Codesota · Benchmark · document-layout-recognition-challenge-testHome/Leaderboards/Vision & Documents/Document Layout Analysis/document-layout-recognition-challenge-test
Unknown

document-layout-recognition-challenge-test.

The RDCL2019 test set from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts. Comprises 85 scanned page images from contemporary magazines and technical/scientific publications (PRImA Layout Analysis Dataset). Evaluation measures region segmentation and classification using Weighted F1-score across layout classes. A continuous competition allowing post-2019 submissions via the Aletheia evaluation tool.

Paper ↗Leaderboard ↓
§ 01 · Leaderboard

Results by metric.

Only 3 models on this benchmark
Help build the community leaderboard — submit your model results.
Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Figure

Figure is the reported evaluation metric for document-layout-recognition-challenge-test. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Figureverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01fglihai
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.972019Source ↗Looks wrong?
02USYD NLP_CS29-2
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.962019Source ↗Looks wrong?
03Faster R-CNN
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.952019Source ↗Looks wrong?

Table

Table is the reported evaluation metric for document-layout-recognition-challenge-test. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Tableverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01USYD NLP_CS29-2
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.962019Source ↗Looks wrong?
02fglihai
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.962019Source ↗Looks wrong?
03Faster R-CNN
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.952019Source ↗Looks wrong?

Text

Text is the reported evaluation metric for document-layout-recognition-challenge-test. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Textverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01USYD NLP_CS29-2
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.932019Source ↗Looks wrong?
02fglihai
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.932019Source ↗Looks wrong?
03Faster R-CNN
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.922019Source ↗Looks wrong?

Overall

Overall is the reported evaluation metric for document-layout-recognition-challenge-test. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Overallverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01fglihai
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.922019Source ↗Looks wrong?
02USYD NLP_CS29-2
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.922019Source ↗Looks wrong?
03Faster R-CNN
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.912019Source ↗Looks wrong?

List

List is the reported evaluation metric for document-layout-recognition-challenge-test. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Listverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01USYD NLP_CS29-2
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.902019Source ↗Looks wrong?
02fglihai
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.902019Source ↗Looks wrong?
03Faster R-CNN
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.892019Source ↗Looks wrong?

Title

Title is the reported evaluation metric for document-layout-recognition-challenge-test. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Titleverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01fglihai
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.842019Source ↗Looks wrong?
02USYD NLP_CS29-2
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.842019Source ↗Looks wrong?
03Faster R-CNN
Result from the ICDAR 2019 Competition on Recognition of Documents with Complex Layouts (RDCL2019). Segmentation + Classification scenario (Scenario B). F1 weighted score.
verified0.822019Source ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Document Layout Analysis