Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques

Authors:
Juan Gómez-Sanchis;José D. Martín-Guerrero;Emilio Soria-Olivas;Marcelino Martínez-Sober;Rafael Magdalena-Benedito;José Blasco
Affiliations:
Electronic Engineering Department, E.T.S.E, University of Valencia, C/Dr Moliner 50, 46100 Burjassot, Valencia, Spain;Electronic Engineering Department, E.T.S.E, University of Valencia, C/Dr Moliner 50, 46100 Burjassot, Valencia, Spain;Electronic Engineering Department, E.T.S.E, University of Valencia, C/Dr Moliner 50, 46100 Burjassot, Valencia, Spain;Electronic Engineering Department, E.T.S.E, University of Valencia, C/Dr Moliner 50, 46100 Burjassot, Valencia, Spain;Electronic Engineering Department, E.T.S.E, University of Valencia, C/Dr Moliner 50, 46100 Burjassot, Valencia, Spain;Centro de Agroingeniería. IVIA, Ctra. Moncada-Náquera, km. 5, 46113 Moncada, Valencia, Spain
Venue:
Expert Systems with Applications: An International Journal
Year:
2012

Citing 1
Cited 2

Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy

IEEE Transactions on Pattern Analysis and Machine Intelligence

Automatic recognition of quarantine citrus diseases

Expert Systems with Applications: An International Journal
A sequential machine vision procedure for assessing paper impurities

Computers in Industry

Quantified Score

Hi-index	12.05

Visualization

Abstract

Penicillium fungi are among the main defects that may affect the commercialization of citrus fruits. Economic losses in fruit production may become enormous if an early detection of that kind of fungi is not carried out. That early detection is usually based either on UltraViolet light carried out manually. This work presents a new approach based on hyperspectral imagery for defect segmentation. Both the physical device and the data processing (geometric corrections and band selection) are presented. Achieved results using classifiers based on Artificial Neural Networks and Decision Trees show an accuracy around 98%; it shows up the suitability of the proposed approach.