A Shape Model with Coactivation Networks for Recognition and Segmentation

T.M. Lebo and R.S. Gaborski (USA)


Computer Vision, Pattern Recognition, Physiological Mo tivation


Research in image understanding is an ongoing endeavor in a variety of disciplines and manifests itself in a variety of application domains. The typical goal of this research is to develop techniques to automatically extract meaningful information from a population of images. Object recog nition is a key process in image understanding because it enables additional higher-level processing. We present a components-based object detection and localization algo rithm that aids segmentation for static images, along with a new approach for the discrimination of object presence in the static domain. The approach integrates the learned knowledge about the category with the supporting informa tion in the image to combine the segmentation and recog nition processes, allowing their interactions to guide sub sequent processing. An activation network provides top down perceptual grouping to supplement the initial holistic interpretations associated with the initial hypotheses. Lo calization is aided by allowing an activated interpretation to trigger an investigation of reinforced interpretations that can support or suppress a current hypothesis, reducing the reliance on low-level feature detectors to achieve proper de tection.

Important Links:

Go Back