Who leads the urdudoc benchmark?

ContourNet [69] currently leads urdudoc with a score of 88.68 on Recall.

What is the state-of-the-art score on urdudoc?

The state-of-the-art result on urdudoc is 88.68 (Recall), achieved by ContourNet [69] as of 2023.

How many models are tracked on urdudoc?

Codesota tracks 5 models on urdudoc across 3 metrics.

When was the urdudoc leaderboard last updated?

The urdudoc leaderboard on Codesota includes results through 2023.

Codesota · Benchmark · urdudocHome/Leaderboards/Vision & Documents/Document OCR/urdudoc

Unknown

urdudoc.

Name: urdudoc Benchmark Results
Creator: Unknown
Published: 2023-01-01
License: https://creativecommons.org/licenses/by/4.0/

urdudoc is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for urdudoc.

Paper ↗Leaderboard ↓

§ 01 · Leaderboard

Results by metric.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

Recall

Recall is the reported evaluation metric for urdudoc. 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 Recallverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	ContourNet [69] From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	88.68	2023	Paper ↗Code ↗	Looks wrong?
02	DRRG [72] From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	84.72	2023	Paper ↗Code ↗	Looks wrong?
03	PSENet [67] From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	77.91	2023	Paper ↗Code ↗	Looks wrong?
04	EAST [75] From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	72.56	2023	Paper ↗Code ↗	Looks wrong?

H Mean

H Mean is the reported evaluation metric for urdudoc. 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 H Meanverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	ContourNet [69] From Table 1: Experimental results on UrduDoc, UTRNet paper (ICDAR 2023)	verified	86.99	2023	Paper ↗Code ↗Source ↗	Looks wrong?
02	DRRG [72] From Table 1: Experimental results on UrduDoc, UTRNet paper (ICDAR 2023)	verified	83.87	2023	Paper ↗Code ↗Source ↗	Looks wrong?
03	PSENet [67] From Table 1: Experimental results on UrduDoc, UTRNet paper (ICDAR 2023)	verified	78.11	2023	Paper ↗Code ↗Source ↗	Looks wrong?
04	EAST [75] From Table 1: Experimental results on UrduDoc, UTRNet paper (ICDAR 2023)	verified	71.48	2023	Paper ↗Code ↗Source ↗	Looks wrong?

Precision

Precision is the reported evaluation metric for urdudoc. 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 Precisionverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	ContourNet [69] From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	86.99	2023	Paper ↗Code ↗	Looks wrong?
02	DRRG [72] From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	83.87	2023	Paper ↗Code ↗	Looks wrong?
03	PSENet [67] From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	78.11	2023	Paper ↗Code ↗	Looks wrong?
04	EAST [75] From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	71.48	2023	Paper ↗Code ↗	Looks wrong?
05	EAST From paper: UTRNet: High-Resolution Urdu Text Recognition In Printed Documents	verified	70.43	2023	Paper ↗Code ↗	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

← Back to Document OCR