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.
Facial attractiveness computation is a challenging task because of the lack of labeled data and discriminative features. In this paper, an end-to-end label distribution learning (LDL) framework with deep convolutional neural network (CNN) and geometric features is proposed to meet these two challenges. Different from the previous work, we recast this task as an LDL problem. Compared with the single...
Saliency computational model with active environment perception can substantially facilitate a wide range of applications. Conventional saliency computational models primarily rely on hand-crafted low level image features, such as color or contrast. However, they may face great challenges in low lighting scenario, due to the lack of well-defined feature to represent saliency information in low contrast...
To accurately reproduce colors, it is necessary to calibrate a digital camera that is used to acquire images. The traditional calibration methods have been used to build a color correction model that has a transformation matrix mapping data from a RGB image to standard XYZ tristimulus. Determination of this matrix is performed through matrix transformation from each color checker patch to its corresponding...
Mura defect is a kind of common defects in thin-film-transistor liquid-crystal display (TFT-LCD). This paper proposes an effective detection method for mura defects based on background reconstruction and multi-channels fusion detection. Independent component analysis (ICA) is used to get a group of basis images from a set of faultless images for background reconstruction which will reserve the background...
Saliency detection is an important task to detect humans' visual attention region, plenty of methods are proposed to solve it. Most of them use single level pixels or patches to reveal the structure of the given image. However, the complexity of background regions and the unevenness of foreground objects still challenge these methods. To distinguish the saliency object from the complex background...
Ratio enhancement (RE) methods are typical fusion techniques that have been widely used in multispectral image pansharpening. The construction of a low-resolution Pan image is a crucial step of RE methods. However, it is observed that the existing RE methods cause serious color distortion in HS image pansharpening. This problem arises from the ideal assumptions of Pan and HS images: (i) the relation...
This paper proposes a novel patch-based object tracking algorithm combining Harris-SIFT and color histogram features to handle the partial occlusion problem. The object is represented as a number of non-overlapping patches. Harris-SIFT feature is defined as Harris corner and its SIFT feature vector, which can represent steady parts of the object when it is partially transformed or occluded. The Harris-SIFT...
In complex urban traffic conditions, the accurate detection of vehicles is challenging to current vehicle detection methods. To achieve the precise vehicle detection in complex urban traffic conditions, we have proposed a vehicle detection method based on a deformable hybrid image template in this paper. Our method contains two steps: constructing our hybrid image template and its probability model,...
In complex urban traffic conditions, occlusion between vehicles is a common problem which is challenging to current vehicle detection methods. In this paper, we have proposed a vehicle detection method based on a part-based model which can deal with the occlusion problem. Our method includes two steps: constructing the part-based model and detecting vehicles from traffic images. In the first step,...
With rapid development of intelligent transportation systems (ITS), video-based road monitoring systems become increasingly popular. Most video processing systems concerns the detection and monitoring of all road vehicles. Few research refers to non-social vehicle detection specially, although it is critical for urban traffic management. In this paper, we present a video-based taxi detection system...
Vision system which can be used for real-time tracking and measuring of moving target is very important in robot soccer match. Based on DSP embedded vision subsystem, this paper proposes a method to measure the binocular distance based on binocular parallax between two images' color. First, camera's intrinsic parameters can be determined by calculating the R component of the pixels' color of the image...
Image interpolation is an important basic digital image processing technology. In order to make image identify more easily, this paper did further research and improvement of the interpolation algorithm based on edge detection and interpolation algorithm based on threshold control.
Explained based on the pseudo-inverse method spectral reflectance restructuring principle, and has confirmed the entire restructuring process using the experiment and Matlab, and used the root-mean- square error, the color difference has carried on the appraisal for the spectrum restructuring aceuracy and the color chromaticity match aceuracy. The experiment proved that the pseudo inverse law restructuring...
Vehicle License Plate Recognition (VLPR) system is a core module in Intelligent Transportation Systems (ITS). In this paper, a VLPR system is proposed. Considering that license plate localization is the most important and difficult part in VLPR system, we present an effective license plate localization method based on analysis of Maximally Stable Extremal Region (MSER) features. Firstly, MSER detector...
With the extending of power grid and the increasing of data amount, traditional data presentation means of scheduling system can't afford to display large and complex information visually and effectively. In order to monitor the grid timely and accurately, more advanced and intuitive tools are imperative to electric power dispatchers. In this article, OpenGL visualization technology will be used in...
In this paper, an efficient image enhancement method based on Retinex and lightness decomposition is proposed, which enhances details and preserves the naturalness simultaneously. The quality of an enhanced image is determined by two factors, details and naturalness. Accordingly, the lightness is proposed to be decomposed into reflex lightness and ambience illumination. The reflex lightness is utilized...
The tracking algorithm of Camshift is only used in simple background with certain color. In this paper, an improved Camshift algorithm is proposed. Firstly the precision localization of the target is realized by wavelet which has the characteristics of multi-resolution analysis and time-frequency local window analysis, then the coordinate of center-of-mass is calculated based on the detected initial...
In this paper a crack image acquisition and processing technology is proposed based on modern digital photography technologies. In order to realize the crack segment from its background without manual interference, a binarization threshold is automatically defined according to the probability distribution between the crack and background. This operation can capture the mostly possible crack pixels...
The ISODATA clustering algorithm is regarded as a common method in the field of analyzing remote sensing images. It is very effective to generate a preliminary overview of images. These kinds of clustering methods are currently done in personal computers. However, with the development of remote sensing technology, the spatial resolutions are increasing rapidly and the sizes of the data are becoming...
The process of manual identification of thin-sections under the polarizing microscope is complex and repetitive. Geographic Information System (GIS) is a system of collecting, storing, managing, computing, analyzing, displaying and describing geospatial information. This paper proposes a way of recognizing and classifying components in clastic rock thin-sections image automatically using the spatial...
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.