Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection

By Yuliang Liu, Lianwen Jin. 2017

322 citations recorded by the source corpus.

Detecting incidental scene text is a challenging task because of multi-orientation, perspective distortion, and variation of text size, color and scale. Retrospective research has only focused on using rectangular bounding box or horizontal sliding window to localize text, which may result in redundant background noise, unnecessary overlap or even information loss. To address these issues, we propose a new Convolutional Neural Networks (CNNs) based method, named Deep Matching Prior Network (DMPNet), to detect text with tighter quadrangle. First, we use quadrilateral sliding windows in several specific intermediate convolutional layers to roughly recall the text with higher overlapping area and then a shared Monte-Carlo method is proposed for fast and accurate computing of the polygonal areas. After that, we designed a sequential protocol for relative regression which can exactly predict text with compact quadrangle. Moreover, a auxiliary smooth Ln loss is also proposed for further regressing the position of text, which has better overall performance than L2 loss and smooth L1 loss in terms of robustness and stability. The effectiveness of our approach is evaluated on a public word-level, multi-oriented scene text database, ICDAR 2015 Robust Reading Competition Challenge 4 Incidental scene text localization. The performance of our method is evaluated by using F-measure and found to be 70.64%, outperforming the existing state-of-the-art method with F-measure 63.76%.

Subfields: Computer Vision and Pattern Recognition

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. Xiang Bai
2. Cong Yao
3. Minghui Liao
4. Xue Yang
5. Xin He
6. Chunhua Shen
7. Shangbang Long
8. Yu Qiao

Citations in the corpus

• All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting (2019, background): “In (Liu et al. 2018; Li, Wang, and Shen 2017; He et al. 2018; Busta et al. 2017; Liu and Jin 2017; He et al. 2017), the detected bounding box of each text instance is represented with a rectangle, which only can tightly cover straight text instances.”
• TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network (2018, methodology): “rk to learn text features, which has shown signicant performance improvement. Inspired by recent advances in generic object detection [35][19][29], the state-of-the-art text detection approaches [45][31] are designed to directly predict word-level bounding boxes, which simplies the previous multi-st”
• Scene Text Detection and Recognition: The Deep Learning Era (2018, methodology): “…[125] Separately trained; passing cropped images: [7] Jointly trained; passing cropped feature maps; gradients propagate end-to-end: [11] [45] [73] [82] [89] (1) Synthesize cropped images: [55] (2) Rendering with natural images: [38] (3) Selective semantic segmentation: [165] Others (1)…”
• Single Shot Text Detector with Regional Attention (2017, methodology): “ work reliably on multi-scale and multiorientation text with single-scale images. Our text detector achieves an F-measure of 77% on the ICDAR 2015 benchmark, advancing the state-of-the-art results in [18,28]. Demo is available at: http://sstd.whuang.org/. 1. Introduction Reading text in the wild has”
• TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (2018, unknown): “4 DMPNet [43] 69 .”
• Sliding Line Point Regression for Shape Robust Scene Text Detection (2018, methodology): “Some methods [6] [7] [8] [9] [10] [11] [12] also tried to solve arbitrary-oriented text detection problem.”
• TextBoxes++: A Single-Shot Oriented Scene Text Detector (2018, methodology): “Specifically, TextBoxes++ outperforms [42] by 3.”
• Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection (2019, methodology): “[31] propose to use quadrangle sliding windows to match texts with perspective transformation.”
• Learning Modulated Loss for Rotated Object Detection (2019, methodology): “Algorithm 1 is similar to the counterpart proposed in Deep Matching Prior Network [46].”
• Arbitrary-Oriented Scene Text Detection via Rotation Proposals (2017, unknown): “4 s SCUT_DMPNet [57] 68 73 71 Yao et al.”
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, background): “A large number of methods have been proposed to detect scene text [7, 36, 37, 50, 19, 23, 54, 21, 47, 54, 56, 30, 52, 55, 34, 15, 48, 43, 57, 16, 35, 31].”
• Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation (2019, methodology): “One-stage methods including Deep Direct Regression [5], TextBox [12], TextBoxes++ [11], DMPNet [16], SegLink [24] and EAST [34], directly estimate bounding boxes of text regions in one step.”
• Real-time Scene Text Detection with Differentiable Binarization (2019, unknown): “TextBoxes++ (Liao, Shi, and Bai 2018) and DMPNet (Liu and Jin 2017) applied quadrilater-als regression to detect multi-oriented text.”
• Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion (2022, methodology): “Boxes++ [24] and DMPNet [31] applied quadrilaterals regression to detect multi-oriented text.”