Visual nervous system based multi-module neural network for object recognition

Tetsuya Tannai, Masafumi Hagiwara

Research output: Contribution to journalConference article

Abstract

Although most of the conventional systems for object recognition have their own special targets, this paper gives a generic idea for universal object recognition method. The proposed multi-module neural network (MMNN) is a hierarchical network with cascade connections, and consists of several modules which can detect specific features. MMNN is constructed based on the information processing of the visual nervous system such as a column structure in the Visual Area I and the hierarchical hypothesis of Hubel-Wiesel. As an example of a target object, we deal with human faces detection in this paper. This system consists of several modules in parallel which are trained to respond selectively to human face components: the eyes, the nose, and the mouth. At last, the face area is detected by integrating the outputs of previous cell layer. We carried out a lot of experiments using 100 images having complex background to conform the effectiveness of the proposed scheme. 83% of faces are detected correctly.

Original languageEnglish
Pages (from-to)4284-4289
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume5
Publication statusPublished - 1998 Dec 1
EventProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5) - San Diego, CA, USA
Duration: 1998 Oct 111998 Oct 14

    Fingerprint

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Hardware and Architecture

Cite this