Arbitrarily Shaped Scene Text Detection with a Mask Tightness Text Detector

Abstract

Scene text in the environment is complicated. It can exist in arbitrary text fonts, sizes or shapes. Although scene text detection has witnessed considerable progress in recent years, the detection of text with complex shapes, especially curved text, remains challenging. Datasets with adequate samples to overcome the problem presented by curved text (or other irregularly shaped text) have been introduced only recently; however, the performance of the reported methods on these datasets is unsatisfactory. Therefore, detecting arbitrarily shaped text remains a challenging. This motivated us to propose the Mask Tightness Text Detector (Mask TTD) to improve text detection performance. Mask TTD uses a tightness prior and text frontier learning to enhance pixel-wise mask prediction. In addition, it achieves mutual promotion by integrating a branch for the polygonal boundary of each text region, which significantly improves the detection performance of arbitrarily shaped text.

Existing System

Convolutional neural network (CNN), Fully Convolutional Network (FCN)

Proposed System

We summarize our contributions as follows: We propose a systematic framework, namely Mask TTD, which can tightly localize arbitrarily shaped text. We propose a novel tightness prior instance segmentation method, which dynamically adjusts text proposals to cover the entire text region and skillfully utilizes text frontier information to enhance text mask prediction. We propose a novel mutual branch promotion method to improve the text detection performance, which combines the advantages of both direct regression and FCN-based methods. We propose a simple but effective polygonal generation algorithm to transfer the mask score map into a polygon (including a rectangle and quadrangle), which is a prerequisite to evaluate the detection performance on all text datasets. The proposed Mask TTD can achieve state-of-the-art performance on both curved and non-curved datasets.

Architecture

BLOCK DIAGRAM