[1]舒 军,何俊成,李振亚. 基于Mask R-CNN的槟榔片分割算法研究[J].湖北工业大学学报,2022,(1):46-53.
　SHU Jun,HE Juncheng,LI Zhenya. Research on Grading Algorithm of Betel Nut Slices Based on Mask RCNN[J].,2022,(1):46-53.
点击复制

 基于Mask R-CNN的槟榔片分割算法研究()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2022年第1期
页码:
46-53
栏目:
湖北工业大学学报
出版日期:
2022-02-28

文章信息/Info

Title:
 Research on Grading Algorithm of Betel Nut Slices Based on Mask RCNN
文章编号:
1003-4684(2022)01-0046-08
作者:
 舒 军1;  何俊成2;  李振亚2
1 湖北工业大学电气与电子工程学院， 湖北 武汉 430068;
2 湖北工业大学太阳能高效利用及储能运行控制湖北省重点实验室， 湖北 武汉 430068
Author(s):
SHU Jun1; HE Juncheng2;  LI Zhenya1
1 School of Electrical and Electronic Engineering, Hubei Univ. of Tech., Wuhan, 430000, China; 
2 Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System, Hubei Univ. of Tech., Wuhan, 430000, China
关键词:
 ; Mask R-CNN;  高分辨率网络;  卷积块注意力;  槟榔片
Keywords:
 ; Mask R-CNN;  High-resolution network;  Convolution block attention;  Betel nut slice
分类号:
TP391.4
文献标志码:
A
摘要:
 针对槟榔片加工过程中自动化程度低，提出一种基于Mask R-CNN的槟榔片自动分级算法：采用改进高分辨率网络作为主干网络提取槟榔片表面信息，减少多次卷积过程中信息损失，提高轮廓分割准确度；采用改进卷积块注意力模型加强内轮廓中有效信息提取，抑制无效信息，提高有核无核籽判断准确率；同时采用深度可分离卷积减少高分辨率主干网络带来的参数量、计算复杂度增加问题。实验结果表明改进后网络相比未改进前分割精度提高2.5%，同时有核无核籽判断准确率提高5.93%，总浮点计算量降低64.9%。
Abstract:
 Aiming at the low degree of automation in the processing of betel nut slices, an automatic grading algorithm for betel nut slices based on Mask R-CNN is proposed. An improved high-resolution network is used as the backbone network to extract the surface information of betel nut slices, reduce information loss during multiple convolutions, and improve the accuracy of contour segmentation. The improved convolution block attention model is applied to strengthen the extraction of effective information from the inner contour, suppress invalid information, and improve the accuracy of nucleus and seedless judgment. At the same time, deep separable convolution is utilized to reduce high-resolution backbone network bands and the problem of the increasing amount of parameters and computational complexity. The experimental results show that the improved network segmentation accuracy is increased by 2.5% compared with the unimproved network, and the accuracy of the core and seedless judgment is increased by 5.93%, and the total floating-point calculation is reduced by 64.9%.

参考文献/References:

[1] 黄鹏, 郑淇, 梁超. 图像分割方法综述[J].武汉大学学报(理学版), 2020, 66(6):519-531.
[2] HE K, GKIOXARI G, DOLLR P, et al. Mask R-CNN[C]∥2017 IEEE International Conference on Computer Vision (ICCV), 2017,2980-2988. 10.1109/ICCV.2017.322.
[3] LIN T, DOLLR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C].//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.936-944. 10.1109/CVPR.2017,106.
[4] NEUBECK A, GOOL L V. Efficient non-maximum suppression[C]∥18th International Conference on Pattern Recognition (ICPR’06), 2006.850-855. 10.1109/ICPR.2006.479.
[5] GIRSHICK R. Fast R-CNN[C]∥2015 IEEE International Conference on Computer Vision (ICCV), 2015.1440-1448. 10.1109/ICCV.2015.169.
[6] SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.5686-5696. 10.1109/CVPR.2019.00584.
[7] WOO S, PARK J, LEE J-Y, et al. CBAM: convolutional block attention module[C]∥Cham:Springer International Publishing, 2018,3-19.
[8] CHOLLET F. Xception: Deep learning with depthwise separable convolutions[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.1800-1807. 10.1109/CVPR.2017,195.
[9] SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning[C]∥AAAI, 2017.
[10] 袁嘉杰, 张灵, 陈云华. 基于注意力卷积模块的深度神经网络图像识别[J]. 计算机工程与应用, 2019, 55: 9-16.
[11] SELVARAJU R R, COGSWELL M,DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020, 128(2):336-359.

相似文献/References:

[1]熊韧,曹海印,王焱清,等.非牛顿润滑静压轴承的节流器流量方程修正[J].湖北工业大学学报,2019,34(5):6.
　XIONG Ren,CAO Haiyin,WANG Yanqing,et al.Modified restrictor flow equations of hydrostatic bearings ubricated by non-Newtonian fluids[J].,2019,34(1):6.
[2]王照远,曹 民,王 毅,等. 场景与数据双驱动的隧道图像拼接方法[J].湖北工业大学学报,2020,(4):11.
　WANG Zhaoyuan,CAO Min,WANG Yi,et al. Tunnel Image Stitching Method based on Scene and Data[J].,2020,(1):11.
[3]潘 健,梁佳成,陈凤娇,等. 单电流闭环多重PR控制的LCL型逆变器[J].湖北工业大学学报,2020,(4):16.
　PAN Jian,LIANG Jiacheng,CHEN Fengjiao,et al. Design of LCL Grid Connected Inverter based on Single Closed Loop Control and Multiple PR Controllers[J].,2020,(1):16.
[4]王晓光,赵 萌,文益雪,等. 定子闭口槽结构对永磁电机齿槽转矩影响分析[J].湖北工业大学学报,2020,(4):25.
　WANG Xiaoguang,ZHAO Meng,WEN Yixue,et al. Study on Cogging Torque and Vibration Noise of Permanent Magnet Motor with Segmental Stator and Closed-Slot[J].,2020,(1):25.
[5]宇 卫,凃玲英,陈 健. 风电场集中接入对集电线电流保护的影响[J].湖北工业大学学报,2020,(4):29.
　YU Wei,TU Lingying,CHEN Jian. Effect of the Collective Line Current Protection when Wind Farms are Centralized Accessed to the Power System[J].,2020,(1):29.
[6]廖政斌,王泽飞,祝 珊. 二惯量系统谐振在线抑制及相位补偿[J].湖北工业大学学报,2020,(4):34.
　LIAO Zhengbin,WANG Zefei,ZHU Shan. Online Resonance Suppression and Phase Compensation for Double Inertia System[J].,2020,(1):34.
[7]王 欣,游 颖,姜天翔,等. 面向3D打印过程的产品工艺设计和优化[J].湖北工业大学学报,2020,(4):39.
　WANG Xin,YOU Ying,JIANG Tianxiang,et al. Product Process Design and Optimization for 3D Printing Processes[J].,2020,(1):39.
[8]冉晶晶,文 红,罗雅梅,等. 全自动样品前处理平台及其控制系统[J].湖北工业大学学报,2020,(4):43.
　RAN Jingjing,WEN Hong,LUO Yamei,et al. Research on Automatic Sample Preprocessing Platform and its Control System[J].,2020,(1):43.
[9]杨 磊,马志艳,石 敏,等. 基于模糊PID的小型冷库过热度控制方法[J].湖北工业大学学报,2020,(4):43.
　YANG Lei,MA Zhiyan,SHI Min,et al. Research on Superheat Control Method of Small Cold Storage based on Fuzzy PID[J].,2020,(1):43.
[10]黄 晶,周细枝,周业望. 动态注塑成型模具的设计与实验研究[J].湖北工业大学学报,2020,(4):52.
　HUANG Jing,ZHOU Xizhi,ZHOU Yewang. Design and Experimental Study of Dynamic Injection Molding[J].,2020,(1):52.

备注/Memo

备注/Memo:
［收稿日期］ 2021-07-30
［第一作者］ 舒    军（1973-），男，湖北荆门人，工学博士，湖北工业大学副教授，研究方向为机器视觉，深度学习
［通信作者］ 何俊成（1995-），男，湖北恩施人，湖北工业大学硕士研究生，研究方向为机器视觉，深度学习
更新日期/Last Update: 2022-02-25