[1507.05717] An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition. A novel neural network architecture, which integrates feature extraction, sequence modeling and transcription into a unified framework, is proposed. Compared with previous systems for scene text recognition, the proposed architecture possesses four distinctive properties: (1) It is end-to-end trainable, in contrast to most of the existing algorithms whose components are separately trained and tuned. (2) It naturally handles sequences in arbitrary lengths, involving no character segmentation or horizontal scale normalization. (3) It is not confined to any predefined lexicon and achieves remarkable performances in both lexicon-free and lexicon-based scene text recognition tasks. (4) It generates an effective yet much smaller model, which

1 mentions: @Nextremer_nb_o
Date:

Referring Tweets

@Nextremer_nb_o
@Nextremer_nb_o 文字認識は "Real-time Scene Text Detection with Differentiable Binarization" t.co/RFt3B0Otdr CRNN構造でCNNで特徴抽出+バイリテラルLSTMの組み合わせ。なるほど、この構造だと可変のサイズを扱えるのね。すごいー。

Related Entries

tf.estimator.EvalSpec  |  TensorFlow Core v2.4.1
Read more tf.estimator.EvalSpec  |  TensorFlow Core v2.4.1
0 users, 1 mentions 2021/05/07 13:58
GitHub - SysCV/bdd100k-models: Model Zoo of BDD100K Dataset
Read more GitHub - SysCV/bdd100k-models: Model Zoo of BDD100K Dataset
0 users, 1 mentions 2022/04/28 09:09
GitHub - NobuoTsukamoto/meta-tensorflow-lite at coral_edgetpu
Read more GitHub - NobuoTsukamoto/meta-tensorflow-lite at coral_edgetpu
0 users, 1 mentions 2022/07/04 13:38
Tensorflow version 2.9.1 seems to be incompatible with cuda version 11.2 · Issue #3015 · googlecolab...
Read more Tensorflow version 2.9.1 seems to be incompatible with cuda version 11.2 · Issue #3015 · googlecolab...
0 users, 1 mentions 2022/08/18 15:09
[2002.01276] GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition
Read more [2002.01276] GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition
0 users, 1 mentions 2022/08/24 13:37
Add MAXIM family of models (#136) · tensorflow/tfhub.dev@21a1e70 · GitHub
Read more Add MAXIM family of models (#136) · tensorflow/tfhub.dev@21a1e70 · GitHub
0 users, 1 mentions 2022/10/25 00:09

ML-Newsについて

機械学習の技術に関する情報は流速も早いし、分野も多様でキャッチアップが大変です。Twitterで機械学習用のリストを作っても、普段は機械学習以外の話題が多く流れており、効率的に情報収集するのは困難です。

ML-NewsはSNSを情報源とした機械学習に特化したニュースサイトです。機械学習に関する論文ブログライブラリコンペティション発表資料勉強会などの最新の情報を効率的に収集できます。

機械学習を応用した自然言語処理、画像認識、情報検索などの分野の情報や機械学習で必要になるデータ基盤やMLOpsの話題もカバーしています。
安定したサイト運営のためにGitHub sponsorを募集しています。

お知らせ

  • 2021/12/31: デザインを刷新しました
  • 2021/04/08: 日本語Kaggleのカテゴリを新設しました