به نام خدا
Title: Application of the Mean Field Methods to MRF Optimization in Computer Vision
Authors: Masaki Saito Takayuki Okatani Koichiro Deguchi
Abstract: The mean field (MF) methods are an energy optimization method for Markov random fields (MRFs). These methods, which have their root in solid state physics, estimate the marginal density of each site of an MRF graph by iterative computation, similarly to loopy belief propagation (LBP).It appears that, being shadowed by LBP, the MF methods have not been seriously considered in the computer vision community. This study investigates whether these methods are useful for practical problems, particularly MPM (Maxi-mum Posterior Marginal) inference, in computer vision. To be specific, we apply the naive MF equations and the TAP (Thou less-Anderson-Palmer) equations to interactive segmentation and stereo matching. In this paper, firstly, we show implementation of these methods for computer vision problems. Next, we discuss advantages of the MF methods to LBP. Finally, we present experimental results that the MFmethods are well comparable to LBP in terms of accuracy and global convergence; furthermore, the 3rd-order TAP equation often outperforms LBP in terms of accuracy.
Publish Year: 2012
Published in: CVPR - IEEE
موضوع: بینایی ماشین (Computer Vision)
ایران سای – مرجع علمی فنی مهندسی
حامی دانش بومی ایرانیان
به نام خدا
Title: Vertical-Edge-Based Car-License-Plate Detection Method
Authors: Abbas M AlGhaili, Syamsiah Mashohor, Abdul Rahman Ramli, and Alyani Ismail
Abstract: This paper proposes a fast method for car-license-plate detection (CLPD) and presents three main contributions.The first contribution is that we propose a fast vertical edgedetection algorithm (VEDA) based on the contrast between thegrayscale values, which enhances the speed of the CLPD method.After binarizing the input image using adaptive thresholding (AT),an unwanted-line elimination algorithm (ULEA) is proposed toenhance the image, and then, the VEDA is applied. The sec-ond contribution is that our proposed CLPD method processesvery-low-resolution images taken by a web camera. After thev ertical edges have been detected by the VEDA, the desired plate details based on color information are highlighted. Then, thecandidate region based on statistical and logical operations will beextracted. Finally, an LP is detected. The third contribution is thatwe compare the VEDA to the Sobel operator in terms of accuracy,algorithm complexity, and processing time. The results show accu-rate edge detection performance and faster processing than Sobelby five to nine times. In terms of complexity, a big-O-notationmodule is used and the following result is obtained: The VEDAhas less complexity byK2 times, whereasK2 represents the masksize of Sobel. Results show that the computation time of the CLPDmethod is 47.7 ms, which meets the real-time requirements.
Publish Year: 2013
Publisher: IEEE TRANS-VEHICULAR TECHNOLOGY
موضوع: پردازش تصویر
ایران سای – مرجع علمی فنی مهندسی
حامی دانش بومی ایرانیان