Intelligent Storage and Retrieval of Power Accessories Based on Deep Learning and Image Recognition

doi:10.11930/j.issn.1004-9649.202006148

Abstract

Abstract: The power accessories have various types and models, and the storage and retrieval management with RFID technology cannot cover them all, which often leads to the inaccuracy and low efficiency of power accessories storage and retrieval, and the management quality not to meet the production requirements. In view of these problems, we carry out a research on intelligent recognition of power accessories based on machine learning and image recognition to correct the deficiency of RFID technology for storage and retrieval management of power accessories. Firstly, the gray-scale processing and binarization methods are used to process the original images, and the minimum circumscribed rectangle is used to correct the original images. Secondly, a deep learning model suitable for identifying power accessories is constructed using CNN and CRNN deep neural networks with combination of CTC loss function, and the suspected accessories are recommended synchronously according to the image recognition coincidence. The images of power accessories are acquired by intelligent equipment, and their name and model are identified in real time using the proposed methods, with prompt of their overall dimension, application scope and product use. The experimental results show that the accuracy of the intelligent recognition of power accessories based on machine learning and image recognition reaches 95%, which significantly improves the intelligent level of warehousing management.

Key words: deep learning, image recognition, intelligent storage, artificial intelligence, internet of things

ZHAO Yongliang, FU Xin, GUO Yang, BIAN Yingying, WANG Sining. Intelligent Storage and Retrieval of Power Accessories Based on Deep Learning and Image Recognition[J]. Electric Power, 2021, 54(3): 55-60.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202006148

https://www.electricpower.com.cn/EN/Y2021/V54/I3/55

References

[1] 赵永良, 付鑫, 吴尚远, 等. 基于计算机视觉的智能仓储图像识别系统设计与实现[J]. 电力信息与通信技术, 2019, 17(12): 31-36
ZHAO Yongliang, FU Xin, WU Shangyuan, et al. Design and implementation of intelligent warehouse image recognition system based on computer vision[J]. Electric Power Information and Communication Technology, 2019, 17(12): 31-36
[2] YUAN Lufeng, WANG Guannan, FAN Shifeng, et al. Intelligent work order recognition system based on end-to-end deep neural network[C]//2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC). Xiamen, China. IEEE, 2019: 387-391.
[3] 庞丝丝, 黄呈铖. 基于卷积神经网络的图像分类研究[J]. 现代计算机, 2019(23): 40-44
PANG Sisi, HUANG Chengcheng. Image classification based on convolution neural network[J]. Modern Computer, 2019(23): 40-44
[4] 王超. 基于卷积神经网络的图像分类技术研究与实现[J]. 电脑知识与技术, 2016, 12(35): 209-211
WANG Chao. Research and implementation of image classification based on convolution neural network[J]. Computer Knowledge and Technology, 2016, 12(35): 209-211
[5] 李华, 屈丹, 张文林, 等. 结合全局词向量特征的循环神经网络语言模型[J]. 信号处理, 2016, 32(6): 715-723
LI Hua, QU Dan, ZHANG Wenlin, et al. Recurrent neural network language model with global word vector features[J]. Journal of Signal Processing, 2016, 32(6): 715-723
[6] 陈翠平. 基于深度信念网络的文本分类算法[J]. 计算机系统应用, 2015, 24(2): 121-126
CHEN Cuiping. Text categorization based on deep belief network[J]. Computer Systems & Applications, 2015, 24(2): 121-126
[7] FELZENSZWALB P, MCALLESTER D, RAMANAN D. A discriminatively trained, multiscale, deformable part model[C]//2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA. IEEE, 2008: 1-8.
[8] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D. Cascade object detection with deformable part models[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 13-18, 2010. San Francisco, CA, USA. IEEE, 2010: 2241-2248.
[9] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.
[10] BENENSON R, MATHIAS M, TIMOFTE R, et al. Pedestrian detection at 100 frames per second[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA. IEEE, 2012: 2903-2910.
[11] 邢艳芳, 段红秀, 何光威. TensorFlow在图像识别系统中的应用[J]. 计算机技术与发展, 2019, 29(5): 192-196
XING Yanfang, DUAN Hongxiu, HE Guangwei. Application of TensorFlow in image recognition system[J]. Computer Technology and Development, 2019, 29(5): 192-196
[12] 杨楠. 基于Caffe深度学习框架的卷积神经网络研究[D]. 石家庄: 河北师范大学, 2016.
YANG Nan. The study of convolution neural network based on Caffe deep learning framework[D]. Shijiazhuang: Hebei Normal University, 2016.
[13] 李梦洁, 董峦. 基于PyTorch的机器翻译算法的实现[J]. 计算机技术与发展, 2018, 28(10): 160-163, 167
LI Mengjie, DONG Luan. Implementation of machine translation algorithm based on PyTorch[J]. Computer Technology and Development, 2018, 28(10): 160-163, 167
[14] SABZMEYDANI P, MORI G. Detecting pedestrians by learning shapelet features[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition. June 17-22, 2007. Minneapolis, MN, USA. IEEE, 2007: 1-8.
[15] 王江涛, 杨静宇. 红外图像中人体实时检测研究[J]. 系统仿真学报, 2007(19): 4490-4494
WANG Jiangtao, YANG Jingyu. Research on real time pedestrian detection in infrared images[J]. Journal of System Simulation, 2007(19): 4490-4494
[16] 刘云鹏, 裴少通, 武建华, 等. 基于深度学习的输变电设备异常发热点红外图片目标检测方法[J]. 电网技术, 2019, 13(2): 27-33
LIU Yunpeng, PEI Shaotong, WU Jianhua, et al. Deep learning based target detection method for abnormal hot spots infrared images of transmission and transformation equipment[J]. Southern Power System Technology, 2019, 13(2): 27-33
[17] REN X F, BO L F, FOX D. RGB-(D) scene labeling: features and algorithms[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA. IEEE, 2012: 2759-2766.
[18] BENENSON R, MATHIAS M, TUYTELAARS T, et al. Seeking the strongest rigid detector[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, OR, USA. IEEE, 2013: 3666-3673.
[19] 高嵩, 陆倚鹏, 王笑倩, 等. 基于深度学习的悬式瓷绝缘子红外图像识别方法[J]. 电力科学与技术学报, 2020, 35(5): 119-125
GAO Song, LU Yipeng, WANG Xiaoqian, et al. Infrared image recognition method of porcelain disc-suspended insulators based on deep learning technology[J]. Journal of Electric Power Science and Technology, 2020, 35(5): 119-125
[20] 王功鹏, 段萌, 牛常勇. 基于卷积神经网络的随机梯度下降算法[J]. 计算机工程与设计, 2018, 39(2): 441-445, 462
WANG Gongpeng, DUAN Meng, NIU Changyong. Stochastic gradient descent algorithm based on convolution neural network[J]. Computer Engineering and Design, 2018, 39(2): 441-445, 462
[21] 杨鹤标, 龚文彦. 基于卷积神经网络的反向传播算法改进[J]. 计算机工程与设计, 2019, 40(1): 126-130
YANG Hebiao, GONG Wenyan. Improvement of back propagation algorithm based on convolution neural network[J]. Computer Engineering and Design, 2019, 40(1): 126-130
[22] 杨晓楠, 孙博, 郎燕生. 基于深度学习的特高压直流闭锁故障智能调度决策[J]. 中国电力, 2020, 53(6): 8-17
YANG Xiaonan, SUN Bo, LANG Yansheng. Intelligent dispatch decision-making for UHVDC blocking fault based on deep learning[J]. Electric Power, 2020, 53(6): 8-17