Abstract
In order to avoid the influence of illumination condition, overlap and other occlusion on image recognition, an improved LeNet convolution neural network is used to improve the structure of the traditional content-based recognition method. An Apple target recognition model based on the improved LeNet convolution neural network is designed and used to avoid the influence of illumination condition, overlap and other occlusion factors on image recognition. The model trains and validates Apple images in different scenarios. The results show that the network model can effectively recognize apple images. The recognition rates of independent fruits, occluded fruits, overlapping fruits and adjacent fruits are 96.25%, 91.37%, 94.91% and 89.56% respectively, and the comprehensive recognition rate is 93.79%. Compared with other methods, this algorithm has stronger anti-jamming ability, faster image recognition speed and higher recognition rate.
Publication Date
3-28-2019
First Page
155
Last Page
158
DOI
10.13652/j.issn.1003-5788.2019.03.028
Recommended Citation
Hongfang, CHENG and Chunyou, ZHANG
(2019)
"Research on apple image recognition technology based on improved LeNet convolution neural network in natural scene,"
Food and Machinery: Vol. 35:
Iss.
3, Article 28.
DOI: 10.13652/j.issn.1003-5788.2019.03.028
Available at:
https://www.ifoodmm.cn/journal/vol35/iss3/28
References
[1] 夏雪, 周国民, 丘耘, 等. 自然环境下苹果作业机器人双果重叠目标侦测方法[J]. 中国农业科技导报, 2018, 20(7): 63-73.
[2] 贾伟宽. 基于智能优化的苹果采摘机器人目标识别研究[D]. 苏州: 江苏大学, 2016: 27-29.
[3] 钱建平, 李明, 杨信廷, 等. 基于双侧图像识别的单株苹果树产量估测模型[J]. 农业工程学报, 2013, 29(6): 132-138.
[4] 许立兵, 朱启兵, 黄敏. 基于ARM的苹果采后田间分级检测系统设计[J]. 计算机工程与应用, 2015, 51(16): 234-238.
[5] 田有文, 赖兴涛, 张芳, 等. 基于高光谱成像的苹果果梗完整性识别方法研究[J]. 沈阳农业大学学报, 2018, 49(2): 234-241.
[6] 周云成, 许童羽, 郑伟, 等. 基于深度卷积神经网络的番茄主要器官分类识别方法[J]. 农业工程学报, 2017, 33(15): 219-226.
[7] 马永杰, 李雪燕, 晓凤. 基于改进深度卷积神经网络的交通标志识别[J]. 激光与光电子学进展, 2018, 55(12): 250-257.
[8] 龙满生, 欧阳春娟, 刘欢, 等. 基于卷积神经网络与迁移学习的油茶病害图像识别[J]. 农业工程学报, 2018, 34(18): 194-201.
[9] BARGOTI S, UNDERWOOD J P. Image segmentation for fruit detection and yield estimation in apple orchards[J]. Journal of Field Robotics, 2017, 34(6): 1 039-1 060.
[10] REN Shao-qing, HE Kai-ming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1 137-1 149.
[11] ALWZWAZY H, ALBEHADILI H, ALWAN Y, et al. Handwritten digitrecognition using convolution neural networks[J]. International Journal of Innovative Research in Computer & Communication Engineering, 2016, 4(2): 1 101-1 106.
[12] 高震宇, 王安, 刘勇, 等. 基于卷积神经网络的鲜茶叶智能分选系统研究[J]. 农业机械学报, 2017, 48(7): 53-58.
[13] LU Jun. Detecting citrus fruits and occlusion recovery under natural illumination conditions[J]. Computers & Electronics in Agriculture, 2015, 110: 121-130.
[14] 傅隆生, 冯亚利, ELKAMIL Tola, 等. 基于卷积神经网络的田间多簇猕猴桃图像识别方法[J]. 农业工程学报, 2018, 34(2): 205-211.
[15] 王丹丹, 何东健. 基于R-FCN深度卷积神经网络的机器人蔬果前苹果目标的识别[J]. 农业工程学报, 2019, 35(3): 156-163.