[논문]Development of a Low-cost Industrial OCR System with an End-to-end Deep Learning Technology

Subedi, Bharat; Yunusov, Jahongir; Gaybulayev, Abdulaziz; Kim, Tae-Hyong

doi:10.14372/iemek.2020.15.2.51

[국내논문] Development of a Low-cost Industrial OCR System with an End-to-end Deep Learning Technology 원문보기

대한임베디드공학회논문지 = IEMEK Journal of embedded systems and applications, v.15 no.2, 2020년, pp.51 - 60

Subedi, Bharat (Kumoh National Institute of Technology) , Yunusov, Jahongir (Kumoh National Institute of Technology) , Gaybulayev, Abdulaziz (Kumoh National Institute of Technology) , Kim, Tae-Hyong (Kumoh National Institute of Technology)

Abstract ▼ AI-Helper

Optical character recognition (OCR) has been studied for decades because it is very useful in a variety of places. Nowadays, OCR's performance has improved significantly due to outstanding deep learning technology. Thus, there is an increasing demand for commercial-grade but affordable OCR systems. We have developed a low-cost, high-performance OCR system for the industry with the cheapest embedded developer kit that supports GPU acceleration. To achieve high accuracy for industrial use on limited computing resources, we chose a state-of-the-art text recognition algorithm that uses an end-to-end deep learning network as a baseline model. The model was then improved by replacing the feature extraction network with the best one suited to our conditions. Among the various candidate networks, EfficientNet-B3 has shown the best performance: excellent recognition accuracy with relatively low memory consumption. Besides, we have optimized the model written in TensorFlow's Python API using TensorFlow-TensorRT integration and TensorFlow's C++ API, respectively.

주제어

표/그림 (8)

그림 Fig. 1 The architecture of test recognition networks
그림 Fig. 2 The architecture of shared feature extraction network
그림 Fig. 3 Samples of the dataset with a different font, color, and background
그림 Fig. 4 A screenshot of OCR software
그림 Fig. 5 The complete OCR system
그림 Fig. 6 Samples of real product images with recognized characters
표 Table 1. Performance of TF-TRT integration
표 Table 2. Performance Comparison

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

In this study, we designed a low-cost industrial OCR system with end-to-end deep learning techniques suitable for embedded systems. Our goal is to develop a real-time OCR system with commercial-grade performance. We tested many DL-based OCR techniques especially end-to-end based ones by aiming at implementing a low-cost embedded system.

제안 방법

In this study, we designed a low-cost industrial OCR system with end-to-end deep learning techniques suitable for embedded systems. Our goal is to develop a real-time OCR system with commercial-grade performance.
Lately, we found an interesting study to increase the performance by carefully balancing network depth, width, and resolution with a simple scaling method [21]. This study also provides a set of networks designed to efficiently use the scaling method called EfficientNets, which shows great performance improvements with controlled numbers of model parameters. As our evaluation of EfficientNets has verified such improvements, we decided to use those networks as the backbone feature extraction Fig.
This study also provides a set of networks designed to efficiently use the scaling method called EfficientNets, which shows great performance improvements with controlled numbers of model parameters. As our evaluation of EfficientNets has verified such improvements, we decided to use those networks as the backbone feature extraction Fig. 2 The architecture of shared feature extraction network model of our OCR system. Fig.

대상 데이터

Candidates for evaluations are ResNet-50 (RN50) with 25M parameters, MobileNet-V1 (MN1) with 5.8M parameters, MobileNet-V3 (MN3) with 5.9M parameters, EfficientNet-B0 (EN0) with 6M parameters, EfficientNet-B1 (EN1) with 7.8M parameters, EfficientNet-B2 (EN2) with 9M parameters, and EfficientNet-B3 (EN3) with 12M parameters. Note that we have not included heavier versions of EfficientNet, from B4 to B7, according to the performance curve the authors provided.

참고문헌 (26)

M. Jaderberg, K. Simonyan, A. Vedaldi, A. Zisserman, "Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition," pp. 1-10, 2014.
A. Poznanski, L. Wolf, "CNN-N-gram for Handwriting Word Recognition," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2305-2314, 2016.
Shangbang Long, Xin He, Cong Yao, "Scene Text Detection and Recognition: The Deep Learning Era," pp. 1-20, 2018.
M. Jaderberg, K. Simonyan, A. Vedaldi, A. Zisserman, "Reading Text in the Wild with Convolutional Neural Networks," International Journal of Computer Vision, Vol. 116, No. 1, pp. 1-20, 2016.

상세보기
M. Liao, B. Shi, X. Bai, X. Wang, W. Liu, "Textboxes: A Fast Text Detector with a Single Deep Neural Network," Proceedings of Advancement of Artificial Intelligence, pp. 4161-4167, 2017.
Z. Tian, W. Huang, T. He, P. He, Y. Qiao, "Detecting Text in Natural Image with Connectionist Text Proposal Network," Proceedings of European Conference on Computer Vision, pp. 56-72, 2016.
X. Zhou, C. Yao, H. Wen, Y. Wang, S. Zhou, W. He, J. Liang, "East: An Efficient and Accurate Scene Text Detector," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5551-5560, 2017.
Christian Bartz, Haojin Yang, Christoph Meinel, "STN-OCR: A Single Neural Network for Text Detection and Text Recognition," pp. 1-9, 2017.
M. Busta, L. Neumann, J. Matas, "Deep Textspotter: An End-to-end Trainable Scene Text Localization and Recognition Framework," Proceedings of IEEE International Conference on Computer Vision, pp. 2204-2212, 2017.
T. He, Z. Tian, W. Huang, C. Shen, Y. Qiao, C.Sun, "An End-to-end Textspotter with Explicit Alignment and Attention," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5020-5029, 2018.
X. Liu, D. Liang, S. Yan, D. Chen, Y. Qiao, J. Yan, "Fots: Fast Oriented Text Spotting with a Unified Network," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676-5685, 2018.
Wikipedia, Comparison of Deep-learning Software, Available on : https://en.wikipedia.org/wiki/Comparison_of_deep-learning_software
M. Liao, B. Shi, X. Bai, "TextBoxes++: A Single-shot Oriented Scene Text Detector," Journal of IEEE Transactions on Image Process, Vol. 27, No. 8, pp. 3676-3690, 2018.

상세보기
B. Shi, X. Bai, C. Yao, "An End-to-end Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition," Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 11, pp. 2298-2304, 2017.

상세보기
K. Simonyanm, A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," Proceedings of International Conference on Learning Representations, pp. 7-9, 2015.
K. He, X. Zhang, S. Ren, J. Sun, "Deep Residual Learning for Image Recognition," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
K. Kim, S. Hong, B. Roh, Y. Cheon, M. Park, "PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection," pp. 1-7, 2016.
A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam,"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," pp. 1-9, 2017.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510-4520, 2018.
A. Howard, M. Sandler, G. Chu, L. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan, V. Q. Le, H. Adam, "Searching for MobileNetV3," Proceedings of IEEE International Conference on Computer Vision, pp. 1314-1324, 2019.
M. Tan, Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolution Neural Networks," pp. 1-10, 2019.
Sandler, M. Howard, A. Zhu, M. Zhmoginov, L. Chen, "Mobilenetv2: Inverted Residuals and Linear Bottlenecks," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510-4520, 2018.
Tan, M. Chen, B. Pang, R. Vasudevan, V. Sandler, M. Howard, Q. V. Le, "MnasNet: Platform-aware Neural Architecture Search for Mobile," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2820-2828, 2019.
Hu, J. Shen, G. Sun, "Squeeze-and-excitation Networks," Proceedings of IEEE Conferenc on Computer Vision and Pattern Recognition, pp. 7132-7141, 2018.
xTensor, Multi-dimensional Arrays with Broadcasting and Lazy Computing, Available on : https://xtensor.readthedocs.io/
Tobias Knopp, NumCpp, Available on : https://numcpp.readthedocs.io/

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증