Shape Robust Text Detection With Progressive Scale Expansion Network

By Xiang-Yang Li, Wenhai Wang, Wenbo Hou, Ruo-Ze Liu, Tong Lu, Jian Yang. Computer Vision and Pattern Recognition, 2018

722 citations recorded by the source corpus.

Scene text detection has witnessed rapid progress especially with the recent development of convolutional neural networks. However, there still exists two challenges which prevent the algorithm into industry applications. On the one hand, most of the state-of-art algorithms require quadrangle bounding box which is in-accurate to locate the texts with arbitrary shape. On the other hand, two text instances which are close to each other may lead to a false detection which covers both instances. Traditionally, the segmentation-based approach can relieve the first problem but usually fail to solve the second challenge. To address these two challenges, in this paper, we propose a novel Progressive Scale Expansion Network (PSENet), which can precisely detect text instances with arbitrary shapes. More specifically, PSENet generates the different scale of kernels for each text instance, and gradually expands the minimal scale kernel to the text instance with the complete shape. Due to the fact that there are large geometrical margins among the minimal scale kernels, our method is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances. Extensive experiments on CTW1500, Total-Text, ICDAR 2015 and ICDAR 2017 MLT validate the effectiveness of PSENet. Notably, on CTW1500, a dataset full of long curve texts, PSENet achieves a F-measure of 74.3% at 27 FPS, and our best F-measure (82.2%) outperforms state-of-art algorithms by 6.6%. The code will be released in the future.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/7b50853560e62e94f4d20426a6ddb43b8c9b314f

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

1. Chunhua Shen
2. Luc Van Gool
3. Dacheng Tao
4. Xiaogang Wang
5. Ling Shao
6. Xiang Bai
7. Yu Qiao
8. Ming-Hsuan Yang

In Media Technology

1. Cong Yao
2. Xiang Bai
3. Minghui Liao
4. Zhaoyi Wan
5. Kai Chen
6. Chunhua Shen
7. Lianwen Jin
8. Yuliang Liu

Citations in the corpus

• Structured Multimodal Attentions for TextVQA (2020, background): “Most works address it separately by designing high performance text detector [31], [32], [33], [34] and sophisticated word recognizer [35], [36], [37], [38], [39], which can be combined together to obtain text contents in an image finally.”
• Real-time Scene Text Detection with Differentiable Binarization (2019, methodology): “Take two recent state-of-the-art methods for scene text detection as examples: PSENet (Wang et al. 2019a) proposed the post-processing of progressive scale expansion for improving the detection accuracies; Pixel embedding in (Tian et al. 2019) is used for clustering the pixels based on the segmentat”
• Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (2021, background): “Therefore, we believe there are many potential technologies and applications ( e.g. , OCR [68, 66, 69], 3D [28, 11, 27] and medical [15, 16, 29] image analysis) to be explored in the future, and hope that PVT could serve as a good starting point.”
• 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.”
• Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network (2019, methodology): “Arbitrary-shaped text detection, one of the most challenging tasks in text detection, is receiving more and more research attention Some new methods [31, 35, 49, 24] have been put forward to detect curve text instance.”
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation (2020, background): “Asymmetrical Residual Block Motivated by the observation and conclusion in [35, 9], the asymmetrical residual block strengthens the horizontal and vertical kernels, which matches the point distribution of object in the driving scene and explicitly makes the skeleton of the kernel powerful,”
• Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion (2022, methodology): “For instance, PSENet [49] applied a progressive scale expansion algorithm to integrate multi-scale results and Tian et al. [46] adopted pixel embedding to group the pixels by calculating the feature distances among pixels.”