method: Samsung Life Insurance2020-10-16

Authors: Dongyoung Kim, Myungsung Kwak

Affiliation: Data Analytics Laboratory (DA Lab), Samsung Life Insurance

Description: A document Text Localization Generative Adversarial Nets (TLGAN) model is utilized to perform the text localization task using SROIE data set. TLGAN learns text-image features via ImageNet pre-trained VGG network in adversarial manner and points out text locations. Note the images were scaled in an arbitrary ratio and the detected coordinates were re-scaled into original image space for the submission.

method: NetEase OCR2020-12-11

Authors: John

Affiliation: NetEase

Description: Our method breaks the task down into two stages´╝îtext area detect and text segmentation´╝îlike maskrcnn. The difference is the first stage in our model just detect the text area not the text lines, the second stage is like dbnet, segment the text area into lines. We merge the two stage into one model and use data augmentation and mutli-scale train and test.

method: Sunshine_OCR2021-03-10

Authors: Sunshine AI Team

Affiliation: Sunshine Insurance Group

Description: We use rot-faster-rcnn/rot-mask-rcnn algorithm which adds rotated rectangle support based on faster-rcnn/mask-rcnn. Firstly ResNet50 backbone + rot-faster-rcnn is used to get a 98.5%+ baseline, then HRNet backone + rot-mask-rcnn +IOU loss + multiscale training&testing is used to get the final score. The data is preprocessed for scale alignment and only augmented by small rotations.
Note: No error fixing/excluding is done on the submit.


Ranking Table

Description Paper Source Code
DateMethodRecallPrecisionHmean
2020-10-16Samsung Life Insurance98.64%99.83%99.23%
2020-12-11NetEase OCR98.37%99.59%98.98%
2021-03-10Sunshine_OCR98.81%98.97%98.89%
2020-08-10BOE_AIoT_CTO98.76%98.92%98.84%
2021-04-01Linklogis_BigData98.72%98.53%98.62%
2019-04-22SCUT-DLVC-Lab-Refinement98.64%98.53%98.59%
2019-04-22Ping An Property & Casualty Insurance Company98.60%98.40%98.50%
2019-04-22H&H Lab97.93%97.95%97.94%
2021-01-2958 OCR10097.64%96.70%97.17%
2020-09-27only PAN96.51%96.80%96.66%
2021-02-01DR Team96.67%96.35%96.51%
2021-01-2858CV97.48%95.43%96.45%
2019-04-22GREAT-OCR Shanghai University96.62%96.21%96.42%
2021-03-08 MDetector96.42%95.91%96.17%
2019-04-23BOE_IOT_AIBD95.95%95.99%95.97%
2019-04-23EM_ocr95.85%96.08%95.97%
2019-05-10Clova OCR96.04%95.79%95.92%
2019-04-21IFLYTEK-textDet_v393.77%95.89%94.81%
2019-04-22A Single-Shot Model for Robust Text Localization93.93%94.80%94.37%
2019-04-22SituTech_OCR93.81%94.18%94.00%
2019-04-23SROIE Fourth Submission92.98%94.99%93.97%
2020-06-15EfficientDet and EAST91.91%95.68%93.76%
2019-04-22HeReceipt-Rotation93.87%93.47%93.67%
2019-04-22Pixellink multi-scale Detection93.07%92.84%92.95%
2019-04-19BiLSTM Based on CTPN91.40%94.03%92.69%
2020-06-25EAST modified90.94%92.63%91.78%
2019-04-17EAST_clip_enhance_896_giou89.69%93.77%91.68%
2019-04-22CITlab Argus Textline Detection92.02%91.34%91.68%
2019-04-19Unet and Morphology Prediction93.28%89.43%91.31%
2019-04-17Textline detection89.85%92.72%91.26%
2019-04-20A Text Localization Method Based on CTPN85.23%88.73%86.94%
2019-04-22MCTPN285.57%87.65%86.59%
2021-04-08test_1.788.24%84.42%86.29%
2019-04-16Vsdnu85.07%87.17%86.11%
2019-04-18CTPN-SROIE81.14%87.23%84.07%
2019-04-22Yolov3_Autohome82.93%83.67%83.30%
2021-04-08base283.94%80.04%81.94%
2021-04-08base383.94%80.04%81.94%
2021-04-08test_1.683.79%80.03%81.87%
2021-04-08base183.71%79.99%81.81%
2019-04-21ICA-IVA81.86%76.43%79.05%
2019-04-22YOLO Text Detector77.29%79.32%78.29%
2021-04-08base477.78%74.18%75.94%
2021-04-08test77.78%74.18%75.94%
2019-04-17Improved yolov3 model68.52%78.23%73.06%
2019-04-22Task 1 - Scanned Receipt Text Localisation (Submitted by Intuit Inc.)71.14%63.76%67.25%
2021-05-10Original CRAFT for SROIE62.73%59.94%61.31%
2019-04-17scene text detection weapon49.61%64.75%56.18%
2019-04-22Unet Segmentation and Watershed56.31%53.46%54.85%
2019-04-22Receipt Info Extracting Task1 zone-dividing32.62%46.48%38.33%
2021-04-13Practicing project for Scientific Research Subject (HCMUS master program)37.02%30.07%33.19%

Ranking Graphic