During the last years, there has been an increasing interest in applying the multiple classifier framework to the domain of structural patternrecognition. Constructing base classifiers when the input patterns are gra...
详细信息
The speaker is one of the privileged many to have been taught syntactic patternrecognition methods by the Late Prof. K.S. Fu. In this talk, I will discuss the evolution of stochastic image grammars from the early sev...
详细信息
The speaker is one of the privileged many to have been taught syntactic patternrecognition methods by the Late Prof. K.S. Fu. In this talk, I will discuss the evolution of stochastic image grammars from the early seventies to now with a focus on image and video understanding applications.
Signatures are extensively used as a means of personal verification. Manual signature-based authentication of a large number of documents is a very difficult and time consuming task. Consequently for many years, in th...
详细信息
Tracking multi-object under occlusion is a challenging task. When occlusion happens, only the visible part of occluded object can provide reliable information for the matching. In conventional algorithms, the deducing...
详细信息
Structured light based patterns provide a means to capture the state of an object shape. However it may be inefficient when the object is freely moving, when its surface contains high curvature parts or in out of dept...
详细信息
This paper proposes an object-matching method for repetitive patterns. Mismatching problems occur when descriptor-based features like SURF or SIFT are applied to repeated image patterns due to the use of the usual dis...
详细信息
We introduce Multiclass Kernel Projection Machines (MKPM), a new formalism that extends the Kernel Projection Machine framework to the multiclass case. Our formulation is based on the use of output codes and it implem...
详细信息
ISBN:
(纸本)9781457703942
We introduce Multiclass Kernel Projection Machines (MKPM), a new formalism that extends the Kernel Projection Machine framework to the multiclass case. Our formulation is based on the use of output codes and it implements a co-regularization scheme by simultaneously constraining the projection dimensions associated with the individual predictors that constitute the global classifier. In order to solve the optimization problem posed by our formulation, we propose an efficient dynamic programming approach. Numerical simulations conducted on a few patternrecognition problems illustrate the soundness of our approach.
Recovering arbitrarily corrupted low-rank matrices arises in computervision applications, including bioinformatic data analysis and visual tracking. The methods used involve minimizing a combination of nuclear norm a...
详细信息
ISBN:
(纸本)9781457703942
Recovering arbitrarily corrupted low-rank matrices arises in computervision applications, including bioinformatic data analysis and visual tracking. The methods used involve minimizing a combination of nuclear norm and l~1 norm. We show that by replacing the l~1 norm on error items with nonconvex M-estimators, exact recovery of densely corrupted low-rank matrices is possible. The robustness of the proposed method is guaranteed by the M-estimator theory. The multiplicative form of half-quadratic optimization is used to simplify the nonconvex optimization problem so that it can be efficiently solved by iterative regularization scheme. Simulation results corroborate our claims and demonstrate the efficiency of our proposed method under tough conditions.
The future multi-modal user interfaces of battery-powered mobile devices are expected to require computationally costly image analysis techniques. The use of Graphic Processing Units for computing is very well suited ...
详细信息
ISBN:
(纸本)9780819484093
The future multi-modal user interfaces of battery-powered mobile devices are expected to require computationally costly image analysis techniques. The use of Graphic Processing Units for computing is very well suited for parallel processing and the addition of programmable stages and high precision arithmetic provide for opportunities to implement energy-efficient complete algorithms. At the moment the first mobile graphics accelerators with programmable pipelines are available, enabling the GPGPU implementation of several image processing algorithms. In this context, we consider a face tracking approach that uses efficient gray-scale invariant texture features and boosting. The solution is based on the Local Binary pattern (LBP) features and makes use of the GPU on the pre-processing and feature extraction phase. We have implemented a series of image processing techniques in the shader language of OpenGL ES 2.0, compiled them for a mobile graphics processing unit and performed tests on a mobile application processor platform (OMAP3530). In our contribution, we describe the challenges of designing on a mobile platform, present the performance achieved and provide measurement results for the actual power consumption in comparison to using the CPU (ARM) on the same platform.
暂无评论