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.
The algorithm of extracting pedestrian features based on Local Binary Pattern (LBP) has the problems of being unable to depict the human visual sensitivity. We proposed an Significant Local Binary Pattern (SLBP) which fused the characteristics of human visual pedestrian system. We extracted the significant factor based on Weber's law, and added the significant factor as a weight to the LBP eigenvalue...
In order to enhance the classification accuracy of the two-dimensional feature of the image, the idea of a separate classification for each projection direction feature is proposed in this paper. Our method first divides the image into blocks and finds the two-dimensional sub-projection matrix of each sub-block, and then completes the feature extraction by using each column of the projection matrix...
In order to overcome the impact of complex illumination environment and head movement, a novel eye state recognition algorithm is proposed in this paper, which is based on feature level fusion. Firstly, Pseudo Zernike feature was found can be used to overcome the impact of head movement and Gabor feature can be used to overcome the impact of illumination changing. Then we got the fusion feature by...
In order to handle occlusion and illumination change in video object tracking, an algorithm named compressive object tracking based on weighted multiple instance learning (COTWMIL) is proposed. Each sample is descripted in a multi-scale fashion with rectangle filterbank, and then the dimension of extracted feature is reduced by compressive sampling. Specifically, object region is first labeled manually...
Vehicle classification in monitor systems has become one of the hot research areas as a branch of intelligent monitor systems research. The texture features extraction is the first step of model classification. We took the actual situation information into account with of vehicle classification and improved the traditional LBP algorithm in dealing with the color image. Improved LBP algorithm has the...
Person re-identification in camera network, with non-overlapping fields of view based on descriptive features is an important task in surveillance systems. In general, the person re-identification aims to recognize an individual through different pictures by measuring the similarity between two individuals.
Weather-dependent road conditions are a major factor in many automobile incidents; computer vision algorithms for automatic classification of road conditions can thus be of great benefit. This paper presents a system for classification of road conditions using still-frames taken from an uncalibrated dashboard camera. The problem is challenging due to variability in camera placement, road layout, weather...
This paper presented a SIFT based multiple instance learning algorithm to deal with the problem of pose variation in the tracking process. The MIL algorithm learns weak classifiers by using instances in the positive and negative bags. Then, a strong classifier is generated by powerful weak classifiers which are selected by maximizing the inner product between the classifier and the maximum likelihood...
Due to the lack of classification accuracy in pattern recognition, in this paper we propose a new algorithm for pattern analysis based on the symbolic pattern method. Proposed algorithm is constructed by using symbolic method and finite state automata model and used for classifying the textures based on the patterns. This algorithm performs symbolization of the data and portioning the texture images...
To enhance the robustness of the vehicle detection system, an effective algorithm to identify the lighting conditions (daylight, night, lowlight (dawn, dusk)) based on histogram analysis is presented in this paper. The algorithm consists of two procedures: extracting and updating background image, and generating a lighting conditions classifier based on background image analysis. The algorithm is...
In this paper, artificial neural network (ANN) and improved binary gravitational search algorithm (IBGSA) are utilized to detect objects in images. Watershed algorithm is used to segment images and extract the objects. Color, texture and geometric features are extracted from each object. IBGSA is used as a feature selection method to find the best subset of features for classifying the desired objects...
A novel hand gesture detection method in complex background is presented in this paper, it proposed a multi class cascade structure classification based on Gentle AdaBoost (GAB) and Weighted Linear Discriminant Analysis (wLDA). The training and testing experiments are based on the sample database established myself. Histogram of Oriented Gradient (HoG) features of one pair of blocks are extracted...
The automatic human face detection from sequences of video plays vital role in intelligent human computer interaction systems for video surveillance, face recognition, emotion recognition and face database management. This paper proposes an automatic and robust method to detect human faces from the background that is capable of processing images rapidly while achieving high detection rates from video...
This paper proposes a new flame region detection method using color and dynamic characteristic of flame in video sequences. Flame has very distinct color characteristics, and nine discriminate rules are proposed in RGB color space for flame detection, and these rules are combined to detect the candidate flame regions. To validate a real burning flame region, this paper uses ViBe algorithm to detect...
Image registration is an important technology of image processing and has a broad application. Good adaptability, computing speed and registration accuracy are the basic requirements in image registration. In recent years, the image registration algorithm based on local invariant features is becoming a hot spot of research, such as the SIFT method is one of them. But the traditional SIFT algorithm...
This paper presents a new algorithm to better classify objects in videos. In our case, the objects are cars, vans, and people on the roads. First, in order to extract the moving objects more precisely, we have proposed a method for foreground extraction based on the contour differences between the video frame and the background image. Second, after we got the integrated moving object, we have proposed...
Principle Component Analysis (PCA) technique is of vital importance and is an efficient method in extracting features in face recognition. Generally speaking, the image always needs to be transformed into ID vector in PCA. This paper mainly researches the method of face recognition based on PCA and K-Nearest Neighbor. A comparison of Nearest Neighbor and K-Nearest Neighbor are given in the last section.
Eye-tracking technology has been studied in the field of Human-Computer Interaction as well as industrial applications such as advertisement, medical diagnostics and surgery. However, because the eye tracking is mainly affected by environmental changes like illumination, scale and image rotation, we do not only use Haar classifier to detect face region and eye area, but also take advantage of the...
This paper introduces the new color face recognition (FR) method that makes effective use of boosting learning as color-component feature selection framework. The proposed boosting color-component feature selection framework is designed for finding the best set of color-component features from various color spaces (or models), aiming to achieve the best FR performance for a given FR task. In addition,...
Face detection is required prior to various face-related applications. The objective of face detection is to determine whether or not there are any faces in an image and, if any, the location of each face is shown. Face detection in a natural scene image is challenging due to large variability of face appearances. This paper proposes a face detection algorithm using the 3×3 block rank patterns of...
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.