Background modeling plays an important role in video surveillance, yet in complex scenes it is still a challenging problem. Among many difficulties, problems caused by illumination variations and dynamic backgrounds are the key aspects. In this work, we develop an efficient background subtraction framework to tackle these problems. First, we propose a scale invariant local ternary pattern operator, and show that it is effective for handling illumination variations, especially for moving soft shadows. Second, we propose a pattern kernel density estimation technique to effectively model the probability distribution of local patterns in the pixel process, which utilizes only one single LBP-like pattern instead of histogram as feature. Third, we develop multimodal background models with the above techniques and a multiscale fusion scheme for handling complex dynamic backgrounds. Exhaustive experimental evaluations on complex scenes show that the proposed method is fast and effective, achieving more than 10% improvement in accuracy compared over existing state-of-the-art algorithms.

In this paper, we propose a simple and robust local descriptor, called the robust local binary pattern (RLBP). The local binary pattern (LBP) works very successfully in many domains, such as texture classification, human detection and face recognition. However, an issue of LBP is that it is not so robust to the noise present in the image. We improve the robustness of LBP by changing the coding bit of LBP. Experimental results on the Brodatz and UIUC texture databases show that RLBP impressively outperforms the other widely used descriptors (e.g., SIFT, Gabor, MR8 and LBP) and other variants of LBP (e.g., completed LBP), especially when we add noise in the images. In addition, experimental results on human face recognition also show a promising performance comparable to the best known results on the Face Recognition Grand Challenge (FRGC) face dataset. IntroductionRecently, many sparse and dense descriptors (e.g., SIFT, Gabor, MR8 and LBP) have been proposed for different kinds of applications. There are several studies to evaluate their performance, e.g., [13,14]. LBP [15] is perhaps the best performing dense descriptor and it has been widely used in various applications, such as texture classification, human detection and face recognition [18]. It has been proven to be highly discriminative and its key advantages, namely its invariance to monotonic gray level changes and computational efficiency, make it suitable for demanding image analysis tasks.However, one issue of LBP is that it is not so robust to the noise present in images when the gray-level changes resulting from the noise are not monotonic, even if the changes are not significant [2]. To this end, we propose a new descriptor based on LBP, i.e., robust local binary pattern (RLBP). The idea is to locate the possible bit in LBP pattern changed by the noise and then revise the changed bit of the LBP pattern. The idea is very simple, but it works very well. For example, the performance of LBP decreases significantly when we add white Gauss noise in the Brodatz texture dataset [1]. However, the performance of RLBP almost does not change. We also add noise in UIUC texture [7] and FRGC face datasets [17] to testify the performance of RLBP.

No abstract

In this paper, we propose a robust local descriptor for face recognition. It consists of two components, one based on a shearlet-decomposition and the other on local binary pattern (LBP). Shearlets can completely analyze the singular structures of piecewise smooth images, which is useful since singularities and irregular structures carry useful information in an underlying image. Furthermore, LBP is effective for describing the edges extracted by shearlets even when the images contain high level of noise. Experimental results using the Face Recognition Grand Challenge (FRGC) dataset show that the proposed local descriptor significantly outperforms many widely used features (e.g., Gabor and deep learning based features) when the images are corrupted by random noise, demonstrating the strong noise robustness of our approach. In addition, experimental results show promising results for two challenging datasets which have poor image quality, i.e., a remote face dataset and the Point and Shoot Face Recognition Challenge (PaSC) dataset.

No abstract