A Fast Uyghur Text Detector for Complex Background Images

By Chenggang Clarence Yan, Hongtao Xie, Jianjun Chen, Zhengjun Zha, Xinhong Hao, Yongdong Zhang, Qionghai Dai. 2018

167 citations recorded by the source corpus.

Uyghur text localization in images with complex backgrounds is a challenging yet important task for many applications. Generally, Uyghur characters in images consist of strokes with uniform features, and they are distinct from backgrounds in color, intensity, and texture. Based on these differences, we propose a FASTroke keypoint extractor, which is fast and stroke-specific. Compared with the commonly used MSER detector, FASTroke produces less than twice the amount of components and recognizes at least 10% more characters. While the characters in a line usually have uniform features such as size, color, and stroke width, a component similarity based clustering is presented without component-level classification. It incurs no extra errors by incorporating a component-level classifier while the computing cost is drastically reduced. The experiments show that the proposed method can achieve the best performance on the UICBI-500 benchmark dataset.

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. Cheng Deng
2. Tongliang Liu
3. Dacheng Tao
4. Erkun Yang
5. Yue Gao
6. Chenggang Clarence Yan
7. Ke Tang
8. Ting Hu

Citations in the corpus

• Adversarial Examples: Attacks and Defenses for Deep Learning (2017, background): “CNNs have shown incredible successes in computer vision tasks, such as image classification [1], [39], object detection [4], [40], text recognition [41], [42], and semantic segmentation [43], [44].”
• Stochastic Gradient Descent for Nonconvex Learning Without Bounded Gradient Assumptions (2019, background): “This boundedness assumption in the literature depends on the realization of the optimization process, which is hard to check in practical application domains including computer vision [20].”
• Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search (2020, background): “S IMILARITY search is a fundamental research topic in numerous computer vision and multimedia applications, including object recognition [1], information retrieval [2]–[19], image classification [20], [21], motion estimation [22], and image understanding [23], [24].”
• Deep Multi-View Enhancement Hashing for Image Retrieval (2020, methodology): “The image retrieval mentioned in this paper refers to content-based visual information retrieval [26], [27], [28].”