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 work solves the problem of human head detection on the images based on the structural approach. Development of the graphs comparison algorithm by their embedding in the vector subspace is considered. Special points are obtained on the images. These points are clusterized to select characteristic regions of the human's face. Centers of clusters mass are further used as graph points. The graph is...
In this paper we propose a new method for scene representation and recognition based on the concept of Region Subspaces. Each image is pre-segmented into semantically meaningful regions and local features are extracted at different scales from each such region. The Region Subspaces are the low-dimensional linear subspaces calculated from the set of local features inside each region. We also define...
Level set methods have been extensively used in contour recognition and image segmentation. The traditional level set methods require to initialize the level set function regularly and are strongly dependent on initial contour position thus there are many problems about the methods. Considering those problems, this article proposed a new level set method to draw geometric active contour self-adaptively...
Human beings transmit a lot of apparent information visually rather than vocally. This consistent expression recognition by machine remains a challenge as of today. To automate recognition of emotional state, machines must be taught to realize facial gestures. The wheelchair is one of the kinds of assistive tools for physically challenged people and elderly people to gain mobility and lead to self-governing...
In order to detect traffic sign effectively and quickly, firstly, this paper firstly discriminates the maximum and minimum values of the color-components R, G and B, and then ignores pixels having little color similarity with traffic sign. Secondly, it regards the points of RGB space as color eigenvector and calculates the cosine value of included angle of vectors to discriminate color similarity...
Red-eye artifact is induced by the light reflected off retinal capillaries when photos are taken under weak light using flash. An automatic method is proposed to remove red-eye artifacts in digital images in this paper. First, a face detector based on histograms of oriented gradients (HOG) features and Real Adaboost algorithm is employed to select faces, and eye-boxes which contain one eye in each...
Image recognition of a user plays an important role in designing intelligent and interactive behaviors for a domestic or service robot. In this paper, an image-based age-group classification method is proposed to estimate three levels of age groups, namely child, adult and the elderly. After face detection from the acquired image frame, human facial area is extracted and 52 feature points are located...
The correct segmentation of textural pattern into different meaningful regions is one of the most important problems in automatic texture image recognition. In this paper, we presented a variational integration of shape prior statistics into a phase-field based segmentation process. By derivating the new phase field functionals with gradient shape policy, we obtain the interface evolution process...
Polymorphism individual identifying of DNA was the image pattern-recognition of the oligonucleotide chip scan photo. The authors of this paper propose their own functions which aim at the issue of bit dot computer recognition of oligonucleotide chip scan photo: implemented chip-scan photo binarization after the determination of threshold-value by using OSTU. Sub-image segmentation and separately processing...
This paper introduces an unsupervised color segmentation method. The underlying idea is to segment the input image several times, each time focussing on a different salient part of the image and to subsequently merge all obtained results into one composite segmentation. We identify salient parts of the image by applying affinity propagation clustering to efficiently calculated local color and texture...
The manipulator based on vision is used widely in many situations. However, there are many questions in the real-time control of manipulator based on vision, for example, the image processing is not exact, the image recognition is not fast and the process of the manipulator movement is not smoothly. All of these problems badly influence on the application of robots. In view of these drawbacks, this...
For the natural scene recognition and moving object segmentation, the segmentation of tree crown could improve the recognition rate and segmentation accuracy of moving objects when they are in strong wind and no buildings. Up to now, many researches mainly focus on the background modeling and texture synthesizing. In this paper, feature modeling of tree crown is discussed and modified by using the...
Neural networks are relatively successful in recognizing individual patterns. However, when images consist of combination of patterns, a preprocessing step of segmentation is required to avoid combinatorial explosion of the training phase. In practical applications, segmentation is a context dependent task which itself requires recognition. In this paper we propose and develop a biologically inspired...
Empirical mode decomposition (EMD) developed by Huang et al. is a nonlinear data analysis method for nonstationary real-valued time series. It has been applied extensively in many research areas. Recently, several generalized EMD methods for complex-valued data analysis was proposed. Since a plane closed curve comprises many two-dimensional (2D) space data points, one can imagine that the boundary...
Many applications of geometry processing and computer vision rely on geometric properties of curves, particularly on their curvature. So the estimation of digital curvepsilas curvature is important. An algorithm of curvature estimation is proposed in this paper, which is based on the recognition of discrete straight segments. For each point of a digital curve, its curvature is estimated by searching...
The paper introduces an approach for threshold potential optimization in the Pulse Coupled Neural Network (PCNN) to solve the quality of generated features for image recognition tasks. Threshold potential plays very important role because it provides and controls pulse effect of PCNN. The suitable control of pulse effect can improve dimension reduction of image classification space by PCNN that is...
Modeling of human motion through a discrete sequence of motion primitives, retaining elements of skillful or unique motion of an individual is addressed. Using wireless inertial motion sensors, a skeletal model of the fluid human gait was gathered. The posture of the human model is described by sets of Euler angles for each sample. An intrinsic classification algorithm known as minimum message length...
Aiming for some limit of the recognition-free approach to the segment merged numerals, a new segmentation method is proposed based on GVF mode in this paper. Firstly, this paper presents a new segment model based on wavelet multi-scale analysis and GVF model, and then we apply this energy model to segment the merged numerals. This method got the candidate segment line by contour method, and then confirmed...
This paper proposes a gait recognition method based on Hilbert-Huang descriptors (HHDs) and K-nearest neighbors method. For each image sequence, background subtraction algorithm is firstly used to segment the silhouettes of moving object from the background. When analyzing the body contours by HHDs, we obtain the gait features. K-nearest neighbors method is finally applied to analysis and recognition...
This paper proposes a new approach to detect the fall of the elderly. The detection system is composed of a PC server and distributed cameras. The distributed cameras are used to capture images of different place in a house, and the PC server is used for fall recognition. In the fall recognition process, we extracted a new feature using for distinguishing lying down normally and behavior of falling...
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.