Pyramid Mask Text Detector

28 Mar 2019  ·  Jingchao Liu, Xuebo Liu, Jie Sheng, Ding Liang, Xin Li, Qingjie Liu ·

Scene text detection, an essential step of scene text recognition system, is to locate text instances in natural scene images automatically. Some recent attempts benefiting from Mask R-CNN formulate scene text detection task as an instance segmentation problem and achieve remarkable performance. In this paper, we present a new Mask R-CNN based framework named Pyramid Mask Text Detector (PMTD) to handle the scene text detection. Instead of binary text mask generated by the existing Mask R-CNN based methods, our PMTD performs pixel-level regression under the guidance of location-aware supervision, yielding a more informative soft text mask for each text instance. As for the generation of text boxes, PMTD reinterprets the obtained 2D soft mask into 3D space and introduces a novel plane clustering algorithm to derive the optimal text box on the basis of 3D shape. Experiments on standard datasets demonstrate that the proposed PMTD brings consistent and noticeable gain and clearly outperforms state-of-the-art methods. Specifically, it achieves an F-measure of 80.13% on ICDAR 2017 MLT dataset.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Scene Text Detection ICDAR 2015 PMTD F-Measure 89.33 # 10
Precision 91.3 # 8
Recall 87.43 # 10
Scene Text Detection ICDAR 2017 MLT PMTD* Precision 84.42 # 1
Recall 76.25 # 2
F-Measure 80.13% # 1