The Experts below are selected from a list of 40845 Experts worldwide ranked by ideXlab platform
Weili Zeng - One of the best experts on this subject based on the ideXlab platform.
-
a new face recognition method based on Image decomposition for single sample per person problem
Neurocomputing, 2015Co-Authors: Weili ZengAbstract:The Image decomposition based method is one of the efficient and important face recognition solutions for the single sample per person problem. The low Image decomposition performance and the unconvincing reconstruction of the Approximation Image are the two main limitations of the previous methods. In this paper, a new single sample face recognition method based on lower-upper (LU) decomposition algorithm is proposed. The procedure of the proposed method is as following. First, the single sample and its transpose are decomposed to two sets of basis Images by using the LU decomposition algorithm, which is more efficient than the Image decomposition algorithms of the previous works. Two Approximation Images are reconstructed from the two basis Image sets by the reverse thinking approach based on experimental analysis. Then, the fisher linear discriminant analysis (FLDA) algorithm is used to evaluate the optimal projection space by using the new training set consisting of the single sample and its two Approximation Images for each person. Finally, the nearest neighbor classifier based on Euclidean distance is adopted as the final classification. We make two main contributions: one is that we propose to decompose the single sample and its transpose using the efficient LU decomposition algorithm, and reorder each basis Image set according to the basis Image energy; the other is that we present a reverse thinking approach based on experimental analysis to reconstruct the Approximation Image. The performance of the proposed method is verified using four public face databases, namely FERET, AR, ORL and Yale B. The experimental results indicate that the proposed method is efficient and outperforms several state-of-the-art approaches which are proposed to address the single sample per person problem.
-
An adaptive Approximation Image reconstruction method for single sample problem in face recognition using FLDA
Multimedia Tools and Applications, 2014Co-Authors: Weili ZengAbstract:Fisher linear discriminant analysis (FLDA) algorithm is a popular subspace method for face recognition, which requires that the number of training samples for each object is not less than two. In this paper, an adaptive Approximation Image reconstruction method based on economy singular value decomposition (ESVD) algorithm is proposed for the single sample problem in face recognition. By using ESVD the single training sample is decomposed to a set of basis Images. Then an adaptive Approximation Image reconstruction method is proposed to reconstruct an Approximation Image by using several significant basis Images. The single training Image and its Approximation Image for each object form a new training set, which can make the FLDA be applied to the single sample problem in face recognition. The major contribution of the proposed work is that the number of significant basis Images for the reconstruction of an Approximation Image is evaluated by using a reverse thinking approach based on experimental analysis. The performance of the proposed method is verified on the Yale, FERET, ORL, UMIST and AR face databases. The experimental results indicate that the proposed method is efficient and outperforms some existing methods which are proposed to overcome the single sample problem.
Zhimin Yan - One of the best experts on this subject based on the ideXlab platform.
-
Privacy-Oriented Successive Approximation Image Position Follower Processing
'Hindawi Limited', 2021Co-Authors: Ying Miao, Danyang Shao, Zhimin YanAbstract:In this paper, we analyze the location-following processing of the Image by successive Approximation with the need for directed privacy. To solve the detection problem of moving the human body in the dynamic background, the motion target detection module integrates the two ideas of feature information detection and human body model segmentation detection and combines the deep learning framework to complete the detection of the human body by detecting the feature points of key parts of the human body. The detection of human key points depends on the human pose estimation algorithm, so the research in this paper is based on the bottom-up model in the multiperson pose estimation method; firstly, all the human key points in the Image are detected by feature extraction through the convolutional neural network, and then the accurate labelling of human key points is achieved by using the heat map and offset fusion optimization method in the feature point confidence map prediction, and finally, the human body detection results are obtained. In the study of the correlation algorithm, this paper combines the HOG feature extraction of the KCF algorithm and the scale filter of the DSST algorithm to form a fusion correlation filter based on the principle study of the MOSSE correlation filter. The algorithm solves the problems of lack of scale estimation of KCF algorithm and low real-time rate of DSST algorithm and improves the tracking accuracy while ensuring the real-time performance of the algorithm
Shuang Wang - One of the best experts on this subject based on the ideXlab platform.
-
a new palmprint identification algorithm based on gabor filter and moment invariant
IEEE Conference on Cybernetics and Intelligent Systems, 2008Co-Authors: Shuang WangAbstract:This paper presents an effective algorithm of palmprint feature extraction. This algorithm is constructed on the basis of Gabor filter and moment invariant (MI). The process of implementing the algorithm is as follows: first, we perform wavelet transform of the original region of interest (ROI) of the palmprint Image to get the Approximation Image (AIROI). Later, we exploit the Gabor filter to capture the texture information of the AIROI, and then compute each pixelpsilas magnitude of the transformed Image to produce a Gabor Magnitude Picture (GMP). We compute the MIs of the GMP and use the MIs as features of palmprint identification. Our experiment on an open database downloaded from PolyU Biometrics Research Center obtains very high right recognition rate.
Zhao-ning Zhang - One of the best experts on this subject based on the ideXlab platform.
-
A novel zero-watermark algorithm based on LU decomposition in NSST domain
2012 IEEE 11th International Conference on Signal Processing, 2012Co-Authors: Shao-cheng Han, Zhao-ning ZhangAbstract:A novel zero-watermark algorithm is proposed based on LU decomposition and Non-Subsampled Shearlet Transform(NSST) for copyright protection of digital Images. In this method, firstly the host Image is performed with NSST, and a sub-Image is extracted from the low-frequency Approximation Image randomly by Logistic chaotic system, then the sub-Image is divided into non-overlapping sub-blocks. Next, each sub-block is performed with LU decomposition, the zero-watermark is derived by judging the numerical relationship between the sum from the first row elements of each sub-block's U matrix and the mean of the sums from the first row elements of all sub-block's U matrix. Experimental results show that the method is robust to adding noise, filtering and JPEG compression, and can resist the Cropping and RST attack to some extent.
John A. Silander - One of the best experts on this subject based on the ideXlab platform.
-
A wavelet transform method to merge Landsat TM and SPOT panchromatic data
International Journal of Remote Sensing, 1998Co-Authors: Jiazheng Zhou, Daniel L. Civco, John A. SilanderAbstract:Abstract To take advantage of the high spectral resolution of Landsat TM Images and the high spatial resolution of SPOT panchromatic Images (SPOT PAN), we present a wavelet transform method to merge the two data types. In a pyramidal fashion, each TM reflective band or SPOT PAN Image was decomposed into an orthogonal wavelet representation at a given coarser resolution, which consisted of a low frequency Approximation Image and a set of high frequency, spatially-oriented detail Images. Band-by-band, the merged Images were derived by performing an inverse wavelet transform using the Approximation Image from each TM band and detail Images from SPOT PAN. The spectral and spatial features of the merged results of the wavelet methods were compared quantitatively with those of intensity-hue-saturation (IHS), principal component analysis (PCA), and the Brovey transform. It was found that multisensor data merging is a trade-off between the spectral information from a low spatial-high spectral resolution sensor an...