A NOVEL TECHNIQUE FOR TANGERINE YIELD PREDICTION USING FLOWER DETECTION ALGORITHM

作者：Dorj Ulzii Orshikh; Lee Malrey^*; Lee Keun Kwang; Jeong Gisung

来源：International Journal of Pattern Recognition and Artificial Intelligence, 2013, 27(5): 1354007.

DOI：10.1142/S0218001413540074

• Tangerine flower/fruit
• yield estimation
• color detection
• Gaussian smoothing
• counting algorithm
• computer vision
• image processing

The main goal of this present paper is to develop color detection, and counting algorithm for tangerine flowers under natural lighting conditions to estimate better yield of tangerine from orchards, and each tree picture was taken from four sides. As a result, total of 1340 subimages of tangerine flowers were detected by the newly introduced algorithm from a sample of 21 tangerine trees during blooming season. A Gaussian filter was used to reduce noise and illumination adjustment as much as possible for better clarity to identify exactly the tangerine flowers. The proposed algorithm gives accurate output of tangerine flower detection by including partially/semipartially occluded tangerine flowers and its clusters. Finally, the output of yield estimation reveals that about 10% of all total tangerine flowers turned out to be tangerine.

• 出版日期2013-8