Pyramid Mask Text Detector

TL;DR

The paper introduces Pyramid Mask Text Detector (PMTD), a novel scene text detection framework that uses pixel-level regression and 3D shape analysis to improve accuracy over existing Mask R-CNN based methods.

Contribution

PMTD reinterprets soft masks in 3D space and employs a plane clustering algorithm for more accurate text box generation, advancing scene text detection techniques.

Findings

Achieves an F-measure of 80.13% on ICDAR 2017 MLT dataset.

Outperforms state-of-the-art scene text detection methods.

Provides consistent and noticeable performance improvements.

Abstract

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.