AI Paper Atlas

Research map / Detection and segmentation / CNN features

An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition

Baoguang Shi, Xiang Bai, Cong Yao

TPAMI 2016 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 3,346 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use CRNN instead of the 90k-dictionary classifierscene text recognizer · IIIT5k (lexicon 50)accuracy (%): 97.1 -> 97.6Improved
use CRNN instead of the 90k-dictionary classifierscene text recognizer · SVT (lexicon 50)accuracy (%): 95.4 -> 96.4Improved
use CRNN instead of the 90k-dictionary classifierscene text recognizer · IC03 (Full lexicon)accuracy (%): 98.6 -> 97.6Hurt
use CRNN instead of the 90k-dictionary classifier without lexiconscene text recognizer · IC03 (no lexicon)accuracy (%): 93.1 -> 89.4Hurt
use CRNN instead of the unconstrained 304M model without lexiconscene text recognizer · SVT (no lexicon)accuracy (%): 71.7 -> 80.8Improved
use CRNN with 8.3M parameters instead of 304M-parameter modelscene text recognizer · model sizeparameters: 304M -> 8.3MImproved
use CRNN instead of Capella Scan on real-world scorespitch recognition · Pitch recognition (Real-World)fragment accuracy (%): 43.5% -> 84.0%Improved
use CRNN instead of PhotoScore on clean scorespitch recognition · Pitch recognition (Clean)fragment accuracy (%): 55.0% -> 74.6%Improved
use CRNN instead of Capella Scan on synthesized scorespitch recognition · Pitch recognition (Synthesized)average edit distance: 2.31 -> 0.30Improved
increase lexicon search radius delta (ablation)lexicon-based transcription · IC03 (lexicon 50k)accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy