Paper Info
Title
Automatic characterisation of dye decolourisation in fungal strains using expert, traditional, and deep features
Abstract
Fungi have diverse biotechnological applications in, among others, agriculture, bioenergy generation, or remediation of polluted soil and water. In this context, culture media based on colour change in response to degradation of dyes are particularly relevant, but measuring dye decolourisation of fungal strains mainly relies on a visual and semiquantitative classification of colour intensity changes. Such a classification is a subjective, time-consuming, and difficult to reproduce process. In order to deal with these problems, we have performed a systematic evaluation of different image-classification approaches considering ad hoc expert features, traditional computer vision features, and transfer-learning features obtained from deep neural networks. Our results favour the transfer learning approach reaching an accuracy of 96.5% in the evaluated dataset. In this paper, we provide the first, at least up to the best of our knowledge, method to automatically characterise dye decolourisation level of fungal strains from images of inoculated plates.
Year
DOI
Venue
2019
10.1007/s00500-019-03832-8
Soft Computing
Keywords
Field
DocType
Fungal decolourisation, Image classification, Computer vision, Deep learning, Transfer learning
Pattern recognition,Computer science,Artificial intelligence,Deep learning,Contextual image classification,Deep neural networks,Machine learning
Journal
Volume
Issue
ISSN
23.0
23.0
1433-7479
Citations 
PageRank 
References 
1
0.35
21
Authors
7
Name
Order
Citations
PageRank
Marina Arredondo-Santoyo110.35
César Domínguez29518.93
Jónathan Heras39423.31
Eloy J. Mata4116.38
Vico Pascual55813.19
Mª Soledad Vázquez-Garcidueñas610.35
Gerardo Vázquez-Marrufo710.35