Automated visual inspection for surgical instruments based on spatial feature and K-Nearest neighbor algorithm

Murtadha Basil Abbas, Anton Satria Prabuwono, Siti Norul Huda Sheikh Abdullah, Rizuana Iqbal Hussain

Research output: Contribution to journalArticle

Abstract

Upon increasing number of computer usage in industries, the traditional methods and equipments of human subjective evaluations are gradually being replaced by the machine vision, which is a smart camera connected with computer based systems. It is called as Automated Visual Inspection System (AVIS). At current state, AVIS applications are mostly developed based on geometric and shape feature extraction methods. Unfortunately, that approach has some problems due to image scaling, illumination, noise and invariant issues. Therefore, the main objective of this research is to design spatial local feature transform for AVIS development. The AVIS methodology covers two parts: the first one is the hardware part which consists of webcam, source light and the conveyor belt while the software part comprising image processing based on the Bag-of-Words (BoW) model and object recognition based on K-Nearest Neighbor (K-NN) algorithm. Nine surgical instruments are used as the case study for the object recognition. This research is evaluated based on single and group classification technology. The obtained results show that the proposed AVIS work can achieve up to 92% and 89% of accuracy rate for individual and group classification in sequence.

Original languageEnglish
Pages (from-to)153-157
Number of pages5
JournalAdvanced Science Letters
Volume20
Issue number1
DOIs
Publication statusPublished - Jan 2014

Fingerprint

Surgical Instruments
Inspection
Nearest Neighbor
Computer Systems
Group Classification
Lighting
Research
Object recognition
Noise
Object Recognition
Industry
Software
Technology
Light
Equipment and Supplies
Subjective Evaluation
Shape Feature
Machine Vision
Local Features
system development

Keywords

  • Automatic visual inspection
  • K-Nearest neighbor
  • Spatial features
  • Surgical instruments

ASJC Scopus subject areas

  • Education
  • Health(social science)
  • Mathematics(all)
  • Energy(all)
  • Computer Science(all)
  • Environmental Science(all)
  • Engineering(all)

Cite this

Automated visual inspection for surgical instruments based on spatial feature and K-Nearest neighbor algorithm. / Abbas, Murtadha Basil; Prabuwono, Anton Satria; Sheikh Abdullah, Siti Norul Huda; Iqbal Hussain, Rizuana.

In: Advanced Science Letters, Vol. 20, No. 1, 01.2014, p. 153-157.

Research output: Contribution to journalArticle

@article{1692159d993742739ff52d3690f2554c,
title = "Automated visual inspection for surgical instruments based on spatial feature and K-Nearest neighbor algorithm",
abstract = "Upon increasing number of computer usage in industries, the traditional methods and equipments of human subjective evaluations are gradually being replaced by the machine vision, which is a smart camera connected with computer based systems. It is called as Automated Visual Inspection System (AVIS). At current state, AVIS applications are mostly developed based on geometric and shape feature extraction methods. Unfortunately, that approach has some problems due to image scaling, illumination, noise and invariant issues. Therefore, the main objective of this research is to design spatial local feature transform for AVIS development. The AVIS methodology covers two parts: the first one is the hardware part which consists of webcam, source light and the conveyor belt while the software part comprising image processing based on the Bag-of-Words (BoW) model and object recognition based on K-Nearest Neighbor (K-NN) algorithm. Nine surgical instruments are used as the case study for the object recognition. This research is evaluated based on single and group classification technology. The obtained results show that the proposed AVIS work can achieve up to 92{\%} and 89{\%} of accuracy rate for individual and group classification in sequence.",
keywords = "Automatic visual inspection, K-Nearest neighbor, Spatial features, Surgical instruments",
author = "Abbas, {Murtadha Basil} and Prabuwono, {Anton Satria} and {Sheikh Abdullah}, {Siti Norul Huda} and {Iqbal Hussain}, Rizuana",
year = "2014",
month = "1",
doi = "10.1166/asl.2014.5272",
language = "English",
volume = "20",
pages = "153--157",
journal = "Advanced Science Letters",
issn = "1936-6612",
publisher = "American Scientific Publishers",
number = "1",

}

TY - JOUR

T1 - Automated visual inspection for surgical instruments based on spatial feature and K-Nearest neighbor algorithm

AU - Abbas, Murtadha Basil

AU - Prabuwono, Anton Satria

AU - Sheikh Abdullah, Siti Norul Huda

AU - Iqbal Hussain, Rizuana

PY - 2014/1

Y1 - 2014/1

N2 - Upon increasing number of computer usage in industries, the traditional methods and equipments of human subjective evaluations are gradually being replaced by the machine vision, which is a smart camera connected with computer based systems. It is called as Automated Visual Inspection System (AVIS). At current state, AVIS applications are mostly developed based on geometric and shape feature extraction methods. Unfortunately, that approach has some problems due to image scaling, illumination, noise and invariant issues. Therefore, the main objective of this research is to design spatial local feature transform for AVIS development. The AVIS methodology covers two parts: the first one is the hardware part which consists of webcam, source light and the conveyor belt while the software part comprising image processing based on the Bag-of-Words (BoW) model and object recognition based on K-Nearest Neighbor (K-NN) algorithm. Nine surgical instruments are used as the case study for the object recognition. This research is evaluated based on single and group classification technology. The obtained results show that the proposed AVIS work can achieve up to 92% and 89% of accuracy rate for individual and group classification in sequence.

AB - Upon increasing number of computer usage in industries, the traditional methods and equipments of human subjective evaluations are gradually being replaced by the machine vision, which is a smart camera connected with computer based systems. It is called as Automated Visual Inspection System (AVIS). At current state, AVIS applications are mostly developed based on geometric and shape feature extraction methods. Unfortunately, that approach has some problems due to image scaling, illumination, noise and invariant issues. Therefore, the main objective of this research is to design spatial local feature transform for AVIS development. The AVIS methodology covers two parts: the first one is the hardware part which consists of webcam, source light and the conveyor belt while the software part comprising image processing based on the Bag-of-Words (BoW) model and object recognition based on K-Nearest Neighbor (K-NN) algorithm. Nine surgical instruments are used as the case study for the object recognition. This research is evaluated based on single and group classification technology. The obtained results show that the proposed AVIS work can achieve up to 92% and 89% of accuracy rate for individual and group classification in sequence.

KW - Automatic visual inspection

KW - K-Nearest neighbor

KW - Spatial features

KW - Surgical instruments

UR - http://www.scopus.com/inward/record.url?scp=84887910968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887910968&partnerID=8YFLogxK

U2 - 10.1166/asl.2014.5272

DO - 10.1166/asl.2014.5272

M3 - Article

AN - SCOPUS:84887910968

VL - 20

SP - 153

EP - 157

JO - Advanced Science Letters

JF - Advanced Science Letters

SN - 1936-6612

IS - 1

ER -