Adaptive integrated image segmentation and object recognition

Bir Bhanu, Jing Peng

Research output: Contribution to journalArticle

84 Citations (Scopus)

Abstract

This paper presents a general approach to image segmentation and object recognition that can adapt the image segmentation algorithm parameters to the changing environmental conditions. Segmentation parameters are represented by a team of generalized stochastic learning automata and learned using connectionist reinforcement learning techniques. The edge-border coincidence measure is first used as reinforcement for segmentation evaluation to reduce computational expenses associated with model matching during the early stage of adaptation. This measure alone, however, can not reliably predict the outcome of object recognition. Therefore, it is used in conjunction with model matching where the matching confidence is used as a reinforcement signal to provide optimal segmentation evaluation in a closed-loop object recognition system. The adaptation alternates between global and local segmentation processes in order to achieve optimal recognition performance. Results are presented for both indoor and outdoor color images where the performance improvement over time is shown for both image segmentation and object recognition.

Original languageEnglish
Pages (from-to)427-441
Number of pages15
JournalIEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
Volume30
Issue number4
DOIs
StatePublished - 1 Nov 2000

Fingerprint

Object recognition
Image segmentation
Reinforcement
Reinforcement learning
Color

Cite this

@article{0b617ffc08b742e489cd2cde3cfa3e1d,
title = "Adaptive integrated image segmentation and object recognition",
abstract = "This paper presents a general approach to image segmentation and object recognition that can adapt the image segmentation algorithm parameters to the changing environmental conditions. Segmentation parameters are represented by a team of generalized stochastic learning automata and learned using connectionist reinforcement learning techniques. The edge-border coincidence measure is first used as reinforcement for segmentation evaluation to reduce computational expenses associated with model matching during the early stage of adaptation. This measure alone, however, can not reliably predict the outcome of object recognition. Therefore, it is used in conjunction with model matching where the matching confidence is used as a reinforcement signal to provide optimal segmentation evaluation in a closed-loop object recognition system. The adaptation alternates between global and local segmentation processes in order to achieve optimal recognition performance. Results are presented for both indoor and outdoor color images where the performance improvement over time is shown for both image segmentation and object recognition.",
author = "Bir Bhanu and Jing Peng",
year = "2000",
month = "11",
day = "1",
doi = "10.1109/5326.897070",
language = "English",
volume = "30",
pages = "427--441",
journal = "IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews",
issn = "1094-6977",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Adaptive integrated image segmentation and object recognition. / Bhanu, Bir; Peng, Jing.

In: IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, Vol. 30, No. 4, 01.11.2000, p. 427-441.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Adaptive integrated image segmentation and object recognition

AU - Bhanu, Bir

AU - Peng, Jing

PY - 2000/11/1

Y1 - 2000/11/1

N2 - This paper presents a general approach to image segmentation and object recognition that can adapt the image segmentation algorithm parameters to the changing environmental conditions. Segmentation parameters are represented by a team of generalized stochastic learning automata and learned using connectionist reinforcement learning techniques. The edge-border coincidence measure is first used as reinforcement for segmentation evaluation to reduce computational expenses associated with model matching during the early stage of adaptation. This measure alone, however, can not reliably predict the outcome of object recognition. Therefore, it is used in conjunction with model matching where the matching confidence is used as a reinforcement signal to provide optimal segmentation evaluation in a closed-loop object recognition system. The adaptation alternates between global and local segmentation processes in order to achieve optimal recognition performance. Results are presented for both indoor and outdoor color images where the performance improvement over time is shown for both image segmentation and object recognition.

AB - This paper presents a general approach to image segmentation and object recognition that can adapt the image segmentation algorithm parameters to the changing environmental conditions. Segmentation parameters are represented by a team of generalized stochastic learning automata and learned using connectionist reinforcement learning techniques. The edge-border coincidence measure is first used as reinforcement for segmentation evaluation to reduce computational expenses associated with model matching during the early stage of adaptation. This measure alone, however, can not reliably predict the outcome of object recognition. Therefore, it is used in conjunction with model matching where the matching confidence is used as a reinforcement signal to provide optimal segmentation evaluation in a closed-loop object recognition system. The adaptation alternates between global and local segmentation processes in order to achieve optimal recognition performance. Results are presented for both indoor and outdoor color images where the performance improvement over time is shown for both image segmentation and object recognition.

UR - http://www.scopus.com/inward/record.url?scp=0034313634&partnerID=8YFLogxK

U2 - 10.1109/5326.897070

DO - 10.1109/5326.897070

M3 - Article

AN - SCOPUS:0034313634

VL - 30

SP - 427

EP - 441

JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

SN - 1094-6977

IS - 4

ER -