SOTAVerified

Text Detection

Detecting the text in the image and localise it using a bounding box. The text can be in any shape and size. We need to localise all such instances of text in the entire image along with bounding box for each word.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 121–130 of 595 papers

TitleStatusHype
TextFuseNet: Scene Text Detection with Richer Fused FeaturesCode1
PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional NetworksCode1
ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text DetectionCode1
UnrealText: Synthesizing Realistic Scene Text Images from the Unreal WorldCode1
Deep Relational Reasoning Graph Network for Arbitrary Shape Text DetectionCode1
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve NetworkCode1
Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text DetectionCode1
ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVTCode1
Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation NetworkCode1
Omnidirectional Scene Text Detection with Sequential-free Box DiscretizationCode1
Show:102550
← PrevPage 13 of 60Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ContourNet [69]Precision86.99—Unverified
2DRRG [72]Precision83.87—Unverified
3PSENet [67]Precision78.11—Unverified
4EAST [75]Precision71.48—Unverified
5EASTPrecision70.43—Unverified