结合深度学习与生物特征识别在冷链拣选中的算法研究

doi:10.11959/j.issn.2096-6652.201906

摘要/Abstract

摘要：

机器人对食品的抓取、拣选是工业自动化中的一个常见问题，但是食品通常形状不规则、特征多变，导致快速、稳定的视觉分析与定位较为困难。提出了一种结合深度学习与生物特征识别的目标点定位方法，首先使用深度学习模型对目标点进行粗定位，之后在粗定位点的邻域中，利用生物特征进行微调，得到精准的目标点坐标。所设计的方法在常见食品——虾的数据上进行了模型训练与性能验证。首先将虾的图像进行预处理后输入深度学习模型得到粗定位点，之后对虾的位姿进行归一化并提取轮廓线，基于对搜索域内的轮廓拟合与特征点检测以精确定位目标点。实验结果证明了该方法的有效性：在包含 1000 张实测样本的测试集上，整体方案的识别率达到97%，可初步满足实际工业应用的要求。

关键词: 机器视觉, 食品拣选, 深度学习, 特征识别

Abstract:

Irregular-shape food picking and processing is a common problem in industrial automation,which can be difficult for classical image processing techniques,because of the big variations in food shape and characteristics,also the high-performance requirements in both algorithm accuracy and speed.In this paper,a hybrid method based on deep learning and feature recognition was proposed,which first roughly localized the target point based on deep learning model,and then created a search range accordingly.After that,based on biological feature analysis,target point could be accurately localized in the search range.Based on the data of shrimps,a kind of common food,the performance of the proposed method was tested.The shrimp images were pre-processed and used to train the deep learning model for rough localization.Then the shrimp body pose was normalized for edge extraction after proper rotation and projection.The extracted edge curve in search range was analyzed to accurately localize the target joint point.The validation results based on a test set including 1000 samples prove the feasibility of the method – the final detection rate of the proposed hybrid method is 97%.The performance meets industrial requirements on this case.

Key words: computer vision, food picking, deep learning, feature recognition

中图分类号:

TP301

陈妮亚, 阮佳阳, 黄金苗, 等. 结合深度学习与生物特征识别在冷链拣选中的算法研究[J]. 智能科学与技术学报, 2019, 1(1): 88-95.

Niya CHEN, Jiayang RUAN, Jinmiao HUANG, et al. Algorithm design for food-picking combining deep learning and biometrics recognition[J]. Chinese Journal of Intelligent Science and Technology, 2019, 1(1): 88-95.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

参考文献 22

[1]	CONNOLLY C . ABB high-speed picking robots establish themselves in food packaging[J]. Industrial Robot, 34(4): 281-284.2007.
[2]	MUHAMMEDALI B , ABDULLAH M Z , A ZEMI M N M . Food handling and packaging using computer vision and robot[C]// In Proceedings of IEEE Conference on Computer Graphics,Imaging and Visualization, 2004: 177-182.
[3]	Gregor Jonsson Inc. Shrimp peeling systems for faster,better,cheaper shrimp processing[R]. 2017.
[4]	ZHAO L T , XI M J , WANG W ,et al. A review of technology development process of a typical shrimp peeling machine[J]. Journal of Advanced Mechanical Design,Systems,and Manufacturing, 2015,9(2): 1-9.
[5]	常亮, 邓小明, 周明全 ,等. 图像理解中的卷积神经网络[J]. 自动化学报, 2016,42(9): 1300-1312.
	CHANG L , DENG X M , ZHOU M Q ,et al. Convolutional neural network in image understanding[J]. Acta Automatica Sinica, 2016,42(9): 1300-1312.
[6]	SZEGEDY C , LIU W , JIA ? Q ,et al. Going deeper with convolutions[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),Boston,MA,USA, 2015: 1-9.
[7]	SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.
[8]	GIRSHICK R , DONAHUE J , DARRELL T ,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[9]	GIRSHICK R , . Fast R-CNN[C]// In Proceedings of IEEE International Conference on Computer Vision, 2015: 1440-1448.
[10]	ALHWARIN F , WANG C , RISTIC-DURRAN T D ,et al. Improved SIFT-features matching for object recognition[C]// In Proceedings of International Conference on Visions of Computer Science, 2008: 179-190.
[11]	LI D , QIAN J S . Sift-based object matching and tracking of coal mine[C]// In Proceedings of IET International Conference on Wireless,Mobile and Multimedia Networks, 2011: 327-330.
[12]	JIAN X , CHEN X , SONG X ,et al. An improved Harris-FAST algorithm for underwater object corner detection[C]// In Proceedings of IEEE Conference on Control and Decision, 2015: 5424-5428.
[13]	YU L U , HAO X W , WANG ? J . Research on Moravec and Harris corner algorithm[J]. Computer Technology ＆ Development, 2011.
[14]	LIE W N , CHUANG C H . Fast and accurate snake model for object contour detection[J]. Electronics Letters, 2001,37(10): 624-626.
[15]	SAKALLI M , LAM K M , YAN H . A faster converging snake algorithm to locate object boundaries[J]. IEEE Transactions on Image Processing, 2006,15(5): 1182-1191.
[16]	YANN L C , BENGIO Y , HINTON G . Deep learning[J]. Nature, 2015,521: 436-444.
[17]	张慧, 王坤峰, 王飞跃 . 深度学习在目标视觉检测中的应用进展与展望[J]. 自动化学报, 2017,43(8): 1289-1305.
	ZHANG H , WANG K F , WANG F Y . Application progress and prospect of deep learning in target visual detection[J]. Acta Automatica Sinica, 2017,43(8): 1289-1305.
[18]	KRIZHEVSKY A , SUTSKEVER I , HINTON G . ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012,25(2).
[19]	HE K M , ZHANG X Y , REN S Q ,et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE conference on computer vision and pattern recognition, 2016.
[20]	JIA D , WEI D , RICHARD S ,et al. ImageNet:a large-scale hierarchical image database[C]// 2009: 248-255.
[21]	张雪松, 庄严, 闫飞 ,等. 基于迁移学习的类别级物体识别与检测研究与进展[J]. 自动化学报, 2018.
	ZHANG X S , ZHUANG Y , YAN F ,et al. Status and development of transfer learning based category-level object recognition and detection[J]. Acta Automatica Sinica, 2018.
[22]	PAN S J , YANG Q . A survey on transfer learning[J]. IEEE Trans.on Knowledge and Data Engineering, 2010,22(10): 1345-1359.