In this paper, a face recognition method using local qualitative representations is proposed to solve the problem of face recognition in varying lighting. Based on the observation that the ordinal relationship between...
详细信息
ISBN:
(纸本)9780819469526
In this paper, a face recognition method using local qualitative representations is proposed to solve the problem of face recognition in varying lighting. Based on the observation that the ordinal relationship between the average brightness of image regions pair is invariant under lighting changes, Local Binary Mapping is defined as an illumination invariant for face recognition based on Local Binary pattern descriptor, which extracts the local variance features of an image. For the 'symbol' feature vector, hamming distance is used as similarity measurement. It has been proved that the proposed method can provide the accuracy of 100 percent for subset 2, 3, 4 and 98.89 percent for subset 5 of the Yale facial database B when all images in subset 1 are used as gallery.
In this paper, we present a novel V-system descriptor for 2D models;the descriptor is invariant against the rotation, translation, scale transform, and can remove the effect of the arbitrary start point of the shape t...
详细信息
In this paper, we present a novel V-system descriptor for 2D models;the descriptor is invariant against the rotation, translation, scale transform, and can remove the effect of the arbitrary start point of the shape through the principal orientation. We show that V-system descriptor can be computed efficiently by the fast V-system transformation, and be good at using multi resolution analysis through weighted Euclidean distance. So the new V-system descriptor has some resistance to slightly occlusion, and may achieve good recognition property according to the actual situation.
In order to make full use of heterogeneous multi-sensor data to serve urban intelligent transportation systems, a real-time urban traffic state fusion model was proposed, named federated evidence fusion model. The mod...
详细信息
In order to make full use of heterogeneous multi-sensor data to serve urban intelligent transportation systems, a real-time urban traffic state fusion model was proposed, named federated evidence fusion model. The model improves conventional D-S evidence theory in temporal domain, such that it can satisfy the requirement of real-time processing and utilize traffic detection information more efficaciously. The model frame and computational procedures are given. In addition, a generalized reliability weight matrix of evidence is also presented to increase the accuracy of estimation. After that, a simulation test is presented to explain the advantage of the proposed method in comparison with conventional D-S evidence theory. Besides, the validity of the model is proven by the use of the data of loop detectors and GPS probe vehicles collected from an urban link in Shanghai. Results of the experiment show that the proposed approach can well embody and track traffic state at character level in real-time conditions.
In this paper, we propose to combine the spectral and texture features to compose the multi-feature vectors for the classification of multispectral remote sensing *** usually is difficult to obtain the higher classifi...
详细信息
In this paper, we propose to combine the spectral and texture features to compose the multi-feature vectors for the classification of multispectral remote sensing *** usually is difficult to obtain the higher classification accuracy if only considers one kind feature, especially for the case of different geographical objects have the same spectrum or texture specialty for a multispectral remote sensing *** spectral feature and the texture feature are composed together to form a new feature vector, which can represent the most effective features of the given remote sensing *** this way we can overcome shortcomings of only using the single feature and raise the classification *** system classification performance with composed feature vector is investigated by *** analysis of results we can learn how to combine the multi-feature vector can obtain a higher classification rate, and experiments proved that the proposed method is feasible and useful in multispectral remote sensing image classification study.
In statistical machine translation (SMT) research, phrase-based methods have been receiving more interest in recent years. In this paper, we first give a brief survey of phrase-based SMT framework, and then make detai...
详细信息
ISBN:
(纸本)9783540709381
In statistical machine translation (SMT) research, phrase-based methods have been receiving more interest in recent years. In this paper, we first give a brief survey of phrase-based SMT framework, and then make detailed comparisons of two typical implementations: alignment template approach and standard phrase-based approach. At last, we propose an improved model to integrate alignment template into standard phrase-based SMT as a new feature in a log-linear model. Experimental results show that our method outperforms the baseline method.
In this paper, a novel neural network based manifold learning method(NNBML)[1] recently appeared in the Journal of Science is introduced. It can effectively convert high-dimensional data into low-dimensional codes, wh...
详细信息
ISBN:
(纸本)9781601320438
In this paper, a novel neural network based manifold learning method(NNBML)[1] recently appeared in the Journal of Science is introduced. It can effectively convert high-dimensional data into low-dimensional codes, which are then used for classification. However, it performs not well while dealing with small size face database used for face recognition. We propose a solution generating more samples data based on the existing data. The proposed method is implemented on two well-known face databases, viz. ORL and Yale face databases. The experimental results show that NNBML is able to deal with the task of face recognition after more data samples generated using the proposed method, and also that NNBML outperforms LDA in terms of recognition rate.
This paper discussed the reliability of computing the road link speed from probe vehicles. An algorithm for the smallest probe vehicle sampling sizes for traffic flow estimation was proposed. Many factors are consider...
详细信息
This paper discussed the reliability of computing the road link speed from probe vehicles. An algorithm for the smallest probe vehicle sampling sizes for traffic flow estimation was proposed. Many factors are considered, such as road style, road link speed and information transmit period of probe vehicle. The field testing using traffic data of Xuhui district in Shanghai presents a good result which validates the effecfiveness of the new model.
This paper discussed a novel segmentation algorithm B-JSEG for color images based on color information and region growing. This method is proposed on the base of JSEG, a popular method in segmentation of color images,...
详细信息
This paper discussed a novel segmentation algorithm B-JSEG for color images based on color information and region growing. This method is proposed on the base of JSEG, a popular method in segmentation of color images, and directional operators for edge detection in images. Compared with other methods existed, new parameters are used to characterize the property of color-texture images in the proposed method. With the aim of alleviating over-segmentation, directional operators are integrated into the JSEG method to take account of both homogeneity and discontinuity in regions. It is shown from the experiments on large amounts of images that the proposed method is robust and able to match better with human's perception than JSEG.
In this paper, a pixel-level image fusion algorithm based on Nonsubsampled Contourlet Transform (NSCT) has been proposed. Compared with Contourlet Transform, NSCT is redundant, shift-invariant and more suitable for im...
详细信息
ISBN:
(纸本)9780819469519
In this paper, a pixel-level image fusion algorithm based on Nonsubsampled Contourlet Transform (NSCT) has been proposed. Compared with Contourlet Transform, NSCT is redundant, shift-invariant and more suitable for image fusion. Each image from different sensors could be decomposed into a low frequency image and a series of high frequency images of different directions by multi-sacle NSCT. For low and high frequency images, they are fused based on local-contrast enhancement and definition respectively. Finally, fused image is reconstructed from low and high frequency fused images. Experiment demonstrates that NSCT could preserve edge significantly and the fusion rule based on region segmentation performances well in local-contrast enhancement.
In accordance with the outer skin and model segmentation issues in simulated plastic surgery, a simplified axis extraction method based on active window was proposed. The new method simplifies the M-Reps by using prio...
详细信息
In accordance with the outer skin and model segmentation issues in simulated plastic surgery, a simplified axis extraction method based on active window was proposed. The new method simplifies the M-Reps by using priori shape information of regions. It is applied to the segmentation of outer skin and model in the plastic surgery simulation. The results show the effectiveness of the proposed method.
暂无评论