A computer vision algorithm for tangerine yield estimation

Abstract

The specific objective of this paper is to develop a computer vision algorithm to detect and count tangerine flowers in an image for estimate tangerine crops. The algorithm consists of image acquisition, Gaussian filter to remove noise, white color detection, counting of tangerine flowers. A Gaussian filter was used to reduce noise and illumination adjustment as much as possible for better clarity. It is observed that the developed method gives better valid output for tangerine flower detection in natural outdoor lighting, with different lighting condition without any alternative lighting source to control the luminance. The simulation result reveals that the method is reliable, feasible and efficient compared to other existing methods. © 2013 SERSC.