A Novel Scene Text Detection Algorithm Based On Convolutional Neural Network

TL;DR

This paper introduces a new CNN-based scene text detection method utilizing I-MSER for candidate region extraction, improving independence and completeness of text regions, and demonstrating superior performance on standard datasets.

Contribution

The paper presents a novel I-MSER based candidate text region extractor combined with a multi-layer CNN for improved scene text detection.

Findings

Enhanced detection accuracy on ICDAR datasets

Improved independence and completeness of candidate regions

Outperforms existing text detection algorithms

Abstract

Candidate text region extraction plays a critical role in convolutional neural network (CNN) based text detection from natural images. In this paper, we propose a CNN based scene text detection algorithm with a new text region extractor. The so called candidate text region extractor I-MSER is based on Maximally Stable Extremal Region (MSER), which can improve the independency and completeness of the extracted candidate text regions. Design of I-MSER is motivated by the observation that text MSERs have high similarity and are close to each other. The independency of candidate text regions obtained by I-MSER is guaranteed by selecting the most representative regions from a MSER tree which is generated according to the spatial overlapping relationship among the MSERs. A multi-layer CNN model is trained to score the confidence value of the extracted regions extracted by the I-MSER for text detection. The new text detection algorithm based on I-MSER is evaluated with wide-used ICDAR 2011 and 2013 datasets and shows improved detection performance compared to the existing algorithms.