A Novel Approach for Text Extraction from Complex Natural Scene

摘要

In this study, hybrid Particle Swarm Optimization (PSO)-based Wavelet Neural Network (WNN) for natural scene text extraction is presented. In our approach, wavelet transformation is done on the different current and the wavelet coefficients are obtained. The wavelet coefficients are given as inputs to the wavelet neural network trained by Particle Swarm Optimization (PSO-WNN). The final network output of real text regions is different from those non-text regions. The experimental results demonstrate the effectiveness of the proposed method for complex natural scene.