TY - GEN
T1 - Defects Detection in Fruits and Vegetables Using Image Processing and Soft Computing Techniques
AU - Narendra, V. G.
AU - Pinto, Ancilla J.
N1 - Publisher Copyright:
© 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2021
Y1 - 2021
N2 - In the science of agriculture, automation helps to improve the country’s quality, economic growth, and productivity. The fruit and vegetable variety influences both the export market and quality assessment. The market value of vegetables and fruits is a key sensory feature, which affects consumer preference and choice. Although the process of sorting and grading can be performed manually, it is inaccurate, time-consuming, unreliable, subjective, hard, expensive, and easily influenced by the surroundings. Therefore, intelligent classification technique is necessary for vegetables and fruits, along with the system for defect detection. This research aims to detect external defects in vegetables and fruits-based on morphology, color, and texture. In this proposed work, the various algorithms proposed for quality inspection, including external fruit defects (i.e., RGB to L*a*b* color conversion and defective area calculation methods are used to recognize errors in both apple and orange) and vegetables (i.e., K-means cluster and defective area calculation methods are used to identify defective tomatoes from their color), several image techniques are used. The overall accuracy achieved in quality analysis and defect detection is 87% (apple: 83%; orange: 93%; and tomatoes: 83%) of defective fruits (apple and orange) and vegetables (tomatoes).
AB - In the science of agriculture, automation helps to improve the country’s quality, economic growth, and productivity. The fruit and vegetable variety influences both the export market and quality assessment. The market value of vegetables and fruits is a key sensory feature, which affects consumer preference and choice. Although the process of sorting and grading can be performed manually, it is inaccurate, time-consuming, unreliable, subjective, hard, expensive, and easily influenced by the surroundings. Therefore, intelligent classification technique is necessary for vegetables and fruits, along with the system for defect detection. This research aims to detect external defects in vegetables and fruits-based on morphology, color, and texture. In this proposed work, the various algorithms proposed for quality inspection, including external fruit defects (i.e., RGB to L*a*b* color conversion and defective area calculation methods are used to recognize errors in both apple and orange) and vegetables (i.e., K-means cluster and defective area calculation methods are used to identify defective tomatoes from their color), several image techniques are used. The overall accuracy achieved in quality analysis and defect detection is 87% (apple: 83%; orange: 93%; and tomatoes: 83%) of defective fruits (apple and orange) and vegetables (tomatoes).
UR - http://www.scopus.com/inward/record.url?scp=85097098661&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097098661&partnerID=8YFLogxK
U2 - 10.1007/978-981-15-8603-3_29
DO - 10.1007/978-981-15-8603-3_29
M3 - Conference contribution
AN - SCOPUS:85097098661
SN - 9789811586026
T3 - Advances in Intelligent Systems and Computing
SP - 325
EP - 337
BT - Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020
A2 - Nigdeli, Sinan Melih
A2 - Bekdas, Gebrail
A2 - Kim, Joong Hoon
A2 - Yadav, Anupam
PB - Springer Science and Business Media Deutschland GmbH
T2 - 6th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2020
Y2 - 22 April 2020 through 24 April 2020
ER -
