Real-time waste paper grading using CBR approach

Mohammad Osiur Rahman, Aini Hussain, Edgar Scavino, Hannan M A, Hassan Basri

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The popularity of optical paper sorting systems has increased because of inadequate throughput of mechanical paper sorting systems. However, the implementation of existing optical methods is still complex, expensive and only able to segregate two types of paper at one time. Moreover, no image processing or intelligent techniques were used to extract the features from the paper objects. This research attempts to develop a smart vision sensing system that is able to identify waste paper grade using case-based reasoning. In order to construct the reference template database, the mode and energy of the region-of-interest in the paper object image are considered. The paper grade is identified based on the maximum occurrence of a specific reference template in the paper object image. The classification success rates with window size 3 × 3 pixels for white paper, old newsprint paper and old corrugated cardboard are 94%, 92% and 98%, respectively, while the achieved average classification success rate is 95.17%. This remarkable achievement is possible due to the accurate identification and dynamic sorting of all grades of papers. This method is clearly superior to other existing techniques in terms of throughput, performance in identification, adaptability with new paper grades and cost of implementation.

Original languageEnglish
Pages (from-to)471-488
Number of pages18
JournalInternational Journal of Innovative Computing, Information and Control
Volume8
Issue number1 A
Publication statusPublished - Jan 2012

Fingerprint

Waste paper
Grading
Sorting
Real-time
Template
Throughput
Newsprint
Case based reasoning
Case-based Reasoning
Region of Interest
Adaptability
Image Processing
Image processing
Sensing
Pixel
Pixels
Costs
Energy
Object

Keywords

  • Grades of paper
  • Template matching
  • Waste paper sorting

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Information Systems
  • Software
  • Theoretical Computer Science

Cite this

Real-time waste paper grading using CBR approach. / Rahman, Mohammad Osiur; Hussain, Aini; Scavino, Edgar; M A, Hannan; Basri, Hassan.

In: International Journal of Innovative Computing, Information and Control, Vol. 8, No. 1 A, 01.2012, p. 471-488.

Research output: Contribution to journalArticle

Rahman, Mohammad Osiur ; Hussain, Aini ; Scavino, Edgar ; M A, Hannan ; Basri, Hassan. / Real-time waste paper grading using CBR approach. In: International Journal of Innovative Computing, Information and Control. 2012 ; Vol. 8, No. 1 A. pp. 471-488.
@article{cb9efa04da97412898ee8683e4ac362f,
title = "Real-time waste paper grading using CBR approach",
abstract = "The popularity of optical paper sorting systems has increased because of inadequate throughput of mechanical paper sorting systems. However, the implementation of existing optical methods is still complex, expensive and only able to segregate two types of paper at one time. Moreover, no image processing or intelligent techniques were used to extract the features from the paper objects. This research attempts to develop a smart vision sensing system that is able to identify waste paper grade using case-based reasoning. In order to construct the reference template database, the mode and energy of the region-of-interest in the paper object image are considered. The paper grade is identified based on the maximum occurrence of a specific reference template in the paper object image. The classification success rates with window size 3 × 3 pixels for white paper, old newsprint paper and old corrugated cardboard are 94{\%}, 92{\%} and 98{\%}, respectively, while the achieved average classification success rate is 95.17{\%}. This remarkable achievement is possible due to the accurate identification and dynamic sorting of all grades of papers. This method is clearly superior to other existing techniques in terms of throughput, performance in identification, adaptability with new paper grades and cost of implementation.",
keywords = "Grades of paper, Template matching, Waste paper sorting",
author = "Rahman, {Mohammad Osiur} and Aini Hussain and Edgar Scavino and {M A}, Hannan and Hassan Basri",
year = "2012",
month = "1",
language = "English",
volume = "8",
pages = "471--488",
journal = "International Journal of Innovative Computing, Information and Control",
issn = "1349-4198",
publisher = "IJICIC Editorial Office",
number = "1 A",

}

TY - JOUR

T1 - Real-time waste paper grading using CBR approach

AU - Rahman, Mohammad Osiur

AU - Hussain, Aini

AU - Scavino, Edgar

AU - M A, Hannan

AU - Basri, Hassan

PY - 2012/1

Y1 - 2012/1

N2 - The popularity of optical paper sorting systems has increased because of inadequate throughput of mechanical paper sorting systems. However, the implementation of existing optical methods is still complex, expensive and only able to segregate two types of paper at one time. Moreover, no image processing or intelligent techniques were used to extract the features from the paper objects. This research attempts to develop a smart vision sensing system that is able to identify waste paper grade using case-based reasoning. In order to construct the reference template database, the mode and energy of the region-of-interest in the paper object image are considered. The paper grade is identified based on the maximum occurrence of a specific reference template in the paper object image. The classification success rates with window size 3 × 3 pixels for white paper, old newsprint paper and old corrugated cardboard are 94%, 92% and 98%, respectively, while the achieved average classification success rate is 95.17%. This remarkable achievement is possible due to the accurate identification and dynamic sorting of all grades of papers. This method is clearly superior to other existing techniques in terms of throughput, performance in identification, adaptability with new paper grades and cost of implementation.

AB - The popularity of optical paper sorting systems has increased because of inadequate throughput of mechanical paper sorting systems. However, the implementation of existing optical methods is still complex, expensive and only able to segregate two types of paper at one time. Moreover, no image processing or intelligent techniques were used to extract the features from the paper objects. This research attempts to develop a smart vision sensing system that is able to identify waste paper grade using case-based reasoning. In order to construct the reference template database, the mode and energy of the region-of-interest in the paper object image are considered. The paper grade is identified based on the maximum occurrence of a specific reference template in the paper object image. The classification success rates with window size 3 × 3 pixels for white paper, old newsprint paper and old corrugated cardboard are 94%, 92% and 98%, respectively, while the achieved average classification success rate is 95.17%. This remarkable achievement is possible due to the accurate identification and dynamic sorting of all grades of papers. This method is clearly superior to other existing techniques in terms of throughput, performance in identification, adaptability with new paper grades and cost of implementation.

KW - Grades of paper

KW - Template matching

KW - Waste paper sorting

UR - http://www.scopus.com/inward/record.url?scp=84856950851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856950851&partnerID=8YFLogxK

M3 - Article

VL - 8

SP - 471

EP - 488

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

SN - 1349-4198

IS - 1 A

ER -