Character Region Awareness for Text Detection

By Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee. Computer Vision and Pattern Recognition, 2019

980 citations recorded by the source corpus.

Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level bounding boxes exhibit limitations in representing the text region in an arbitrary shape. In this paper, we propose a new scene text detection method to effectively detect text area by exploring each character and affinity between characters. To overcome the lack of individual character level annotations, our proposed framework exploits both the given character-level annotations for synthetic images and the estimated character-level ground-truths for real images acquired by the learned interim model. In order to estimate affinity between characters, the network is trained with the newly proposed representation for affinity. Extensive experiments on six benchmarks, including the TotalText and CTW-1500 datasets which contain highly curved texts in natural images, demonstrate that our character-level text detection significantly outperforms the state-of-the-art detectors. According to the results, our proposed method guarantees high flexibility in detecting complicated scene text images, such as arbitrarily-oriented, curved, or deformed texts.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/206b2aeb81b29463968b8deb1efce51941f18208

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Real-time Scene Text Detection with Differentiable Binarization (2019, neutral): “(Lyu et al. 2018b) 87.6 76.2 81.5 5.7 TextSnake (Long et al. 2018) 83.2 73.9 78.3 1.1 (Xue, Lu, and Zhan 2018) 83.0 77.4 80.1 - (Xue, Lu, and Zhang 2019) 87.4 76.7 81.7 - CRAFT (Baek et al. 2019) 88.2 78.2 82.9 8.6 SAE (Tian et al. 2019) 84.2 81.7 82.9 -”
COFAR: Commonsense and Factual Reasoning in Image Search (2022, methodology): “We obtain these likelihood scores by using off-the-shelf approaches such as CRAFT+CRNN (Baek et al., 2019; Shi et al., 2017) for detecting and recognizing business brand mentions in the image, VGG face (Parkhi et al.”
ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network (2020, methodology): “Compared to segmentation-based methods [41, 46, 1, 39, 47, 29], regression-based methods are more direct solutions to oriented or curved text detection, e.”
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets (2023, methodology): “To this end, we applied the off-the-shelf text-detector CRAFT [5] to annotate the start, middle, and end frames of each clip in our dataset with bounding box information on all written text.”
Scene Text Detection and Recognition: The Deep Learning Era (2018, background): “According to Baek et al. (2019a), most researchers are actually using different subsets when they refer to the same dataset, causing discrepancies in performance.”
Multiple Transformer Mining for VizWiz Image Caption (2021, methodology): “The effectiveness of OCR in image captioning is approved [4], thus several open source OCR solutions have been evaluated, and ﬁnally [2] and [1] are leveraged in our method.”
OCR-Free Document Understanding Transformer (2021, methodology): “For example, a recent advanced OCR-based model [4,3] requires more than 80M parameters.”
Towards Accurate Text-based Image Captioning with Content Diversity Exploration (2021, background): “Recently, M4CCaptioner [40] tries to use additional OCR tools [4, 6, 31] to recognise texts in images.”
Confidence-aware Non-repetitive Multimodal Transformers for TextCaps (2020, positive): “To solve this problem, our model adapts CRAFT (Baek et al. 2019b) and ABCNet (Liu et al.”
CORD: A Consolidated Receipt Dataset for Post-OCR Parsing (2019, background): “Recently, deep learning in computer vision domain has significantly improved the performances of OCR [3, 4].”
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection (2019, neutral): “7 CRAFT [48] 88.”