Recognizing Multiple Objects via Regression Incorporating the Co-occurrence of Categories

Abstract

Abstract. Most previous methods for generic object recognition explicitly or implicitly assume that an image contains objects from a single category, although objects from multiple categories often appear together in an image. In this paper, we present a novel method for object recognition that explicitly deals with objects of multiple categories coexisting in an image. Furthermore, our proposed method aims to recognize objects by taking advantage of a scene's context represented by the co-occurrence relationship between object categories. Specifically, our method estimates the mixture ratios of multiple categories in an image via MAP regression, where the likelihood is computed based on the linear combination model of frequency distributions of local features, and the prior probability is computed from the co-occurrence relation. We conducted a number of experiments using the PASCAL dataset, and obtained the results that lend support to the effectiveness of the proposed method.

Feature co-occurrence representation based on boosting for object detection

“…First, we look at methods that consider the co-occurrence of different categories [13][5] [12]. Using categories determined and their degree of reliability from appearance, these methods revise classification results from the relationship between those categories.…”

“…Also proposed in recent years are image categorization methods that make use of context [13][5] [12]. These methods use category-classification results determined from appearance to evaluate the relationship between categories and revise category output.…”