Dual Stage Image Analysis for a complex pattern classification task: Ham veining defect detection. (March 2020)

• Record Type: Journal Article
• Authors: Lopes, Jessica F.; Barbon, Ana Paula A.C.; Orlandi, Giorgia; Calvini, Rosalba; Lo Fiego, Domenico P.; Ulrici, Alessandro; Barbon, Sylvio
• Is Part Of: Biosystems engineering. Volume 191(2020)
• Page Start: 129
• Page End: 144
• Publication Date: 2020-03
• Subjects: Computer Vision System -- Machine learning -- Pork quality -- Raw ham; Bioengineering -- Periodicals; Agricultural engineering -- Periodicals; Biological systems -- Periodicals; Génie rural -- Périodiques; Systèmes biologiques -- Périodiques; 631
• DOI: 10.1016/j.biosystemseng.2020.01.008
• Languages: English
• ISSNs: 1537-5110

Abstract

Abstract : Veins in pork thigh carcass are directly related to the quality of dry-cured ham, and consequently to its market value. Some veining defects over the surface of raw ham are easily detected by humans and precisely assessed by a specialist. However, the automatic evaluation of raw ham quality by image analysis poses some challenges to the traditional Computer Vision Systems (CVS), many of them grounded on the complex image pattern related to each defect level. To improve the CVS classification performance without overburdening feature extraction, as well as the common machine learning modelling, we propose Dual Stage Image Analysis (DSIA). DSIA is an additional step in a CVS, that was built in two stages based on the "divide and conquer" strategy. The first stage consists of splitting the region of interest into sub-regions to predict the presence of veining. In the second stage, the algorithm computes the number of veining sub-regions to assess the final defect level classification. A total of 194 raw ham samples were used to evaluate the DSIA performance in the experiments. Support Vector Machine and Random Forest algorithms were compared for inducing the classification model using 92 image features. Random Forest model was the best, capable of predicting defect level with 88.10% accuracy using DSIA. Without DSIA, the CVS with RF achieved an accuracy of 63.10%. Highlights: The proposed method improved the image pattern recognition of complex patterns. The classification accuracy was improved by more than 20%. A real dataset was explored with two different machine learning algorithms. It is a straightforward method to perform embedded in the traditional CVS pipeline.