Automated Fruit and Flower Counting using Digital Image Analysis

• Main Author: Hoo, Zhou Yang
• Format: Final Year Project / Dissertation / Thesis
• Published: 2015
• Subjects: TA Engineering (General). Civil engineering (General); TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utar.edu.my/1813/1/BEE%2D2015%2D1005052%2D1.pdf; http://eprints.utar.edu.my/1813/

The purpose of this project is to predict the yield of fruit and flowers. The ability to predict the yield would benefit the farmers as they plan the sale, the shipment and operations. In this project we have used digital images to segment the fruit and flowers. The proposed algorithm includes image segmentation, size thresholding and shape analysis, counting of the regions of interest, and yield prediction. We have used two colour spaces RGB and YCbCr. The percentage error quantification for RGB model(R-G) is 8.75% for dragon fruit and 11.30% for daisy while for YCbCr model(C) percentage error is 8.07% for dragon fruit and 5.54% for daisy. Based on our analysis we have observed that YCbCr gives better results. Finally result of regression analysis for dragon fruit and daisy are 0.9517 and 0.9751 respectively. The average percentage error in yield prediction for dragon fruit is 1.40% and daisy is 5.52%.