Xueyi Ye

Learn More
Iris recognition using complex valued 2D Gabor filters received a great success in broad applications. Such method encoded the iris phase information which was extracted according to the complex valued 2D filters' response. In this paper, we theoretically analyzed the complex-valued 2D Gabor filters. Based on analysis, we concluded that the real part of(More)
Previous algorithms have good localization performance for iris images captured in the ideal condition. However, in practice, the quality of iris image is greatly influenced by luminance, eyelashes, hair or glasses frame, which is easy to cause mis- localization. In order to improve the robustness of iris localization, this paper proposes a new localization(More)
The contradiction between the capacity and the robustness of image watermark has not been solved in the digital watermark research. In this paper, a robust Discrete Wavelet Transform (DWT) - Singular Value Decomposition (SVD) watermark method based on multiple-level Discrete Cosine Transform (DCT) is proposed by the advantage of DCT's energy concentration.(More)
3D map building is an important task of autonomous land vehicle (ALV) for obstacle detection, path planning. Traditional methods using stereo vision usually relies on dense disparity map obtained by stereo matching, and 3D map is built based on the disparity map. Traditional methods are sensitive to mismatch pixels in disparity map, and dense stereo(More)
A processing algorithm was presented for face recognition under variation illumination. It needs only one parameter to set and can remove the "halo" efficiently. Firstly, it estimated the illumination from image using total variation model. Secondly, it recovered the image reflectance, which is invariant of illumination. Experiment results show that this(More)
Image resizing is one of the basic operations for image and video display, transmission, and analysis, etc. Traditional image resizing methods usually utilize an interpolation algorithm to zoom in or zoom out an image, e.g., the nearest neighborhood interpolation, the bilinear interpolation and the cubic interpolation are most widely used ones. The(More)
Face detection is an important first step towards solving plethora of other computer vision problems. A fast robust face detection algorithm under a skin color model with geometry constraints is proposed in this paper. An ellipse color model in the YCbCr color space is first used to detect the skin regions. A light compensation algorithm is utilized to the(More)
In an embedded system, the hardware resources are limited. In order to obtain such traffic information as traffic volume and vehicle speed in an embedded system, a series of efficient video processing algorithms and optimization techniques are proposed. The key algorithm to detect vehicles is the background subtraction method, in which the approximated(More)