Abstract
Objective: An automatic identification method of jujube defects based on improved convolution neural network was established. Methods: Using the dual branch convolution neural network structure, branch 1 combined with the transfer learning strategy for pre training, analysis 2 extracted the feature information from the jujube image based on the lightweight network fusion feature map. The superiority of this method was verified by comparative experiments. Results: Compared with the improvement before, the improved defect recognition method optimized the structure of the convolutional neural network, and the detection accuracy was further improved, from 96.02% to 99.50%. Conclusion: This method improved the network learning speed and convergence speed, and had good classification and recognition effect.
Publication Date
8-28-2021
First Page
158
Last Page
162,192
DOI
10.13652/j.issn.1003-5788.2021.08.027
Recommended Citation
Zhong-zhi, ZHANG; Huan-qing, XUE; and Guang-ling, FAN
(2021)
"Research on jujube defect recognition method based on improved convolution neural network,"
Food and Machinery: Vol. 37:
Iss.
8, Article 27.
DOI: 10.13652/j.issn.1003-5788.2021.08.027
Available at:
https://www.ifoodmm.cn/journal/vol37/iss8/27
References
[1] 姜洪权, 贺帅, 高建民, 等. 一种改进卷积神经网络模型的焊缝缺陷识别方法[J]. 机械工程学报, 2020, 56（8）: 235-242.
[2] 杨森, 冯全, 张建华, 等. 基于轻量卷积网络的马铃薯外部缺陷无损分级[J]. 食品科学, 2021, 42（10）: 284-289.
[3] 张思雨, 张秋菊, 李可. 采用机器视觉与自适应卷积神经网络检测花生仁品质[J]. 农业工程学报, 2020, 36（4）: 269-277.
[4] 海潮, 赵凤霞, 孙烁. 基于Blob分析的红枣表面缺陷在线检测技术[J]. 食品与机械, 2018, 34（1）: 126-129.
[5] 周伟, 徐颖若. 基于PLC和图像处理的水果分类智能控制系统[J]. 农机化研究, 2021, 12（5）: 235-239.
[6] 赵小霞, 李志强. 基于PLC和机器视觉的水果自动分级系统研究[J]. 农机化研究, 2021, 12（8）: 75-79.
[7] 李雅倩. 并联机器人夹持机构串类水果夹取控制研究[D]. 镇江: 江苏大学, 2020: 27-29.
[8] 杨双艳, 杨紫刚, 张四伟, 等. 基于近红外光谱和PSO-SVM算法的烟叶自动分级方法[J]. 贵州农业科学, 2018, 46（12）: 141-144.
[9] 王阳阳, 黄勋, 陈浩, 等. 基于同态滤波和改进K-means的苹果分级算法研究[J]. 食品与机械, 2019, 35（12）: 47-51, 112.
[10] 王立扬, 张瑜, 沈群, 等. 基于改进型LeNet-5的苹果自动分级方法[J]. 中国农机化学报, 2020, 41（7）: 105-110.
[11] 于蒙, 李雄, 杨海潮, 等. 基于图像识别的苹果的等级分级研究[J]. 自动化与仪表, 2019, 34（7）: 39-43.
[12] 樊泽泽, 柳倩, 柴洁玮, 等. 基于颜色与果径特征的苹果树果实检测与分级[J]. 计算机工程与科学, 2020, 42（9）: 1 599-1 607.
[13] 王冉冉, 刘鑫, 尹孟, 等. 面向苹果硬度检测仪的声振信号激励与采集系统设计[J]. 浙江大学学报（农业与生命科学版）, 2020, 46（1）: 111-118.
[14] 刘英, 周晓林, 胡忠康, 等. 基于优化卷积神经网络的木材缺陷检测[J]. 林业工程学报, 2019, 4（1）: 115-120.
[15] 王泽霞, 陈革, 陈振中. 基于改进卷积神经网络的化纤丝饼表面缺陷识别[J]. 纺织学报, 2020, 41（4）: 115-120.
[16] 王志中. 基于改进蚁群算法的移动机器人路径规划研究[J]. 机械设计与制造, 2018, 12（1）: 242-244.
[20] CAETANO C E F, LIMA A B, PAULINO J O S, et al. A conductor arrangement that overcomes the effective length issue in transmission line grounding[J]. Electric Power Systems Research, 2018, 46（5）: 159-162.
[21] JIA Zhi-wei, WANG Li-Jun, ZHANG Jin-chuan, et al. High efficiency, low power-consumption DFB quantum cascade lasers without lateral regrowth[J]. Nanoscale Research Letters, 2017, 12（1）: 88-95.
[22] 杨志锐, 郑宏, 郭中原, 等. 基于网中网卷积神经网络的红枣缺陷检测[J]. 食品与机械, 2020, 36（2）: 140-145, 181.
[23] 张昱, 陈光黎. 基于最小二乘支持向量机的机器视觉识别方法[J]. 测控技术, 2011, 30（7）: 97-100.