Kietzmann Tim C, Lange Sascha, Riedmiller Martin
Institute of Cognitive Science, University of Osnabrück, Osnabrück, Germany.
Biol Cybern. 2009 Jan;100(1):59-79. doi: 10.1007/s00422-008-0281-6. Epub 2008 Dec 17.
We propose a conceptual framework for artificial object recognition systems based on findings from neurophysiological and neuropsychological research on the visual system in primate cortex. We identify some essential questions, which have to be addressed in the course of designing object recognition systems. As answers, we review some major aspects of biological object recognition, which are then translated into the technical field of computer vision. The key suggestions are the use of incremental and view-based approaches together with the ability of online feature selection and the interconnection of object-views to form an overall object representation. The effectiveness of the computational approach is estimated by testing a possible realization in various tasks and conditions explicitly designed to allow for a direct comparison with the biological counterpart. The results exhibit excellent performance with regard to recognition accuracy, the creation of sparse models and the selection of appropriate features.
我们基于对灵长类动物皮层视觉系统的神经生理学和神经心理学研究结果，提出了一个用于人工物体识别系统的概念框架。我们确定了在设计物体识别系统过程中必须解决的一些基本问题。作为答案，我们回顾了生物物体识别的一些主要方面，然后将其转化到计算机视觉技术领域。关键建议是使用增量式和基于视图的方法，以及在线特征选择能力和物体视图的互连，以形成整体物体表示。通过在明确设计用于与生物对应物进行直接比较的各种任务和条件下测试一种可能的实现方式，来评估计算方法的有效性。结果在识别准确性、稀疏模型的创建和适当特征的选择方面表现出优异的性能。
