Low-rank matrix recovery is an important problem extensively studied in machine learning, data mining and computer vision communities. A novel method is proposed for low-rank matrix recovery, targeting at higher recov...Low-rank matrix recovery is an important problem extensively studied in machine learning, data mining and computer vision communities. A novel method is proposed for low-rank matrix recovery, targeting at higher recovery accuracy and stronger theoretical guarantee. Specifically, the proposed method is based on a nonconvex optimization model, by solving the low-rank matrix which can be recovered from the noisy observation. To solve the model, an effective algorithm is derived by minimizing over the variables alternately. It is proved theoretically that this algorithm has stronger theoretical guarantee than the existing work. In natural image denoising experiments, the proposed method achieves lower recovery error than the two compared methods. The proposed low-rank matrix recovery method is also applied to solve two real-world problems, i.e., removing noise from verification code and removing watermark from images, in which the images recovered by the proposed method are less noisy than those of the two compared methods.展开更多
Recently, a qualitative approach was proposed for 3-D shape recovery based on a hybrid object representation[1]. In this approach, aspect recovery is the most important stage which binds regions in the image into mean...Recently, a qualitative approach was proposed for 3-D shape recovery based on a hybrid object representation[1]. In this approach, aspect recovery is the most important stage which binds regions in the image into meaningful aspects to support 3-D primitive recovery. There is no known polynondal time algo-rithm to solve this problem. The previous approach dealt with this problem by using a heuristic method based on the conditional probability. Unlike the previous method, this paper presents a novel parallel voting scheme to conquer the problem for efficiency. For this purpose) the previous global aspect rep-resentation is replaced with a distributed representation of aspects. Based on this representation, a three-layer parallel voting network for aspect recovery is proposed. For evaluating likelihood, a continuous Hopfield net is employed so that all aspect coverings in decreasing order of likelihood can be enumerated.The paper describes this method in detail and demonstrates its usefulness with simulation.展开更多
基金Projects(61173122,61262032) supported by the National Natural Science Foundation of ChinaProjects(11JJ3067,12JJ2038) supported by the Natural Science Foundation of Hunan Province,China
文摘Low-rank matrix recovery is an important problem extensively studied in machine learning, data mining and computer vision communities. A novel method is proposed for low-rank matrix recovery, targeting at higher recovery accuracy and stronger theoretical guarantee. Specifically, the proposed method is based on a nonconvex optimization model, by solving the low-rank matrix which can be recovered from the noisy observation. To solve the model, an effective algorithm is derived by minimizing over the variables alternately. It is proved theoretically that this algorithm has stronger theoretical guarantee than the existing work. In natural image denoising experiments, the proposed method achieves lower recovery error than the two compared methods. The proposed low-rank matrix recovery method is also applied to solve two real-world problems, i.e., removing noise from verification code and removing watermark from images, in which the images recovered by the proposed method are less noisy than those of the two compared methods.
文摘Recently, a qualitative approach was proposed for 3-D shape recovery based on a hybrid object representation[1]. In this approach, aspect recovery is the most important stage which binds regions in the image into meaningful aspects to support 3-D primitive recovery. There is no known polynondal time algo-rithm to solve this problem. The previous approach dealt with this problem by using a heuristic method based on the conditional probability. Unlike the previous method, this paper presents a novel parallel voting scheme to conquer the problem for efficiency. For this purpose) the previous global aspect rep-resentation is replaced with a distributed representation of aspects. Based on this representation, a three-layer parallel voting network for aspect recovery is proposed. For evaluating likelihood, a continuous Hopfield net is employed so that all aspect coverings in decreasing order of likelihood can be enumerated.The paper describes this method in detail and demonstrates its usefulness with simulation.