From appearance to context-based recognition: Dense labeling in small images

Traditionally, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. As supported by our human studies, this contextual information is necessary for accurate recognition in low resolution images. This scenario with impoverished appearance information, as opposed to using images of higher resolution, provides an appropriate venue for studying the role of context in recognition. In this paper, we explore the role of context for dense scene labeling in small images. Given a segmentation of an image, our algorithm assigns each segment to an object category based on the segment's appearance and contextual information. We explicitly model context between object categories through the use of relative location and relative scale, in addition to co-occurrence. We perform recognition tests on low and high resolution images, which vary significantly in the amount of appearance information ...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Devi Parikh, C. Lawrence Zitnick, Tsuhan Chen
• Keywords: Blind Recognition, Computer Vision, Context, CVPR 2008, Impoverished Appearance Information, Object Appearance Information, Object Categories, Object Category, Small Images, Tiny Images