Colour based Quality Analysis of Fruits for Automatic Grading using Raspberry PI

Abstract: Non destructive quality evaluation of fruits is important and very vital for the food and agricultural industry. This project presents fruit quality detection system. The system design considers some features that includes fruit colours and size, which increases accuracy for detection of fruits pixels. Histogram of Oriented Gradients (HOG) is used for background removal, for colour classification Support Vector Machine (SVM) is used. The main idea behind the histogram of oriented gradient is that the local appearance and shape of object in an image can be described by the intensity distribution of gradients or direction of the contours. At present, most existing fruit quality detecting and grading system have the disadvantage of low efficiency, low speed of grading, high cost and complexity. IMAGE PROCESSING offers solution for the automated fruit size grading to provide accurate, reliable, consistent and quantitative information apart from handling large volumes, which may not be achieved by employing the human graders. The hardware prototype also created by using RAPBERRY PI ultra low power microcontroller.

Keywords: RASPBERRY PI, IMAGE PROCESSING, Conveyor setup, IR sensor.