Improved image magnification algorithm based on Otsu thresholding

• An improved version of DCCI algorithm is proposed to magnify gray and color images.
• A new method to detect strong edge pixels is proposed using Otsu thresholding.
• Parameters of the DCCI algorithm which selected based on training are eliminated.
• Visual results show that the proposed algorithm outperforms the compared methods.
• Better quantitative results in terms of time, PSNR, SSIM and FSIM are obtained.

An improved image magnification algorithm for gray and color images is presented in this paper to meet the challenge of preserving high-frequency components of an image, including both image edges and texture structures. In the proposed algorithm, a new edge detection method that uses the well-known Otsu automatic optimum thresholding is proposed to distinguish strong edge pixels. The parameters of the original directional cubic convolution interpolation algorithm, which were selected based on training, were eliminated. As a result, our algorithm achieves more accurate edge detection, better interpolation results, and less computational complexity. Simulation results demonstrate that the improved algorithm can reconstruct the magnified image, preserve edges and textures simultaneously, and reduce common interpolation artifacts. Furthermore, it generates higher visual quality of the magnified images and achieves higher peak signal-to-noise ratio, structural similarity, and feature similarity compared with other state-of-the-art methods.

Figure optionsDownload as PowerPoint slide