This paper presented an improved linear discriminant analysis (LDA) algorithm for face recognition, which can effectively deal with the two problems in traditional LDA-based approaches: (1) the small sample size probl...
详细信息
This paper presented an improved linear discriminant analysis (LDA) algorithm for face recognition, which can effectively deal with the two problems in traditional LDA-based approaches: (1) the small sample size problem, and (2) the Fisher criterion is nonoptimal with respect to classification rate. In particular, the proposed algorithm can also improve the classification rate of one or several appointed classes. The key to this method is to use the technique that it can reserves the significant discriminatory information for dimension reduction and meanwhile utilize a modified Fisher criterion. The comparative experiments on ORL face database verify the effectiveness of the proposed method.
The multiple subimage were extracted from the reference image according to a predefined selection method. They were regarded as a template and correlated with the real image. The multiple matching results were integra...
详细信息
The multiple subimage were extracted from the reference image according to a predefined selection method. They were regarded as a template and correlated with the real image. The multiple matching results were integrated with the clustering method based on the spatial relation among the subimages. The confidence of the final matching result was given. The test result showed that the method had improved the performance of correlation-based matching.
Aiming at the nonlinearity of photoresponse characteristic in infrared focal plane array (IRFPA), an approach for nonuniformity correction in IRFPA was proposed, which is simple and easy to implement by hardware circu...
详细信息
Aiming at the nonlinearity of photoresponse characteristic in infrared focal plane array (IRFPA), an approach for nonuniformity correction in IRFPA was proposed, which is simple and easy to implement by hardware circuit. The theoretical analysis and comparison of simulation results show that its performance is more perfect than that of the piecewise linear algorithm and the polynomial fitting algorithm, and only a few correction factors are needed.
The trend of intelligentization in development of automation technology is discussed. It is clarified that patternrecognition and intelligent system has become the kernel science and technology of promoting automatio...
详细信息
The trend of intelligentization in development of automation technology is discussed. It is clarified that patternrecognition and intelligent system has become the kernel science and technology of promoting automation. Example of research and application in patternrecognition and intelligent system is described, from which we can know the overseas development status. In the end, challenge and countermeasure of automatization in China are presented.
Central nervous system dysfunction in infants may be manifested through inconsistent, rigid and abnormal limb movements. Detection and quantification of these movements in infants from videos are hence desirable for p...
详细信息
ISBN:
(纸本)9781467383264
Central nervous system dysfunction in infants may be manifested through inconsistent, rigid and abnormal limb movements. Detection and quantification of these movements in infants from videos are hence desirable for providing useful information to clinicians. This could lead to computer-aided diagnosis of dysfunctions where early treatment may improve infant development. In this paper, we propose a scheme for detecting and quantifying qualitative aspects of limb movement through multiple tracking and state space motion modeling on videos. The main novelties of the paper include: (a) An enhanced detection method for effectively detection small weak marker points from video; (b) Bayesian estimation and nearest neighbor searching for selecting new observation in individual tracker and for tracking marker trajectories on limbs; (c) A criterion for anomaly detection based on the frequency and duration of abrupt changes in limb movement, using window averaged prominent residual powers. The proposed method has been tested on videos of neonates, results show that the proposed method is promising for tracking and quantifying the movement of neonate limbs for helping medical diagnostics.
This paper proposed a method for generating chaotic key stream based on the chaotic map and a fast algorithm to implement it. This method divides the chaotic attractor into 2n symmetric sub-intervals, samples from the...
详细信息
This paper proposed a method for generating chaotic key stream based on the chaotic map and a fast algorithm to implement it. This method divides the chaotic attractor into 2n symmetric sub-intervals, samples from the chaotic orbit every n time intervals, and gets the independently and uniformly distributed 2n-phase key stream. The theoretical and numerical analyses show that the sequence also has a high complexity. This method can be used in fields such as cryptography, numerical simulation and spread spectrum communication, etc.
This paper proposes a genetic-based algorithm for surface reconstruction of three-dimension (3-D) objects from a group of contours representing its section plane lines. The algorithm can optimize the triangulation of ...
详细信息
This paper proposes a genetic-based algorithm for surface reconstruction of three-dimension (3-D) objects from a group of contours representing its section plane lines. The algorithm can optimize the triangulation of the surface of 3-D objects with a multi-objective optimization function to meet the needs of a wide range of applications. Further, a new crossover operator for triangulation and a new 3-D quadrilateral mutation operator are also introduced.
Two treatments of color image segmentation with information entropy were introduced: (1) The layers of the image are analyzed with whole information entropy and the segmentation resolution can be self-adapted;(2) The ...
详细信息
Two treatments of color image segmentation with information entropy were introduced: (1) The layers of the image are analyzed with whole information entropy and the segmentation resolution can be self-adapted;(2) The image is segmented with patch information entropy by segmenting the image in patch. According to the segmentation results, it can be found that the image segmentation with alterable resolution is more similar to the processing character of human vision.
A FLIR image segmentation algorithm based on genetic algorithm and fuzzy set theory was presented. The method defines different member function for the object and background of the image to transform the image into fu...
详细信息
A FLIR image segmentation algorithm based on genetic algorithm and fuzzy set theory was presented. The method defines different member function for the object and background of the image to transform the image into fuzzy domain with maximum fuzzy entropy. The procedure for finding combination of a, b and c is implemented by genetic algorithm, thresholding image into object and background by maximizing the fuzzy entropy. The experiment results show that our proposed method gives better performance and higher calculation speed than other general methods with good real-time by using genetic algorithm.
Moment invariants are important shape descriptors in computer vision. The method of generating trigonometric function is suggested as a new efficient way to derive various moment invariants. General rule of moment inv...
详细信息
Moment invariants are important shape descriptors in computer vision. The method of generating trigonometric function is suggested as a new efficient way to derive various moment invariants. General rule of moment invariant construction is summarized and the notion of moment invariant space is established. Five more moment invariants are derived and tested. Furthermore, general explicit constructions of some high-order moment invariants are developed. The comparisons are made between the stabilities of several invariants for the discrete image. With the help of these additional moment invariants, we can distinguish the image and the object more accurately.
暂无评论