition algorithm based on SIFT and ORB features extraction and score-level fusion is presented in this paper. Score-level fusion is an information fusion technique, which has six common combination rules. Two dynamic weight combination rules are proposed as a supplement here. The main steps of the proposed algorithm...
Criminal investigation image database retrieval is one of the key tasks in Forensic Science. Tire pattern is an important type of image data for crime scene investigation. It has been found that the rotation of tire pattern image has a great influence on retrieval precision. To relieve this problem, this paper proposes a new texture feature extraction method based on Radon transform, for more efficient...
In order to extract the content information of Theme Web Pages more accurately, this paper proposes a self-learning method based on the tag information by calculating the information quantity of various tag indicators. This method predefines several tag information indexes and coefficients index to calculate a variety of tag information quantity of the web pages in turn, and then the candidate content...
We propose a compressive sensing based method to recognize face with pose variations. The face recognition framework includes two issues: feature extraction and classification. For feature extraction, we present a random measurement matrix to compress an image from high dimensional space to a low dimensional space. The compressive feature has a powerful discrimination because it can preserve most...
SIFT features have been found to be effective in describing image textures. Because SIFT features have some great characteristics, such as translation invariance, zooming in and out invariance, spin invariance and affine invariance, etc, so the image retrieval precision is satisfactory usually. However, in Content Based Image Retrieval (CBIR), there are so many SIFT feature points extracted from an...
HDR (high dynamic range) imaging is to obtain HDR image by fusing a few LDR (Low dynamic range) images with different dynamic range together. Due to the difference in the dynamic ranges between acquired image and actual scene, overexposure and underexposure may appear in HDR images obtained. Thus, the detail information of images may get lost in the result image This paper proposes a method to relieve...
Semantic relation extraction is an important part of information extraction, it has application value in the automatic question answering system, retrieval system, ontology learning, semantic web annotation, and many other areas. Pattern representation method is context pattern in previous semi-Supervised semantic relation extraction based on bootstrapping, but it did not consider the role of the...
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.