Reproduce “A Novel Integrated Framework for Learning both Text Detection and Recognition” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Wanchen Sui, Qing Zhang, Jun Yang, Wei Chu
The authors present a jointly trained text detection and recognition system that shares full-image features between an R-FCN detector and a recognizer. Its Fully Convolutional Recognizer replaces recurrent sequence layers with convolutional layers. On Chinese business cards, line-level end-to-end F-measure rises from 0.6905 without sharing to 0.7223 sharing through conv3_3; this comparison does not isolate sharing’s effect.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.