딥러닝을 이용한 폐 기능 검사지의 정형화
Structuring of Pulmonary Function Test Paper Using Deep Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 문자 검출 및 인식 기술을 활용하여 비정형의 폐 기능 검사지 이미지로부터 연구를 위한 관련 정보들을 추출하여 정형화하는 방법을 제안한다. 또한 문자 인식 오차율을 줄이기 위한 후처리 방법 또한 개발하고자 한다. 제안하는 정형화 방법은 폐 기능 검사지 이미지에대해 문자 검출 모델을 사용해 검사지 내에 존재하는 모든 문자를 검출하고, 검출된 문자 이미지를 문자 인식 모델에 통과시켜 문자열을 얻어낸다. 얻어낸 문자열에 대해 문자열 매칭을 이용한유효성 검토를 진행하고 정형화를 마무리한다. 제안하는 정형화 시스템의 오차율은 약 1% 이내, 검사지 당 처리속도는 2초 이내로 전문인력의 수작업을 통한 정형화 방법보다 더 효율적이고 안정적인 방식이라는 것을 확인할 수 있다.
Abstract
In this paper, we propose a method of extracting and recognizing related information for research from images of the unstructured pulmonary function test papers using character detection and recognition techniques. Also, we develop a post-processing method to reduce the character recognition error rate. The proposed structuring method uses a character detection model for the pulmonary function test paper images to detect all characters in the test paper and passes the detected character image through the character recognition model to obtain a string. The obtained string is reviewed for validity using string matching and structuring is completed. We confirm that our proposed structuring system is a more efficient and stable method than the structuring method through manual work of professionals because our system’s error rate is within about 1% and the processing speed per pulmonary function test paper is within 2 seconds.
참고문헌 (20)
- Max Jaderberg, "Reading Text in the Wild with Convolutional Neural Networks", International Journal of Computer Vision, 116(1), pp.1~20 (2016), Springer Science and Business Media LLC[DOI]
- Ankush Gupta, "Synthetic Data for Text Localisation in Natual Images", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2315~2324 (2016)
- Xing, Linjie, "Convolutional Character Networks", IEEE, 2019, 9126~9136
- Yuliang Liu, "Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection", International Journal of Computer Vision, 129(6), pp.1972~1992 (2021), Springer Science and Business Media LLC[DOI]
- Lyu, Pengyuan, "Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes", European Conference on Computer Vision (ECCV), pp.71~88 (2018)
- Liao, Minghui, "Real-time Scene Text Detection with Differentiable Binarization", AAAI Conference on Artificial Intelligence, pp.11474~11481 (2020)
- Liu, Jingchao, "Pyramid mask text detector", preprint arXiv:1903.11800 Mar. 2019, ~ (2019)
- Huang, Zhida, "Mask R-CNN with pyramid attention network for scene text detection", 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp.764~772 (2019), IEEE
- Loginov, "Why You Should Try the Real Data for the Scene Text Recognition", arXiv preprint arXiv:2107.13938 Jul. 2021, ~ (2021)
- Zhang, Xiangyu, "Shufflenet: An extremely efficient convolutional neural network for mobile devices", IEEE conference on computer vision and pattern recognition (CVPR), pp.6848~6856 (2018)
- Baek, Youngmin, "Character region awareness for text detection", IEEE, 2019, 9365~9374
- Cai, Hongxiang, "Revisiting Classification Perspective on Scene Text Recognition", arXiv preprint arXiv:2102.10884 Jun. 2021, ~ (2021)
- Iandola, Forrest N., "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size", arXiv preprint arXiv:1602.07360 Dec. 2017, ~ (2017)
- Huang, Gao, "Densely connected convolutional networks", IEEE conference on computer vision and pattern recognition (CVPR), pp.4700~4708 (2018)
- Howard, Andrew, "Searching for mobilenetv3", IEEE, 2019, 1314~1324
- Tan, Mingxing, "Efficientnet: Rethinking model scaling for convolutional neural networks", International Conference on Machine Learning (PMLR), pp.97~ (2019)
- Ye, Jian, "TextFuseNet: Scene Text Detection with Richer Fused Features", IJCAI, pp.516~522 (2020)
- Cui, Mengmeng, "Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition", arXiv preprint arXiv:2106.06960 Jun. 2021, ~ (2021)
- Lee, Junyeop, "On recognizing texts of arbitrary shapes with 2D self-attention", IEEE, 2020, 546~547
- Wan, Zhaoyi, "Textscanner: Reading characters in order for robust scene text recognition", AAAI Conference on Artificial Intelligence, pp.12120~12127 (2020)