Weakly-supervised learning approach for potato defects segmentation. (October 2019)

• Record Type: Journal Article
• Authors: Marino, Sofia; Beauseroy, Pierre; Smolarz, André
• Is Part Of: Engineering applications of artificial intelligence. Volume 85(2019)
• Page Start: 337
• Page End: 346
• Publication Date: 2019-10
• Subjects: Weakly-supervised segmentation -- Convolutional neural networks -- Potato classification -- Disease detection -- Defect detection -- Agricultural applications; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2019.06.024
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Rigorous quality analysis of potatoes is essential to define their market price. Manual approaches to detect skin defects of this tuber are laborious, subjective and time-consuming. In this paper, we introduce a weakly-supervised learning method to classify, localize and segment potato defects to automate the quality control task. A large and diversified image-level labeled dataset is created including potatoes from six different classes: healthy, damaged, greening, black dot, common scab and black scurf. A convolutional neural network (CNN) is trained to achieve the classification task. Then, we leverage the discriminative regions that appear in the activation maps of the trained CNN to localize the classified defect. A coarse-to-fine segmentation method is proposed to obtain a more precise defect size. Based on this segmentation, a classification according to the severity of the defect is done, showing the importance of the segmentation phase. Experimental results demonstrate that CNN outperforms conventional classifiers. At a final stage, a multi-label multi-class dataset is used to evaluate the whole system, achieving an average precision of 0.91 and an average recall of 0.90.