Fruit-Scan: System to Automatically Detect Raspberry Quality Using Computer Vision Techniques
Dr. Márcio J. Lacerda, Ph.D.
ABSTRACT
Chile ranks tenth among the countries that export raspberries. In the Maule Region there are approximately 1,200 families who obtain their economic livelihood based on raspberry production. Raspberry exporting companies carry out quality control of the fruit through a human expert. The quality test consists of visually analyzing a small sample of fruit and determining the percentages of healthy fruit and fruit with defects. This talk presents the results of the Fruit-Scan project: System to automatically detect raspberry quality using computer vision techniques. The developed technology uses convolutional neural networks to analyze images of raspberry trays and count healthy and defective raspberries. The research was financed by the Innovation Fund for Competitiveness FIC of the Regional Government of Maule through the Transfer Project for the Development of the Raspberry Quality Estimation Equipment code 40.001.110-0.
BIOSKETCH
Marco Mora received the B.S. degree in Electronics Engineering and the M.S. degree in Electrical Engineering from Department of Electrical Engineering, Universidad de Concepción, Concepción, Chile, in 1998 and 2004, respectively; and the Ph.D in Computer Science from Polytechnical National Institute of Toulouse (INPT), University of Toulouse, Toulouse, France, in 2008. He is a Full Professor in the Department of Computer Science and Industry at Universidad Católica del Maule, Talca, Chile. He is Head and Senior Researcher of the Laboratory of Technological Research in Pattern Recognition (LITRP), Universidad Católica del Maule. His research interests are digital image processing, neural networks, biometrics, and industrial applications of pattern recognition.