Multipurpose image recognition based on active search and adaptive fuzzy inference neural network

Hitoshi Iyatomi, Masafumi Hagiwara

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a versatile image recognition method, combining conventional pattern matching and a learning system. The proposed system first quickly determines candidate regions containing the target object in the image, and then examines the result by using the learning system. In the pattern matching, "active search" is used, which quickly extracts the target object using multiple two-dimensional reference images. As a learning system, an adaptive fuzzy inference neural network (AFINN) is used, which can perform knowledge processing. The AFINN automatically constructs the inference model, such as the selection of the necessary input information, and automatically acquires the inference rules through learning. Consequently, by applying the AFINN to the image recognition problem, highly versatile object recognition is realized without requiring explicit knowledge for recognition. The proposed system can be applied to a wide range of problems, since diversified objects can be recognized by simply modifying the registered reference images. In this paper, the method is applied to a sample problem, consisting of an image of the laboratory containing various objects, such as computers, monitors, and chairs, and it is verified that high recognition accuracy can be realized.

Original languageEnglish
Pages (from-to)69-79
Number of pages11
JournalSystems and Computers in Japan
Volume37
Issue number3
DOIs
Publication statusPublished - 2006 Mar

Fingerprint

Image recognition
Image Recognition
Fuzzy Inference
Fuzzy inference
Learning systems
Learning Systems
Pattern matching
Neural Networks
Neural networks
Pattern Matching
Computer monitors
Object recognition
Target
Inference Rules
Object Recognition
Monitor
Processing
Necessary
Object
Range of data

Keywords

  • Active search
  • Fuzzy inference
  • Image recognition
  • Neural network

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Multipurpose image recognition based on active search and adaptive fuzzy inference neural network. / Iyatomi, Hitoshi; Hagiwara, Masafumi.

In: Systems and Computers in Japan, Vol. 37, No. 3, 03.2006, p. 69-79.

Research output: Contribution to journalArticle

@article{7dad10cefdb94e0a9686bbd180e5ee30,
title = "Multipurpose image recognition based on active search and adaptive fuzzy inference neural network",
abstract = "This paper presents a versatile image recognition method, combining conventional pattern matching and a learning system. The proposed system first quickly determines candidate regions containing the target object in the image, and then examines the result by using the learning system. In the pattern matching, {"}active search{"} is used, which quickly extracts the target object using multiple two-dimensional reference images. As a learning system, an adaptive fuzzy inference neural network (AFINN) is used, which can perform knowledge processing. The AFINN automatically constructs the inference model, such as the selection of the necessary input information, and automatically acquires the inference rules through learning. Consequently, by applying the AFINN to the image recognition problem, highly versatile object recognition is realized without requiring explicit knowledge for recognition. The proposed system can be applied to a wide range of problems, since diversified objects can be recognized by simply modifying the registered reference images. In this paper, the method is applied to a sample problem, consisting of an image of the laboratory containing various objects, such as computers, monitors, and chairs, and it is verified that high recognition accuracy can be realized.",
keywords = "Active search, Fuzzy inference, Image recognition, Neural network",
author = "Hitoshi Iyatomi and Masafumi Hagiwara",
year = "2006",
month = "3",
doi = "10.1002/scj.20269",
language = "English",
volume = "37",
pages = "69--79",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "3",

}

TY - JOUR

T1 - Multipurpose image recognition based on active search and adaptive fuzzy inference neural network

AU - Iyatomi, Hitoshi

AU - Hagiwara, Masafumi

PY - 2006/3

Y1 - 2006/3

N2 - This paper presents a versatile image recognition method, combining conventional pattern matching and a learning system. The proposed system first quickly determines candidate regions containing the target object in the image, and then examines the result by using the learning system. In the pattern matching, "active search" is used, which quickly extracts the target object using multiple two-dimensional reference images. As a learning system, an adaptive fuzzy inference neural network (AFINN) is used, which can perform knowledge processing. The AFINN automatically constructs the inference model, such as the selection of the necessary input information, and automatically acquires the inference rules through learning. Consequently, by applying the AFINN to the image recognition problem, highly versatile object recognition is realized without requiring explicit knowledge for recognition. The proposed system can be applied to a wide range of problems, since diversified objects can be recognized by simply modifying the registered reference images. In this paper, the method is applied to a sample problem, consisting of an image of the laboratory containing various objects, such as computers, monitors, and chairs, and it is verified that high recognition accuracy can be realized.

AB - This paper presents a versatile image recognition method, combining conventional pattern matching and a learning system. The proposed system first quickly determines candidate regions containing the target object in the image, and then examines the result by using the learning system. In the pattern matching, "active search" is used, which quickly extracts the target object using multiple two-dimensional reference images. As a learning system, an adaptive fuzzy inference neural network (AFINN) is used, which can perform knowledge processing. The AFINN automatically constructs the inference model, such as the selection of the necessary input information, and automatically acquires the inference rules through learning. Consequently, by applying the AFINN to the image recognition problem, highly versatile object recognition is realized without requiring explicit knowledge for recognition. The proposed system can be applied to a wide range of problems, since diversified objects can be recognized by simply modifying the registered reference images. In this paper, the method is applied to a sample problem, consisting of an image of the laboratory containing various objects, such as computers, monitors, and chairs, and it is verified that high recognition accuracy can be realized.

KW - Active search

KW - Fuzzy inference

KW - Image recognition

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=33644909055&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33644909055&partnerID=8YFLogxK

U2 - 10.1002/scj.20269

DO - 10.1002/scj.20269

M3 - Article

AN - SCOPUS:33644909055

VL - 37

SP - 69

EP - 79

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 3

ER -