Scene Text Recognition

121 papers with code • 15 benchmarks • 27 datasets

See Scene Text Detection for leaderboards in this task.

Libraries

Use these libraries to find Scene Text Recognition models and implementations

Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition

wzx99/clipocr 8 Oct 2023

In this paper, we explore the potential of the Contrastive Language-Image Pretraining (CLIP) model in scene text recognition (STR), and establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) to leverage both visual and linguistic knowledge in CLIP.

29
08 Oct 2023

Towards Large-scale Building Attribute Mapping using Crowdsourced Images: Scene Text Recognition on Flickr and Problems to be Solved

ya0-sun/str-berlin 14 Sep 2023

This work addresses the challenges in applying Scene Text Recognition (STR) in crowdsourced street-view images for building attribute mapping.

2
14 Sep 2023

Orientation-Independent Chinese Text Recognition in Scene Images

fudanvi/fudanocr 3 Sep 2023

We conduct experiments on a scene dataset for benchmarking Chinese text recognition, and the results demonstrate that the proposed method can indeed improve performance through disentangling content and orientation information.

301
03 Sep 2023

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

fudanvi/fudanocr ICCV 2023

However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text Recognition (CTR).

301
03 Sep 2023

DTrOCR: Decoder-only Transformer for Optical Character Recognition

Swall0w/dtrocr 30 Aug 2023

Typical text recognition methods rely on an encoder-decoder structure, in which the encoder extracts features from an image, and the decoder produces recognized text from these features.

51
30 Aug 2023
603
24 Aug 2023

Relational Contrastive Learning for Scene Text Recognition

thundervvv/rclstr 1 Aug 2023

We argue that such prior contextual information can be interpreted as the relations of textual primitives due to the heterogeneous text and background, which can provide effective self-supervised labels for representation learning.

15
01 Aug 2023

Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition

alibabaresearch/advancedliteratemachinery 25 Jul 2023

Specifically, MGP-STR achieves an average recognition accuracy of $94\%$ on standard benchmarks for scene text recognition.

603
25 Jul 2023

Context Perception Parallel Decoder for Scene Text Recognition

PaddlePaddle/PaddleOCR 23 Jul 2023

We first present an empirical study of AR decoding in STR, and discover that the AR decoder not only models linguistic context, but also provides guidance on visual context perception.

37,721
23 Jul 2023

Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement

csguoh/lemma 19 Jul 2023

Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success.

36
19 Jul 2023