method: BreSee OCR2021-07-01
Authors: Mengyue Shao, Jie Wu, Jiling Wu, Tianpeng Li, Linzhi Zhuang
Affiliation: BreSee AI Lab, Zhejiang Sci-Tech University
Description: In this task1, we follow YOLOv5 and DBNet as the base model to do detection task. And some targeted optimization of models have been carried out according to the data set provided, and better results have been achieved. The two basic models are fused to reach the final result.
method: Linklogis_BeeAI2021-07-20
Authors: Guopeng Wang, Juntao Zhang， WeiJie Luo， Keshu Chen，Chong Xie，Xiuyun Mo, Yan Xu
Affiliation: Linklogis_BeeAI Team
Description: We have modified certain parts of frameworks in DBnet, and apply Recall-Loss to improve its precision as well as accelerate inference speed. Meanwhile, we trained a handwritten model to remove handwritten characters.
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.
| Date | Method | Recall | Precision | Hmean | |||
|---|---|---|---|---|---|---|---|
| 2021-07-01 | BreSee OCR | 99.15% | 99.40% | 99.28% | |||
| 2021-07-20 | Linklogis_BeeAI | 99.20% | 99.30% | 99.25% | |||
| 2020-10-16 | Samsung Life Insurance | 98.64% | 99.83% | 99.23% | |||
| 2020-12-11 | NetEase OCR | 98.37% | 99.59% | 98.98% | |||
| 2021-03-10 | Sunshine_OCR | 98.81% | 98.97% | 98.89% | |||
| 2020-08-10 | BOE_AIoT_CTO | 98.76% | 98.92% | 98.84% | |||
| 2021-04-01 | Linklogis_BigData | 98.72% | 98.53% | 98.62% | |||
| 2019-04-22 | SCUT-DLVC-Lab-Refinement | 98.64% | 98.53% | 98.59% | |||
| 2019-04-22 | Ping An Property & Casualty Insurance Company | 98.60% | 98.40% | 98.50% | |||
| 2019-04-22 | H&H Lab | 97.93% | 97.95% | 97.94% | |||
| 2022-05-09 | A modified CTPN model 2.0 | 97.52% | 97.40% | 97.46% | |||
| 2021-05-23 | Gem AI - OCR Team | 98.01% | 96.79% | 97.40% | |||
| 2021-01-29 | 58 OCR100 | 97.64% | 96.70% | 97.17% | |||
| 2021-10-22 | A modified CTPN model 1.0 | 97.16% | 97.10% | 97.13% | |||
| 2020-09-27 | only PAN | 96.51% | 96.80% | 96.66% | |||
| 2021-02-01 | DR Team | 96.67% | 96.35% | 96.51% | |||
| 2021-01-28 | 58CV | 97.48% | 95.43% | 96.45% | |||
| 2019-04-22 | GREAT-OCR Shanghai University | 96.62% | 96.21% | 96.42% | |||
| 2021-03-08 | MDetector | 96.42% | 95.91% | 96.17% | |||
| 2021-06-30 | Granville ocr | 96.02% | 95.96% | 95.99% | |||
| 2019-04-23 | BOE_IOT_AIBD | 95.95% | 95.99% | 95.97% | |||
| 2019-04-23 | EM_ocr | 95.85% | 96.08% | 95.97% | |||
| 2019-05-10 | Clova OCR | 96.04% | 95.79% | 95.92% | |||
| 2019-04-21 | IFLYTEK-textDet_v3 | 93.77% | 95.89% | 94.81% | |||
| 2019-04-22 | A Single-Shot Model for Robust Text Localization | 93.93% | 94.80% | 94.37% | |||
| 2019-04-22 | SituTech_OCR | 93.81% | 94.18% | 94.00% | |||
| 2019-04-23 | SROIE Fourth Submission | 92.98% | 94.99% | 93.97% | |||
| 2020-06-15 | EfficientDet and EAST | 91.91% | 95.68% | 93.76% | |||
| 2019-04-22 | HeReceipt-Rotation | 93.87% | 93.47% | 93.67% | |||
| 2019-04-22 | Pixellink multi-scale Detection | 93.07% | 92.84% | 92.95% | |||
| 2019-04-19 | BiLSTM Based on CTPN | 91.40% | 94.03% | 92.69% | |||
| 2020-06-25 | EAST modified | 90.94% | 92.63% | 91.78% | |||
| 2019-04-17 | EAST_clip_enhance_896_giou | 89.69% | 93.77% | 91.68% | |||
| 2019-04-22 | CITlab Argus Textline Detection | 92.02% | 91.34% | 91.68% | |||
| 2023-12-12 | ViTLP | 91.62% | 91.68% | 91.65% | |||
| 2019-04-19 | Unet and Morphology Prediction | 93.28% | 89.43% | 91.31% | |||
| 2019-04-17 | Textline detection | 89.85% | 92.72% | 91.26% | |||
| 2021-05-17 | PhucPH | 91.18% | 89.69% | 90.43% | |||
| 2019-04-20 | A Text Localization Method Based on CTPN | 85.23% | 88.73% | 86.94% | |||
| 2019-04-22 | MCTPN2 | 85.57% | 87.65% | 86.59% | |||
| 2021-04-08 | test_1.7 | 88.24% | 84.42% | 86.29% | |||
| 2019-04-16 | Vsdnu | 85.07% | 87.17% | 86.11% | |||
| 2019-04-18 | CTPN-SROIE | 81.14% | 87.23% | 84.07% | |||
| 2019-04-22 | Yolov3_Autohome | 82.93% | 83.67% | 83.30% | |||
| 2021-04-08 | base2 | 83.94% | 80.04% | 81.94% | |||
| 2021-04-08 | base3 | 83.94% | 80.04% | 81.94% | |||
| 2021-04-08 | test_1.6 | 83.79% | 80.03% | 81.87% | |||
| 2021-04-08 | base1 | 83.71% | 79.99% | 81.81% | |||
| 2019-04-21 | ICA-IVA | 81.86% | 76.43% | 79.05% | |||
| 2019-04-22 | YOLO Text Detector | 77.29% | 79.32% | 78.29% | |||
| 2021-04-08 | base4 | 77.78% | 74.18% | 75.94% | |||
| 2021-04-08 | test | 77.78% | 74.18% | 75.94% | |||
| 2019-04-17 | Improved yolov3 model | 68.52% | 78.23% | 73.06% | |||
| 2019-04-22 | Task 1 - Scanned Receipt Text Localisation (Submitted by Intuit Inc.) | 71.14% | 63.76% | 67.25% | |||
| 2021-05-10 | Original CRAFT for SROIE | 62.73% | 59.94% | 61.31% | |||
| 2019-04-17 | scene text detection weapon | 49.61% | 64.75% | 56.18% | |||
| 2019-04-22 | Unet Segmentation and Watershed | 56.31% | 53.46% | 54.85% | |||
| 2019-04-22 | Receipt Info Extracting Task1 zone-dividing | 32.62% | 46.48% | 38.33% | |||
| 2021-04-13 | Practicing project for Scientific Research Subject (HCMUS master program) | 37.02% | 30.07% | 33.19% |