Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection

Hai Vu, Christos Tachtatzis, Paul Murray, David Harle, Trung Kien Dao, Robert Atkinson, Thi-Lan Le, Ivan Andonovic, Stephen Marshall

Research output: Contribution to conferencePaper

Abstract

A conventional method to inspect the varietal purity of rice seeds is based on evaluating human visual inspection where a random sample is drawn from a batch. This is a tedious, laborious, time consuming and extremely inefficient task. This paper presents an automatic rice seed inspection method using Hyperspectral imaging and machine learning, to automatically detect unwanted seeds from other varieties which may be contained in a batch. Hyperspectral image data from Near-infrared (NIR) and Visible cameras are acquired for six common rice seed varieties. The results of applying two classifiers are presented, a Support Vector Machine (SVM) and a Random Forest (RF), where each consists of six one-versus-rest binary classifiers. The results show that combining spectral and shape- based features derived from the rice seeds, increase precision of the multi-label classification to 84% compared 74% when only visual features are used.

Conference

Conference12th IEEE-RIVF International Conference on Computing and Communication Technologies
Abbreviated titleIEEE-RIVF
CountryViet Nam
CityHanoi
Period7/11/169/11/16
Internet address

Fingerprint

Imaging systems
Seed
Inspection
Classifiers
Support vector machines
Learning systems
Labels
Cameras
Hyperspectral imaging
Infrared radiation

Keywords

  • rice seed
  • inspection
  • hyperspectral imaging

Cite this

Vu, H., Tachtatzis, C., Murray, P., Harle, D., Dao, T. K., Atkinson, R., ... Marshall, S. (Accepted/In press). Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection. Paper presented at 12th IEEE-RIVF International Conference on Computing and Communication Technologies, Hanoi, Viet Nam.
Vu, Hai ; Tachtatzis, Christos ; Murray, Paul ; Harle, David ; Dao, Trung Kien ; Atkinson, Robert ; Le, Thi-Lan ; Andonovic, Ivan ; Marshall, Stephen. / Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection. Paper presented at 12th IEEE-RIVF International Conference on Computing and Communication Technologies, Hanoi, Viet Nam.6 p.
@conference{c7e719dbb3f641979006ff949862a569,
title = "Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection",
abstract = "A conventional method to inspect the varietal purity of rice seeds is based on evaluating human visual inspection where a random sample is drawn from a batch. This is a tedious, laborious, time consuming and extremely inefficient task. This paper presents an automatic rice seed inspection method using Hyperspectral imaging and machine learning, to automatically detect unwanted seeds from other varieties which may be contained in a batch. Hyperspectral image data from Near-infrared (NIR) and Visible cameras are acquired for six common rice seed varieties. The results of applying two classifiers are presented, a Support Vector Machine (SVM) and a Random Forest (RF), where each consists of six one-versus-rest binary classifiers. The results show that combining spectral and shape- based features derived from the rice seeds, increase precision of the multi-label classification to 84{\%} compared 74{\%} when only visual features are used.",
keywords = "rice seed, inspection, hyperspectral imaging",
author = "Hai Vu and Christos Tachtatzis and Paul Murray and David Harle and Dao, {Trung Kien} and Robert Atkinson and Thi-Lan Le and Ivan Andonovic and Stephen Marshall",
note = "{\circledC} 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 12th IEEE-RIVF International Conference on Computing and Communication Technologies, IEEE-RIVF ; Conference date: 07-11-2016 Through 09-11-2016",
year = "2016",
month = "8",
day = "30",
language = "English",
url = "http://rivf2016.tlu.edu.vn/",

}

Vu, H, Tachtatzis, C, Murray, P, Harle, D, Dao, TK, Atkinson, R, Le, T-L, Andonovic, I & Marshall, S 2016, 'Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection' Paper presented at 12th IEEE-RIVF International Conference on Computing and Communication Technologies, Hanoi, Viet Nam, 7/11/16 - 9/11/16, .

Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection. / Vu, Hai; Tachtatzis, Christos; Murray, Paul; Harle, David; Dao, Trung Kien; Atkinson, Robert; Le, Thi-Lan; Andonovic, Ivan; Marshall, Stephen.

2016. Paper presented at 12th IEEE-RIVF International Conference on Computing and Communication Technologies, Hanoi, Viet Nam.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection

AU - Vu, Hai

AU - Tachtatzis, Christos

AU - Murray, Paul

AU - Harle, David

AU - Dao, Trung Kien

AU - Atkinson, Robert

AU - Le, Thi-Lan

AU - Andonovic, Ivan

AU - Marshall, Stephen

N1 - © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2016/8/30

Y1 - 2016/8/30

N2 - A conventional method to inspect the varietal purity of rice seeds is based on evaluating human visual inspection where a random sample is drawn from a batch. This is a tedious, laborious, time consuming and extremely inefficient task. This paper presents an automatic rice seed inspection method using Hyperspectral imaging and machine learning, to automatically detect unwanted seeds from other varieties which may be contained in a batch. Hyperspectral image data from Near-infrared (NIR) and Visible cameras are acquired for six common rice seed varieties. The results of applying two classifiers are presented, a Support Vector Machine (SVM) and a Random Forest (RF), where each consists of six one-versus-rest binary classifiers. The results show that combining spectral and shape- based features derived from the rice seeds, increase precision of the multi-label classification to 84% compared 74% when only visual features are used.

AB - A conventional method to inspect the varietal purity of rice seeds is based on evaluating human visual inspection where a random sample is drawn from a batch. This is a tedious, laborious, time consuming and extremely inefficient task. This paper presents an automatic rice seed inspection method using Hyperspectral imaging and machine learning, to automatically detect unwanted seeds from other varieties which may be contained in a batch. Hyperspectral image data from Near-infrared (NIR) and Visible cameras are acquired for six common rice seed varieties. The results of applying two classifiers are presented, a Support Vector Machine (SVM) and a Random Forest (RF), where each consists of six one-versus-rest binary classifiers. The results show that combining spectral and shape- based features derived from the rice seeds, increase precision of the multi-label classification to 84% compared 74% when only visual features are used.

KW - rice seed

KW - inspection

KW - hyperspectral imaging

UR - http://rivf2016.tlu.edu.vn/

UR - http://ieeexplore.ieee.org/Xplore/home.jsp

M3 - Paper

ER -

Vu H, Tachtatzis C, Murray P, Harle D, Dao TK, Atkinson R et al. Spatial and spectral features utilization on a hyperspectral imaging system for rice seed varietal purity inspection. 2016. Paper presented at 12th IEEE-RIVF International Conference on Computing and Communication Technologies, Hanoi, Viet Nam.