Object recognition in man, monkey, and machine
Object recognition in man, monkey, and machine
复制标题
人、猴子和机器的物体识别
DOI：
10.7551/mitpress/5089.001.0001
复制
发表时间：
1999
期刊：
影响因子：
1.8
通讯作者：
H. Bülthoff
中科院分区：
文献类型：
--
作者：
M. Tarr;H. Bülthoff
这些关于三维视觉物体识别的相互关联的文章展示了该领域一些最具创造力的神经科学，认知和计算科学家的前沿研究。卡桑德拉摩尔和帕特里克卡瓦纳采用了一个经典的演示，“双色调”图像的感知，并将其转化为一种方法，用于理解物体表面表征的本质以及自下而上和自上而下过程之间的相互作用。Michael J. Tarr和伊莎贝尔高蒂尔使用计算机图形学来研究视点依赖的识别机制是否可以在感知定义的类的样本之间推广。Melvyn A. Goodale和G.基思汉弗莱使用创新的心理物理学技术来研究脑损伤受试者的视觉和空间处理的分离方面。D.I. Perrett，M.W. Oram和E.阿什布里奇联合收割机将猴子的神经生理学单细胞数据与计算分析相结合，以一种新的方式思考调节视点依赖的物体识别和心理旋转的机制。Shimon Ullman还从机器视觉的角度讨论了解释视点依赖行为的可能机制。最后，菲利普·G。Schyns综合了许多领域的工作，提供了一个连贯的解释刺激类和识别任务如何相互作用。贡献者带来了广泛的方法来承担基于图像的对象识别的共同问题。
These interconnected essays on three-dimensional visual object recognition present cutting-edge research by some of the most creative neuroscientific, cognitive, and computational scientists in the field. Cassandra Moore and Patrick Cavanagh take a classic demonstration, the perception of "two-tone" images, and turn it into a method for understanding the nature of object representations in terms of surfaces and the interaction between bottom-up and top-down processes. Michael J. Tarr and Isabel Gauthier use computer graphics to study whether viewpoint-dependent recognition mechanisms can generalize between exemplars of perceptually defined classes. Melvyn A. Goodale and G. Keith Humphrey use innovative psychophysical techniques to investigate dissociable aspects of visual and spatial processing in brain-injured subjects. D.I. Perrett, M.W. Oram, and E. Ashbridge combine neurophysiological single-cell data from monkeys with computational analyses for a new way of thinking about the mechanisms that mediate viewpoint-dependent object recognition and mental rotation. Shimon Ullman also addresses possible mechanisms to account for viewpoint-dependent behavior, but from the perspective of machine vision. Finally, Philippe G. Schyns synthesizes work from many areas, to provide a coherent account of how stimulus class and recognition task interact. The contributors bring a wide range of methodologies to bear on the common problem of image-based object recognition.