CM-Net: Concentric Mask based Arbitrary-Shaped Text Detection

TL;DR

CM-Net is a novel real-time text detection framework that efficiently combines concentric masks and multi-perspective features to accurately detect arbitrary-shaped text with high speed.

Contribution

The paper introduces CM-Net, a new framework that improves both speed and accuracy in arbitrary-shaped text detection using concentric masks and multi-perspective feature learning.

Findings

Outperforms existing real-time methods in speed and accuracy.

Effectively fits arbitrary-shaped text contours with concentric masks.

Demonstrates robustness and efficiency across multiple datasets.

Abstract

Recently fast arbitrary-shaped text detection has become an attractive research topic. However, most existing methods are non-real-time, which may fall short in intelligent systems. Although a few real-time text methods are proposed, the detection accuracy is far behind non-real-time methods. To improve the detection accuracy and speed simultaneously, we propose a novel fast and accurate text detection framework, namely CM-Net, which is constructed based on a new text representation method and a multi-perspective feature (MPF) module. The former can fit arbitrary-shaped text contours by concentric mask (CM) in an efficient and robust way. The latter encourages the network to learn more CM-related discriminative features from multiple perspectives and brings no extra computational cost. Benefiting the advantages of CM and MPF, the proposed CM-Net only needs to predict one CM of the text instance to rebuild the text contour and achieves the best balance between detection accuracy and speed compared with previous works. Moreover, to ensure that multi-perspective features are effectively learned, the multi-factor constraints loss is proposed. Extensive experiments demonstrate the proposed CM is efficient and robust to fit arbitrary-shaped text instances, and also validate the effectiveness of MPF and constraints loss for discriminative text features recognition. Furthermore, experimental results show that the proposed CM-Net is superior to existing state-of-the-art (SOTA) real-time text detection methods in both detection speed and accuracy on MSRA-TD500, CTW1500, Total-Text, and ICDAR2015 datasets.