Potato defects classification and localization with convolutional neural networks
Autor: | Sofia Marino, André Smolarz, Pierre Beauseroy |
---|---|
Přispěvatelé: | Laboratoire Modélisation et Sûreté des Systèmes (LM2S), Institut Charles Delaunay (ICD), Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS)-Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS) |
Rok vydání: | 2019 |
Předmět: |
2. Zero hunger
Computer science business.industry Pattern recognition 04 agricultural and veterinary sciences 02 engineering and technology Convolutional neural network [INFO.INFO-PF]Computer Science [cs]/Performance [cs.PF] [INFO.INFO-SY]Computer Science [cs]/Systems and Control [cs.SY] 040103 agronomy & agriculture 0202 electrical engineering electronic engineering information engineering 0401 agriculture forestry and fisheries 020201 artificial intelligence & image processing Artificial intelligence business |
Zdroj: | Fifteenth International Conference on Quality Control by Artificial Vision Fifteenth International Conference on Quality Control by Artificial Vision, May 2019, Mulhouse, France. pp.28, ⟨10.1117/12.2521264⟩ |
DOI: | 10.1117/12.2521264 |
Popis: | International audience; Various defects can appear on the surface of a potato, producing an adverse effect on their market price. For several years, manual methods have been applied to classify this tuber, which caused certain drawbacks such as: high-cost, high-processing time and subjective results. In this paper we introduce a deep-learning based method to classify and localize defects in potatoes with the aim to automate the quality control task. An extensive dataset was created including six potato categories: healthy, damaged, greening, black dot, common scab and black scurf. Then, a convolutional neural network (CNN) was trained with this dataset in order to achieve the classification task. We also propose to leverage the localization capability of the trained network to localize the region of the classified defect. Finally, a global evaluation was done in a test set, where 4 different sides images were taken into account to represent one tuber. Experimental results with different CNN architectures are shown. We achieved an average F1-score of 0.94 for the classification task. The localization performance is measured qualitatively by a heat map output, which shows that the proposed method accurately localize the defects. |
Databáze: | OpenAIRE |
Externí odkaz: |