Epshtein Boris, Lifshitz Ita, Ullman Shimon
Department of Computer Science, The Weizmann Institute of Science, Rehovot 76100, Israel.
Proc Natl Acad Sci U S A. 2008 Sep 23;105(38):14298-303. doi: 10.1073/pnas.0800968105. Epub 2008 Sep 16.
The human visual system recognizes objects and their constituent parts rapidly and with high accuracy. Standard models of recognition by the visual cortex use feed-forward processing, in which an object's parts are detected before the complete object. However, parts are often ambiguous on their own and require the prior detection and localization of the entire object. We show how a cortical-like hierarchy obtains recognition and localization of objects and parts at multiple levels nearly simultaneously by a single feed-forward sweep from low to high levels of the hierarchy, followed by a feedback sweep from high- to low-level areas.
人类视觉系统能够快速且高精度地识别物体及其组成部分。视觉皮层的标准识别模型采用前馈处理，即先检测物体的部分，再识别完整物体。然而，部分本身往往具有模糊性，需要先检测和定位整个物体。我们展示了一种类似皮层的层级结构如何通过从层级结构的低层到高层的单次前馈扫描，然后是从高层到低层区域的反馈扫描，几乎同时在多个层级上实现物体及其部分的识别和定位。
