Multi-Oriented Text Detection and Verification in Video Frames and Scene Images

TL;DR

This paper introduces a novel multi-oriented text detection method in videos and images using Fourier-Laplacian filtering and HMM verification, effectively handling curved and oblique text in multiple scripts.

Contribution

The approach uniquely combines frequency domain filtering, skeletonization, and HMM verification for robust multi-oriented text detection, including curved text, in diverse scripts.

Findings

Outperforms existing methods in multi-oriented text detection

Effective in detecting curved and oblique text in videos and images

Successfully applied to English, Chinese, Devanagari, and Bengali scripts

Abstract

In this paper, we bring forth a novel approach of video text detection using Fourier-Laplacian filtering in the frequency domain that includes a verification technique using Hidden Markov Model (HMM). The proposed approach deals with the text region appearing not only in horizontal or vertical directions, but also in any other oblique or curved orientation in the image. Until now only a few methods have been proposed that look into curved text detection in video frames, wherein lies our novelty. In our approach, we first apply Fourier-Laplacian transform on the image followed by an ideal Laplacian-Gaussian filtering. Thereafter K-means clustering is employed to obtain the asserted text areas depending on a maximum difference map. Next, the obtained connected components (CC) are skeletonized to distinguish various text strings. Complex components are disintegrated into simpler ones according to a junction removal algorithm followed by a concatenation performed on possible combination of the disjoint skeletons to obtain the corresponding text area. Finally these text hypotheses are verified using HMM-based text/non-text classification system. False positives are thus eliminated giving us a robust text detection performance. We have tested our framework in multi-oriented text lines in four scripts, namely, English, Chinese, Devanagari and Bengali, in video frames and scene texts. The results obtained show that proposed approach surpasses existing methods on text detection.