Apple detection from apple tree image based on BP neural network and Hough transform

Using machine vision to accurately identify apple number on the tree is becoming the key supporting technology for orchard precision production management. For adapting to the complexity of the field environment in various detection situations, such as illumination changes, color variation, fruit overlap, and branches and leaves shading, a robust algorithm for detecting and counting apples based on their color and shape modes was proposed. Firstly, BP (back propagation) neural network was used to train apple color identification model. Accordingly the irrelevant background was removed by using the trained neural network model and the image only containing the apple color pixels was acquired. Then apple edge detection was carried out after morphological operations on the obtained image. Finally, the image was processed by using circle Hough transform algorithm, and apples were located with the help of calculating the center coordinates of each apple edge circle. The validation experimental results showed that the correlation coefficient of R2 between the proposed approaches based counting and manually counting reached 0.985. It illustrated that the proposed algorithm could be used to detect and count apples from apple trees’ images taken in field environment with a high precision and strong anti-jamming feature. Keywords: apple detecting and counting, BP neural network, Hough transform,color segmentation, edge detection DOI: 10.3965/j.ijabe.20150806.1239 Citation: Xiao C Y, Zheng L H, Li M Z, Chen Y, Mai C Y. Apple detection from apple tree image based on BP neural network and Hough transform. Int J Agric & Biol Eng, 2015; 8(6): 46-53.

[1]  Sanjiv Singh,et al.  Improving Orchard Efficiency with Autonomous Utility Vehicles , 2010 .

[2]  Qi Wang,et al.  Automated Crop Yield Estimation for Apple Orchards , 2012, ISER.

[3]  Gang Pan,et al.  Digital camera based measurement of crop cover for wheat yield prediction , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[4]  R. Zhou,et al.  Using colour features of cv. ‘Gala’ apple fruits in an orchard in image processing to predict yield , 2012, Precision Agriculture.

[5]  Qamar Uz Zaman,et al.  Estimation of wild blueberry fruit yield using digital color photography. , 2009 .

[6]  Larry S. Davis,et al.  Hierarchical generalized Hough transforms and line-segment based generalized H ugh transforms , 1982, Pattern Recognit..

[7]  Divya Garg,et al.  A Survey of Computer Vision Methods for Counting Fruits and Yield Prediction , 2013 .

[8]  Dennis Jarvis,et al.  Estimation of mango crop yield using image analysis - Segmentation method , 2013 .

[9]  José Luis Pons Rovira,et al.  Machine Vision and Applications Manuscript-nr. a Vision System Based on a Laser Range--nder Applied to Robotic Fruit Harvesting , 2022 .

[10]  Hava T. Siegelmann,et al.  Analog computation via neural networks , 1993, [1993] The 2nd Israel Symposium on Theory and Computing Systems.

[11]  Salah Sukkarieh,et al.  Orchard fruit segmentation using multi-spectral feature learning , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Sanjiv Singh,et al.  Yield estimation in vineyards by visual grape detection , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Raphael Linker,et al.  Determination of the number of green apples in RGB images recorded in orchards , 2012 .

[14]  Josef Kittler,et al.  A comparison of Hough transform methods , 1989 .

[15]  Q. Zaman,et al.  Estimation of Rice Yield and Protein Content Using Remote Sensing Images Acquired by Radio Controlled Unmanned Helicopter , 2008 .

[16]  K. Swain,et al.  Land-use Suitability Evaluation Criteria for Precision Agriculture Adoption in a Moderately Yielding Soya bean Cropping Area in Thailand , 2007 .

[17]  Eduardo Sontag,et al.  Turing computability with neural nets , 1991 .