With the rapid development and application of CRFs (Conditional Random Fields) in computer vision, many researchers have made some outstanding progress in this domain because CRFs solve the classical version of the label bias problem with respect to MEMMs (maximum entropy Markov models) and HMMs (hidden Markov models). This paper reviews the research development and status of object recognition with CRFs and especially introduces two main discrete optimization methods for image labeling with CRFs: graph cut and mean field approximation. This paper describes graph cut briefly while it introduces mean field approximation more detailedly which has a substantial speed of inference and is researched popularly in recent years.
Abstract-In this paper, we propose a new approach for semantic image labeling by incorporating texture, gradient and color information. In our paper, the texture information is extracted by Gray Level Co-occurrence Matrix (GLCM). The gradient information is obtained by Histograms of Oriented Gradients (HOG). We apply the HOG, GLCM descriptors with color information simultaneously to enrich the image features of different information. To utilizing these features more effectively, we use the Approximate Nearest Neighbors (ANN) algorithm for clustering. After obtaining these information, the Joint Boost algorithm is applied to give an effective classifier by training many weak learner classifiers. At the end, a set of experiments with one descriptor or several descriptors combined are made to evaluating the performance of our method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.