Occlusion in face recognition is a common yet challenging problem. While sparse representation based classification (SRC) has been shown promising performance in laboratory conditions (i.e. noiseless or random pixel corrupted), it performs much worse in practical scenarios. In this paper, we consider the practical face recognition problem, where the occlusions are predictable and available for sampling. We propose the structured occlusion coding (SOC) to address occlusion problems. The structured coding here lies in two folds. On one hand, we employ a structured dictionary for recognition. On the other hand, we propose to use the structured sparsity in this formulation. Specifically, SOC simultaneously separates the occlusion and classifies the image. In this way, the problem of recognizing an occluded image is turned into seeking a structured sparse solution on occlusion-appended dictionary. In order to construct a well-performing occlusion dictionary, we propose an occlusion mask estimating technique via locality constrained dictionary (LCD), showing striking improvement in occlusion sample. On a category-specific occlusion dictionary, we replace l 1 norm sparsity with the structured sparsity which is shown more robust, further enhancing the robustness of our approach. Moreover, SOC achieves significant improvement in handling large occlusion in real world. Extensive experiments are conducted on public data sets to validate the superiority of the proposed algorithm. occlusion identification accuracy. If too much discriminative information is abandoned, the following classification becomes difficult. To enhance the accuracy of occlusion identification, [11] adopts the prior that the occlusion is spatially continuous and consequently achieves excellent performance. However, such unsupervised approach might cause misestimate when occlusion is severe. For instance, a scarf larger than half of the testing face may be considered as a useful signal, and therefore face pixels may be discarded in each iteration. We call it a degenerate solution. Besides, the algorithm in [11] has to be carried out subject-by-subject and exhaustively search the class with the minimum normalized error, which is time-consuming and detrimental to real-time applications.Recently, several occlusion dictionary based approaches [13][14][15][16] for robust face recognition have been attached more and more importance. This kind of method is capable of efficiently handling various occlusions. They exploit characteristics of non-occluded and occluded region, assuming that both of them can be coded over the corresponding part of dictionary [12]. These methods act in the similar way with each other. Concretely, an occlusion dictionary is concatenated to the original dictionary to perform occlusion coding. The goal is to jointly represent the occluded image. Fig. 1 illustrates how occlusion dictionary methods work. By seeking a sparse solution, the occluded image successfully decomposes into face and occlusion. The classification is carried out via th...

No abstract

No abstract

No abstract

No abstract