Visual processing and classification of items on a moving conveyor: A selective perception approach

H. Işil Bozma; Hülya Yalçin

doi:10.1016/S0736-5845(01)00035-7

Visual processing and classification of items on a moving conveyor: A selective perception approach

H. Işil Bozma^*, Hülya Yalçin

^*Corresponding author for this work

Bogazici University

Research output: Contribution to journal › Article › peer-review

28 Citations (Scopus)

Abstract

Many industrial applications require some sort of automated visual processing and classification of items placed on a moving conveyor. In this paper, we present a selective perception based approach to visual processing. The novelty of this approach is that instead of processing the whole image, only areas that are deemed "interesting" and hence calling for attention are analyzed. The attentional sequences thus constructed can then be used for a variety of tasks including shape determination. Since only a small portion of the whole image is processed, visual processing can be real-time and flexible without requiring special hardware. Two different applications based on this approach are described. In a defective item detection task, we explain in detail how attentional sequences can be used. As a second application, the approach has been implemented in an automated remote controller sorter in a TV manufacturing plant - thus confirming its practical applicability.

Original language	English
Pages (from-to)	125-133
Number of pages	9
Journal	Robotics and Computer-Integrated Manufacturing
Volume	18
Issue number	2
DOIs	https://doi.org/10.1016/S0736-5845(01)00035-7
Publication status	Published - Apr 2002
Externally published	Yes

Funding

This research has been supported in part by Boğaziçi University Research Fund grant #97HA201 and TÜBİTAK grant Misag-65, 1995. The project on the automated sorting of remote controllers has been made possible with cooperation of BEKO Elektronik A.Ş. İstanbul. S. Burak Göktürk has been a major contributor to the project. We also gratefully acknowledge the contributions of Ümit Baştuǧ, Metin Özdilek and the rest of the BEKO team to the mechanical design and implementation efforts. The authors also thank the anonymous readers for their suggestions regarding the improvement of the manuscript. This research has been supported in part by Boğaziçi University Research Fund Project grants ♯AF 96A0236, and ♯AF 96HA0222 and TÜBITAK grant Misag-65, 1995.

Funders	Funder number
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu	Misag-65
Boğaziçi Üniversitesi	♯AF 96A0236, AF 96HA0222, 97HA201

Keywords

2D shape description
Attentive systems
Classification
Computer vision
Selective perception
Visual processing

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/S0736-5845(01)00035-7

Cite this

@article{c573ef5cda9a438ea4fb08eb04e94b1e,

title = "Visual processing and classification of items on a moving conveyor: A selective perception approach",

abstract = "Many industrial applications require some sort of automated visual processing and classification of items placed on a moving conveyor. In this paper, we present a selective perception based approach to visual processing. The novelty of this approach is that instead of processing the whole image, only areas that are deemed {"}interesting{"} and hence calling for attention are analyzed. The attentional sequences thus constructed can then be used for a variety of tasks including shape determination. Since only a small portion of the whole image is processed, visual processing can be real-time and flexible without requiring special hardware. Two different applications based on this approach are described. In a defective item detection task, we explain in detail how attentional sequences can be used. As a second application, the approach has been implemented in an automated remote controller sorter in a TV manufacturing plant - thus confirming its practical applicability.",

keywords = "2D shape description, Attentive systems, Classification, Computer vision, Selective perception, Visual processing",

author = "Bozma, {H. I{\c s}il} and H{\"u}lya Yal{\c c}in",

year = "2002",

month = apr,

doi = "10.1016/S0736-5845(01)00035-7",

language = "English",

volume = "18",

pages = "125--133",

journal = "Robotics and Computer-Integrated Manufacturing",

issn = "0736-5845",

publisher = "Elsevier Ltd",

number = "2",

}

TY - JOUR

T1 - Visual processing and classification of items on a moving conveyor

T2 - A selective perception approach

AU - Bozma, H. Işil

AU - Yalçin, Hülya

PY - 2002/4

Y1 - 2002/4

N2 - Many industrial applications require some sort of automated visual processing and classification of items placed on a moving conveyor. In this paper, we present a selective perception based approach to visual processing. The novelty of this approach is that instead of processing the whole image, only areas that are deemed "interesting" and hence calling for attention are analyzed. The attentional sequences thus constructed can then be used for a variety of tasks including shape determination. Since only a small portion of the whole image is processed, visual processing can be real-time and flexible without requiring special hardware. Two different applications based on this approach are described. In a defective item detection task, we explain in detail how attentional sequences can be used. As a second application, the approach has been implemented in an automated remote controller sorter in a TV manufacturing plant - thus confirming its practical applicability.

AB - Many industrial applications require some sort of automated visual processing and classification of items placed on a moving conveyor. In this paper, we present a selective perception based approach to visual processing. The novelty of this approach is that instead of processing the whole image, only areas that are deemed "interesting" and hence calling for attention are analyzed. The attentional sequences thus constructed can then be used for a variety of tasks including shape determination. Since only a small portion of the whole image is processed, visual processing can be real-time and flexible without requiring special hardware. Two different applications based on this approach are described. In a defective item detection task, we explain in detail how attentional sequences can be used. As a second application, the approach has been implemented in an automated remote controller sorter in a TV manufacturing plant - thus confirming its practical applicability.

KW - 2D shape description

KW - Attentive systems

KW - Classification

KW - Computer vision

KW - Selective perception

KW - Visual processing

UR - http://www.scopus.com/inward/record.url?scp=0036535512&partnerID=8YFLogxK

U2 - 10.1016/S0736-5845(01)00035-7

DO - 10.1016/S0736-5845(01)00035-7

M3 - Article

AN - SCOPUS:0036535512

SN - 0736-5845

VL - 18

SP - 125

EP - 133

JO - Robotics and Computer-Integrated Manufacturing

JF - Robotics and Computer-Integrated Manufacturing

IS - 2

ER -

Visual processing and classification of items on a moving conveyor: A selective perception approach

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this