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 581–590 of 595 papers

TitleStatusHype
Lost Shopping! Monocular Localization in Large Indoor Spaces—0
Incidental Scene Text Understanding: Recent Progresses on ICDAR 2015 Robust Reading Competition Challenge 4—0
Text-Attentional Convolutional Neural Networks for Scene Text Detection—0
OCR accuracy improvement on document images through a novel pre-processing approach—0
ICDAR 2015 Text Reading in the Wild Competition—0
Symmetry-Based Text Line Detection in Natural Scenes—0
Discrete Wavelet Transform and Gradient Difference based approach for text localization in videos—0
Video Text Localization with an emphasis on Edge Features—0
A Fast Hierarchical Method for Multi-script and Arbitrary Oriented Scene Text Extraction—0
Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition—0
Show:102550
← PrevPage 59 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