Scene analysis is a major aspect of perception and continues to challenge machine perception. This paper addresses the scene-analysis problem by integrating a primitive segmentation stage with a model of associative memory. Our model is a multistage system that consists of an initial primitive segmentation stage, a multimodule associative memory, and a short-term memory (STM) layer. Primitive segmentation is performed by locally excitatory globally inhibitory oscillator network (LEGION), which

more »

... egments the input scene into multiple parts that correspond to groups of synchronous oscillations. Each segment triggers memory recall and multiple recalled patterns then interact with one another in the STM layer. The STM layer projects to the LEGION network, giving rise to memory-based grouping and segmentation. The system achieves scene analysis entirely in phase space, which provides a unifying mechanism for both bottom-up analysis and top-down analysis. The model is evaluated with a systematic set of three-dimensional (3-D) line drawing objects, which are arranged in an arbitrary fashion to compose input scenes that allow object occlusion. Memory-based organization is responsible for a significant improvement in performance. A number of issues are discussed, including input-anchored alignment, top-down organization, and the role of STM in producing context sensitivity of memory recall. Index Terms-Associative memory, grouping, integration, locally excitatory globally inhibitory oscillator network (LEGION), scene analysis, segmentation, short-term memory (STM). DeLiang Wang (M'90-SM'01) received the B.S. and M.S. degrees from the , leading the Florida State Vision Group. His current research interests include low-dimensional representations of images, image classification and segmentation, statistical computer vision, neural networks, and computational models of vision.