Computer Engineering and Applications ›› 2022, Vol. 58 ›› Issue (7): 1-20.DOI: 10.3778/j.issn.1002-8331.2110-0253

• Research Hotspots and Reviews • Previous Articles     Next Articles

Research and Prospect of Brain-Inspired Model for Visual Object Recognition

YANG Xi, YAN Jie, WANG Wen, LI Shaoyi, LIN Jian   

  1. 1.School of Astronautics, Northwestern Polytechnical University, Xi’an 710072, China
    2.Functional and Molecular Imaging Key Lab of Shaanxi Province, Department of Radiology, Air Force Medical University, Xi’an 710038, China
    3.Unmanned Systems Research Institute, Northwestern Polytechnical University, Xi’an 710072, China
  • Online:2022-04-01 Published:2022-04-01

脑启发的视觉目标识别模型研究与展望

杨曦,闫杰,王文,李少毅,林健   

  1. 1.西北工业大学 航天学院,西安 710072
    2.空军军医大学 放射科 陕西省功能与分子影像重点实验室,西安 710038
    3.西北工业大学 无人系统技术研究院,西安 710072

Abstract: Visual object recognition is one of the most fundamental and challenging research topics in the field of computer vision. The research on the neural mechanism of the primates’ recognition function may bring revolutionary breakthroughs in brain-inspired vision. This review aims to systematically review the recent works on the intersection of computational neuroscience and computer vision. It attempts to investigate the current brain-inspired object recognition models and their underlying visual neural mechanism. According to the technical architecture and exploitation methods, the paper describes the brain-inspired object recognition models and their advantages and disadvantages in realizing brain-inspired object recognition. It focuses on analyzing the similarity between the artificial and biological neural network, and studying the biological credibility of the current popular DNN-based visual benchmark models. The analysis provides a guide for researchers to measure the occasion and condition when conducting visual object recognition research.

Key words: brain-inspired vision, model for object recognition, neural mechanisms, deep neural network

摘要: 视觉目标识别是计算机视觉领域中最基本、最具有挑战性的研究课题之一。由于灵长类出色的视觉目标识别能力,对其神经功能机理的研究可能为类脑视觉带来革命性的突破。旨在系统地回顾最近在计算神经科学和计算机视觉交叉领域的工作,研究当前基于脑启发的目标识别模型及其依据的视觉神经机制。从认知功能和皮层动力学方面总结了灵长类视觉目标识别机制的基本特征和主要贡献;根据技术架构和开发方式总结了基于大脑启发的目标识别模型及其实现类脑目标识别的优缺点。进一步对人工神经网络与视觉神经网络进行相似性分析,研究了当前流行的CNN视觉基准模型在生物学上的可信性。总结了当前视觉目标识别常用的实验设计条件和数据分析方法,可以作为一个研究人员进行视觉目标识别研究时权衡时机和条件的使用指南。

关键词: 类脑视觉, 目标识别模型, 神经机制, 深度神经网络