Dynamic texture is an extension of texture to the temporal domain. Description and recognition of dynamic textures has attracted growing attention. In this paper, a new method for recognizing dynamic textures is propo...
详细信息
ISBN:
(纸本)9783540709312
Dynamic texture is an extension of texture to the temporal domain. Description and recognition of dynamic textures has attracted growing attention. In this paper, a new method for recognizing dynamic textures is proposed. The textures are modeled with volume local binary patterns (VLBP), which are an extension of the LBP operator widely used in still texture analysis, combining the motion and appearance together. A rotation invariant VLBP is also proposed. Our approach has many advantages compared with the earlier approaches, providing a better performance for two test databases. Due to its rotation invariance and robustness to gray-scale variations, the method is very promising for practical applications.
In order to enlarge the processing level with macrocosm idea, a classified recognition method is proposed, it classifies a bar-like block structure, analyses its topological adjacent relationship and recognizes lines ...
详细信息
ISBN:
(纸本)9789889867140
In order to enlarge the processing level with macrocosm idea, a classified recognition method is proposed, it classifies a bar-like block structure, analyses its topological adjacent relationship and recognizes lines by imitating uman vision process. In the block structure, a rational set in which all pixels have a common character retrieve the colony characteristic of related pixels, individual pixel has not such geometrical features, so the structure is a higher representation of individual pixel. After classification the blocks are organized into chains, lines (including arcs and curves) are extracted. In cross region of lines, the algorithm modifies only Bar-like blocks instead of dealing with points which are near intersection area. The results demonstrate the effectiveness.
Hand biometrics, including fingerprint, palmprint, hand geometry and hand vein pattern, have obtained extensive attention in recent years. Physiologically, skin is a complex multi-layered tissue consisting of various ...
详细信息
ISBN:
(纸本)9783540763895
Hand biometrics, including fingerprint, palmprint, hand geometry and hand vein pattern, have obtained extensive attention in recent years. Physiologically, skin is a complex multi-layered tissue consisting of various types of components. Optical research suggests that different components appear when the skin is illuminated with light sources of different wavelengths. This motivates us to extend the capability of camera by integrating information from multispectral palm images to a composite representation that conveys richer and denser pattern for recognition. Besides, usability and security of the whole system might be boosted at the same time. In this paper, comparative study of several pixel level multispectral palm image fusion approaches is conducted and several well-established criteria are utilized as objective fusion quality evaluation measure. Among others, Curvelet transform is found to perform best in preserving discriminative patterns from multispectral palm images.
Hough Transform (HT) is a widely used method for finding lines, circles and other image features by projecting images onto a parametric space to simplify the feature detection. Direction detection has played an import...
详细信息
ISBN:
(纸本)9781601320438
Hough Transform (HT) is a widely used method for finding lines, circles and other image features by projecting images onto a parametric space to simplify the feature detection. Direction detection has played an important role in many applications. Various approaches including HT-based methods have been developed for direction detection. Most HT-based methods try first to enhance image line features of an image, and then map the enhanced features onto Hough space to find line(s). In this paper, a new robust method which is based on Hough Transform is proposed. Standard Deviation as a cost function is applied along every angle index in Hough space and it transfers the two-dimensional Hough space into a one-dimensional curve which can reveal the overall directional information in the original image. Its full utilization of statistic information inherent within Hough space makes it sensitive to feature direction and robust to interference caused by bias in Hough space.
Iris image quality assessment is an important part of iris recognition system because the qualities of iris images would largely influence the recognition results. In this paper, we analyze and compare several represe...
详细信息
ISBN:
(纸本)9784901122078
Iris image quality assessment is an important part of iris recognition system because the qualities of iris images would largely influence the recognition results. In this paper, we analyze and compare several representative quality assessment methods, and then propose an effective method based on Laplacian of Gaussian operator for iris image assessment. Through computer simulations of several typical algorithms on our iris image database, SJTU-IDB, the proposed method is shown superior to the compared quality assessment methods.
A hidden Markov model (HMM) for recognition of handwritten Devanagari words is proposed. The HMM has the property that its states are not defined a priori, but are determined automatically based on a database of handw...
详细信息
In multiple object tracking, the confusion caused by occlusion and similar appearances is an important issue to be solved. In this paper, trackability is proposed to measure how well given features can be used to find...
详细信息
ISBN:
(纸本)9783540741954
In multiple object tracking, the confusion caused by occlusion and similar appearances is an important issue to be solved. In this paper, trackability is proposed to measure how well given features can be used to find the correspondence of any given object in videos with multiple objects. Based on the analysis of trackability and computational complexity of the features under various occlusion conditions, a dynamic feature method cascade is presented to match the objects in consecutive frames. The cascade is composed of three tracking features: appearance;velocity and position. These features are enabled or disabled online to reduce computational complexity while obtaining similar trackability. Experiments are conducted on 27062 frame occlusion objects, in the cases of good trackability, our experiments can obtain high succussful tracking rate with low computation burden, and in the cases of poor trackability, our estimation of trackability and confusion matrix can explain why they can not be tracked well.
The article presents the multimodal user interface ICANDO (Intellectual computer AssistaNt for Disabled Operators) that was awarded with the first prize of the Loco Mummy Software Contest in 2006. The interface is int...
详细信息
The article presents the multimodal user interface ICANDO (Intellectual computer AssistaNt for Disabled Operators) that was awarded with the first prize of the Loco Mummy Software Contest in 2006. The interface is intended mainly for assistance to the persons without hands or with disabilities of their hands or arms but could be useful for ordinary users at hands-free contactless human-computer interaction too. It combines the module for automatic recognition of voice commands in English, French and Russian as well as the head tracking module in one multimodal interface. ICANDO interface was applied for hands-free work with Graphical User Interface of a personal computer in such tasks as Internet communication and work with graphical and text documents. The article describes the aim and the architecture of the interface, the methods for speech recognition and head tracking, information fusion and synchronization of the multimodal streams. The presented results of testing and exploitation of ICANDO user interface have confirmed high accuracy and robustness of the interface for contactless operation with a computer. The comparison of multimodal and standard ways of interaction has discovered that the first one is slower by a factor of 1.9 that is quite well for hands-free interaction between a computer and an impaired person.
The proceedings contain 99 papers. The topics discussed include: learning in computervision: some thoughts;biometric recognition: overview and recent advances;a family of novel graph kernels for structural pattern re...
详细信息
ISBN:
(纸本)9783540767244
The proceedings contain 99 papers. The topics discussed include: learning in computervision: some thoughts;biometric recognition: overview and recent advances;a family of novel graph kernels for structural patternrecognition;a system biology approach for the steady-state analysis of gene signaling networks;model-based correlation measure for nonuniformity gain and offset parameters of infrared focal-plane-array sensors;a cyclostationary analysis applied to detection and diagnosis of faults in helicopter gearboxes;robust industrial machine sounds identification based on frequency spectrum analysis;fuzzy vector directional filters for multichannel image denoising;video analysis via nonlinear dimensionality reduction;a multiple substructure matching algorithm for fingerprint verification;and image segmentation using automatic seeded region growing and instance-based learning.
Gabor filter responses are general purpose features for computervision and image processing and have been very successful in many application areas, for example in biometric authentication (fingerprint matching, face...
详细信息
ISBN:
(纸本)9780769528779
Gabor filter responses are general purpose features for computervision and image processing and have been very successful in many application areas, for example in biometric authentication (fingerprint matching, face detection, face recognition and iris recognition). In a typical feature construction, filters are utilised as a multi-resolution structure of several filters tuned to different frequencies and orientations. The multi-resolution structure is similar to wavelets, but the non-orthogonality of Gabor functions implies the main weakness: computational heaviness. The high computational complexity prevents their use in many real-time or near real-time tasks. In this study, an efficient sequential computation method for multi-resolution Gabor features is presented.
暂无评论