Comparison of target Probabilistic Neural network (PNN) classification for beef and pork

Lestari Handayani, Jasril, Elvia Budianita, Winda Oktista, Rizki Hadi, Denanda Fattah, Rado Yendra, Ahmad Fudholi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This research focuses on image recognition of beef and pork. Beef as an example of halal food, while pork as haram food, especially for Muslims. This study used PNN classification and feature extraction methods. These images show some fundamental differences between pork and beef which based on colors and texture. Color was extracted by HSV model, otherwise texture extracted with 3 methods. These methods were Gabor, Principle Component Analysis (PCA) and Local Binary Pattern (LBP). Performance comparison of these methods was measured from the target accuracy of classification. Experiments conducted on 100 images of beef, pork and mixed, with attention to smoothing parameter (spread value/σ) in PNN and distribution data training and data testing. The best spread value obtained 10 for Gabor+HSV+PNN and LBP+HSV+PNN, but PCA+HSV+PNN was 108. The mixed meat was recognizable by PCA+HSV+PNN and LBP+HSV+PNN equal to 100%. The highest classification performance was achieved by PCA+HSV+PNN. This method can be used to distinguish between meat of permitted food and prohibited food. Mixing pork with beef would be prohibited food for Muslims and other peoples.

Original languageEnglish
Pages (from-to)2753-2760
Number of pages8
JournalJournal of Theoretical and Applied Information Technology
Volume95
Issue number12
Publication statusPublished - 30 Jun 2017

Fingerprint

Probabilistic Neural Network
Beef
Neural networks
Principle Component Analysis
Target
Meats
Binary
Texture
Textures
Color
Image recognition
Image Recognition
Smoothing Parameter
Network Analysis
Data Distribution
Performance Comparison
Feature Extraction
Feature extraction
Testing

Keywords

  • Image recognition
  • Local Binary Pattern (LBP)
  • Principle Component Analysis (PCA)

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Comparison of target Probabilistic Neural network (PNN) classification for beef and pork. / Handayani, Lestari; Jasril; Budianita, Elvia; Oktista, Winda; Hadi, Rizki; Fattah, Denanda; Yendra, Rado; Fudholi, Ahmad.

In: Journal of Theoretical and Applied Information Technology, Vol. 95, No. 12, 30.06.2017, p. 2753-2760.

Research output: Contribution to journalArticle

Handayani, L, Jasril, Budianita, E, Oktista, W, Hadi, R, Fattah, D, Yendra, R & Fudholi, A 2017, 'Comparison of target Probabilistic Neural network (PNN) classification for beef and pork', Journal of Theoretical and Applied Information Technology, vol. 95, no. 12, pp. 2753-2760.
Handayani L, Jasril, Budianita E, Oktista W, Hadi R, Fattah D et al. Comparison of target Probabilistic Neural network (PNN) classification for beef and pork. Journal of Theoretical and Applied Information Technology. 2017 Jun 30;95(12):2753-2760.
Handayani, Lestari ; Jasril ; Budianita, Elvia ; Oktista, Winda ; Hadi, Rizki ; Fattah, Denanda ; Yendra, Rado ; Fudholi, Ahmad. / Comparison of target Probabilistic Neural network (PNN) classification for beef and pork. In: Journal of Theoretical and Applied Information Technology. 2017 ; Vol. 95, No. 12. pp. 2753-2760.
@article{ee47f02d42fe49a7bc46dba7a49ce84d,
title = "Comparison of target Probabilistic Neural network (PNN) classification for beef and pork",
abstract = "This research focuses on image recognition of beef and pork. Beef as an example of halal food, while pork as haram food, especially for Muslims. This study used PNN classification and feature extraction methods. These images show some fundamental differences between pork and beef which based on colors and texture. Color was extracted by HSV model, otherwise texture extracted with 3 methods. These methods were Gabor, Principle Component Analysis (PCA) and Local Binary Pattern (LBP). Performance comparison of these methods was measured from the target accuracy of classification. Experiments conducted on 100 images of beef, pork and mixed, with attention to smoothing parameter (spread value/σ) in PNN and distribution data training and data testing. The best spread value obtained 10 for Gabor+HSV+PNN and LBP+HSV+PNN, but PCA+HSV+PNN was 108. The mixed meat was recognizable by PCA+HSV+PNN and LBP+HSV+PNN equal to 100{\%}. The highest classification performance was achieved by PCA+HSV+PNN. This method can be used to distinguish between meat of permitted food and prohibited food. Mixing pork with beef would be prohibited food for Muslims and other peoples.",
keywords = "Image recognition, Local Binary Pattern (LBP), Principle Component Analysis (PCA)",
author = "Lestari Handayani and Jasril and Elvia Budianita and Winda Oktista and Rizki Hadi and Denanda Fattah and Rado Yendra and Ahmad Fudholi",
year = "2017",
month = "6",
day = "30",
language = "English",
volume = "95",
pages = "2753--2760",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "12",

}

TY - JOUR

T1 - Comparison of target Probabilistic Neural network (PNN) classification for beef and pork

AU - Handayani, Lestari

AU - Jasril,

AU - Budianita, Elvia

AU - Oktista, Winda

AU - Hadi, Rizki

AU - Fattah, Denanda

AU - Yendra, Rado

AU - Fudholi, Ahmad

PY - 2017/6/30

Y1 - 2017/6/30

N2 - This research focuses on image recognition of beef and pork. Beef as an example of halal food, while pork as haram food, especially for Muslims. This study used PNN classification and feature extraction methods. These images show some fundamental differences between pork and beef which based on colors and texture. Color was extracted by HSV model, otherwise texture extracted with 3 methods. These methods were Gabor, Principle Component Analysis (PCA) and Local Binary Pattern (LBP). Performance comparison of these methods was measured from the target accuracy of classification. Experiments conducted on 100 images of beef, pork and mixed, with attention to smoothing parameter (spread value/σ) in PNN and distribution data training and data testing. The best spread value obtained 10 for Gabor+HSV+PNN and LBP+HSV+PNN, but PCA+HSV+PNN was 108. The mixed meat was recognizable by PCA+HSV+PNN and LBP+HSV+PNN equal to 100%. The highest classification performance was achieved by PCA+HSV+PNN. This method can be used to distinguish between meat of permitted food and prohibited food. Mixing pork with beef would be prohibited food for Muslims and other peoples.

AB - This research focuses on image recognition of beef and pork. Beef as an example of halal food, while pork as haram food, especially for Muslims. This study used PNN classification and feature extraction methods. These images show some fundamental differences between pork and beef which based on colors and texture. Color was extracted by HSV model, otherwise texture extracted with 3 methods. These methods were Gabor, Principle Component Analysis (PCA) and Local Binary Pattern (LBP). Performance comparison of these methods was measured from the target accuracy of classification. Experiments conducted on 100 images of beef, pork and mixed, with attention to smoothing parameter (spread value/σ) in PNN and distribution data training and data testing. The best spread value obtained 10 for Gabor+HSV+PNN and LBP+HSV+PNN, but PCA+HSV+PNN was 108. The mixed meat was recognizable by PCA+HSV+PNN and LBP+HSV+PNN equal to 100%. The highest classification performance was achieved by PCA+HSV+PNN. This method can be used to distinguish between meat of permitted food and prohibited food. Mixing pork with beef would be prohibited food for Muslims and other peoples.

KW - Image recognition

KW - Local Binary Pattern (LBP)

KW - Principle Component Analysis (PCA)

UR - http://www.scopus.com/inward/record.url?scp=85021760557&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021760557&partnerID=8YFLogxK

M3 - Article

VL - 95

SP - 2753

EP - 2760

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 12

ER -