Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
An Information Fusion and Recognition Method for Color Face Images

HUANG Xiaohua,WANG Chunmao,ZHENG Wenming,

中国图象图形学报 , 2010,
Abstract: In this paper, a face recognition method, which utilizes an information fusion for color images and supervised neighbor preserving embedding, is presented for improving the perform ance of face recognition. First, Gabor transformation is used to extract information per channel of color image respectively, and then canonical correlation analysis is utilized to fuse extracted Gabor features. Supervised neighbor preserving embedding is used to reduce dimensionality. Finally, nearest neighbor classifier is used to classify reduced features. Experiments are carried on XM2VTS and FRAV2D color face databases, and utilize principal component analysis, linear discriminant analysis and supervised neighbor preserving embedding to reduce dimensionality of Gabor features on gray method and multi-channel feature fusion method. These results show that the combination of multi-channel information fusion and supervised neighbor preserving embedding can improve the performance of recognition system.
Sparsity Preserving Canonical Correlation Analysis with Application in Feature Fusion

HOU Shu-Dong,SUN Quan-Sen,

自动化学报 , 2012,
Abstract: Sparsity preserving projections (SPP) aim to preserve the sparse reconstructive relationship among the data and have been successfully applied in face recognition. The projections are invariant to rotations, rescalings, and translations of the data, and more importantly, they contain natural discriminating information even without class labels. Enlightened by this, we propose a sparsity preserving canonical correlation analysis (SPCCA). It can not only fuse the discriminative information of two feature sets efficiently, but also constrains the sparse reconstructive relationship among each feature set in order to increase the representational power and has good discrimination capability of the feature extracted by SPCCA. Experimental results on the multiple feature databases and face databases show that the proposed SPCCA is better than CCA.
Research on Gesture Recognition Based on Improved GBMR Segmentation and Multiple Feature Fusion  [PDF]
Xianfei Zhu, Weizhong Yan, Dongzhi Chen, Cuicui Gao
Journal of Computer and Communications (JCC) , 2019, DOI: 10.4236/jcc.2019.77010
Aiming at addressing the problem of interactive gesture recognition between lunar robot and astronaut, a novel gesture detection and recognition algorithm is proposed. In gesture detection stage, based on saliency detection via Graph-Based Manifold Ranking (GBMR) algorithm, the depth information of foreground is added to the calculation of superpixel. By increasing the weight of connectivity domains in graph theory model, the foreground boundary is highlighted and the impact of background is weakened. In gesture recognition stage, Pyramid Histogram of Oriented Gradient (PHOG) feature and Gabor amplitude also phase feature of image samples are extracted. To highlight the Gabor amplitude feature, we propose a novel feature calculation by fusing feature in different directions at the same scale. Because of the strong classification capability and not-easy-to-fit advantage of Adaboosting, this paper applies it as the classifier to realize gesture recognition. Experimental results show that the improved gesture detection algorithm can maintain the robustness to influences of complex environment. Based on multi-feature fusion, the error rate of gesture recognition remains at about 4.2%, and the recognition rate is around 95.8%.
An Airplane Image Target's Multi-feature Fusion Recognition Method

LI Xin-De,YANG Wei-Dong,DEZERT Jean,
,杨伟东,DEZERT Jean

自动化学报 , 2012,
Abstract: This paper proposes an image target's multi-feature fusion recognition method based on probabilistic neural networks (PNN) and Dezert-Smarandache theory (DSmT). To aim at multiple features extracted from an image, the information from them is fused. Firstly, the image is preprocessed with binarization and then multiple features are extracted, such as Hu moments, normalized moment of inertia, affine invariant moments, discrete outline parameters and singular values. Secondly, due to the difficulty of the construction of the basic belief assignment in DSmT, in this paper the target recognition rate matrix is constructed by PNN, that is, the basic belief assignments can be assigned to the evidence sources by PNN. Finally, the procedure of airplane target recognition can be accomplished by the DSmT combination rule at the level of decision fusion. For small distortion of target image, the multi-feature fusion method proposed in this paper is compared with the single-feature one through a series of experiments. The experimental result in this paper proves that this method greatly improves the right recognition rate, satisfies real-time requirements, and has good ability of rejection of judgement and strong insensitivity to target image size. And even for big distortion, the right recognition rate can also reach 89.3%.
Affine Invariant Feature Extraction Algorithm Based on Generalized Canonical Correlation Analysis

Zhang Jie-yu Chen Qiang Bai Xiao-jing Sun Quan-sen Xia De-shen,

电子与信息学报 , 2009,
Abstract: A novel method of extracting affine invariant feature is proposed using the theory of Generalized Canonical Correlation Analysis(GCCA). First, a new kind of transformation named MSAE is constructed based on MSA. Second, MSAE is proved to be affine invariant. Then MSA is combined with MSAE using GCCA to obtain a new feature with more information. Finally, the coil-100 image database viewed from different angles in the case of Gaussian noise or occlusion is put into recognition experiments using minimum distance classifier. The comparing results among MSA, MSAE and combined feature indicate that the combined feature can obtain highest recognition accuracy followed by MSAE and MSA in turn.
Generalized Canonical Correlation Analysis for Disparate Data Fusion  [PDF]
Ming Sun,Carey E. Priebe,Minh Tang
Computer Science , 2012,
Abstract: Manifold matching works to identify embeddings of multiple disparate data spaces into the same low-dimensional space, where joint inference can be pursued. It is an enabling methodology for fusion and inference from multiple and massive disparate data sources. In this paper we focus on a method called Canonical Correlation Analysis (CCA) and its generalization Generalized Canonical Correlation Analysis (GCCA), which belong to the more general Reduced Rank Regression (RRR) framework. We present an efficiency investigation of CCA and GCCA under different training conditions for a particular text document classification task.
Enhanced Face Recognition using Data Fusion  [cached]
Alaa Eleyan
International Journal of Intelligent Systems and Applications , 2012,
Abstract: In this paper we scrutinize the influence of fusion on the face recognition performance. In pattern recognition task, benefiting from different uncorrelated observations and performing fusion at feature and/or decision levels improves the overall performance. In features fusion approach, we fuse (concatenate) the feature vectors obtained using different feature extractors for the same image. Classification is then performed using different similarity measures. In decisions fusion approach, the fusion is performed at decisions level, where decisions from different algorithms are fused using majority voting. The proposed method was tested using face images having different facial expressions and conditions obtained from ORL and FRAV2D databases. Simulations results show that the performance of both feature and decision fusion approaches outperforms the single performances of the fused algorithms significantly.
International Journal of Engineering Science and Technology , 2011,
Abstract: Palmprint recognition has attracted various researchers in recent years due to its richness in amount of features. In this work, palmprint authentication system is classified into palmprint acquisition, preprocessing, feature extraction, feature fusion and matching. In the preprocessing stage we employed a modified preprocessing technique to extract the ROI and it is further enhanced using adaptive histogram equalization. In feature extraction, the single sample representation has become bottleneck in producing high performance. To solve this we propose an intramodal feature fusion for palmprint authentication. The proposed system extracts multiplefeatures like Texture (Gabor), Line and Appearance (PCA) features from the preprocessed palmprint images. The feature vectors obtained from different approaches are in different dimensions and also the features from same image may be correlated. Therefore, we propose wavelet based fusion techniques to fuse extracted features as it contains wavelet extensions and uses mean-max fusion method to overcome the problem of feature fusion. Finally the feature vector is matched with stored template using NN classifier. The proposed approach is validated for their efficiency on PolyU palmprint database of 200 users. The experimental results illustrates thatthe feature level fusion improves the recognition accuracy significantly.
Cross-pose Face Recognition by Canonical Correlation Analysis  [PDF]
Annan Li,Shiguang Shan,Xilin Chen,Bingpeng Ma,Shuicheng Yan,Wen Gao
Computer Science , 2015,
Abstract: The pose problem is one of the bottlenecks in automatic face recognition. We argue that one of the diffculties in this problem is the severe misalignment in face images or feature vectors with different poses. In this paper, we propose that this problem can be statistically solved or at least mitigated by maximizing the intra-subject across-pose correlations via canonical correlation analysis (CCA). In our method, based on the data set with coupled face images of the same identities and across two different poses, CCA learns simultaneously two linear transforms, each for one pose. In the transformed subspace, the intra-subject correlations between the different poses are maximized, which implies pose-invariance or pose-robustness is achieved. The experimental results show that our approach could considerably improve the recognition performance. And if further enhanced with holistic+local feature representation, the performance could be comparable to the state-of-the-art.
Two-dimensional canonical correlation analysis and its application to face recognition

SONG Dong-xing,LIU Yong-jun,CHEN Cai-kou,

计算机应用 , 2008,
Abstract: According to the traditional Canonical Correlation Analysis (CCA), a novel method of combined feature extraction called Two-Dimensional Canonical Correlation Analysis (2DCCA) was proposed in this paper. It combines feature matrix directly by using the main idea of image projection in face recognition. Compared with the traditional CCA based on feature vectors, this method has the following two main advantages: first, the Small Sample Size problem (SSS) occurred in traditional CCA is essentially inevitable as a result of the evidently reducing dimension of the covariance matrix. By the same reason, the second advantage is that much computational time would be saved if using the proposed method. Finally, extensive experiments performed on ORL and AR face database verify the effectiveness of the proposed method.
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.