We present a new deinterlacing algorithm based on modularization by the local frequency characteristics of images. The input patterns of an image are divided into two regions—the edge region and the smooth region. Each region is assigned to one neural network. The local frequency characteristics of patterns are similar within each region, resulting in more accurate training for each network. The regional neural networks are composed of two modules. One is for the low-frequency components of the input pattern, and the other is for the high-frequency components. Both modules are combined in the output. Therefore, each module compensates for the drawbacks of the other. In simulation, the proposed algorithm showed better performances in both still images and video sequences than other algorithms.
Deinterlacing is the conversion process from the interlaced scan to progressive one. While many previous algorithms that are based on weighted-sum cause blurring in edge region, deinterlacing using neural network can reduce the blurring through recovering of high frequency component by learning process, and is found robust to noise. In proposed algorithm, input image is divided into edge and smooth region, and then, to each region, one neural network is assigned. Through this process, each neural network learns only patterns that are similar, therefore it makes learning more effective and estimation more accurate. But even within each region, there are various patterns such as long edge and texture in edge region. To solve this problem, modular neural network is proposed. In proposed modular neural network, two modules are combined in output node. One is for low frequency feature of local area of input image, and the other is for high frequency feature. With this structure, each modular neural network can learn different patterns with compensating for drawback of counterpart. Therefore it can adapt to various patterns within each region effectively. In simulation, the proposed algorithm shows better performance compared with conventional deinterlacing methods and single neural network method.