15 July 2013 Image deinterlacing using region-based back propagation artificial neural network
Author Affiliations +
Optical Engineering, 52(7), 073107 (2013). doi:10.1117/1.OE.52.7.073107
A back propagation artificial neural network (BP-ANN) has good self-learning, self-adaptation and generalization abilities, which we intend to use to interpolate an image. The interpolated pixels are classified into two regions, each region corresponding to one BP-ANN. In order to optimize the structure of the BP-ANN and the process of deinterlacing, three experiments were performed to test the architecture and parameters of region-based BP-ANN. The experimental results show that the proposed algorithm with an 8161 structure provides the best balance between time consumption and visual quality. Compared to the other six advanced deinterlacing algorithms, our region-based BP-ANN method provides about an average of 0.14 to 0.64 dB higher peak signal-to-noise-ratio while maintaining high efficiency.
© 2013 Society of Photo-Optical Instrumentation Engineers (SPIE)
Yurong Qian, Jin Wang, Gwanggil Jeon, Jechang Jeong, "Image deinterlacing using region-based back propagation artificial neural network," Optical Engineering 52(7), 073107 (15 July 2013). http://dx.doi.org/10.1117/1.OE.52.7.073107


Artificial neural networks

Image quality


Data modeling

Optical engineering

Computer simulations

Back to Top