Hybrid Image Upsampling Method in the Discrete Cosine Transform Domain

Abstract

We present a direct image resizing method in the compressed domain. Our method reduces the ringing effect for blocks with vertical or horizontal edge. Moreover, our method omits the inverse discrete cosine transform (IDCT) operation required to represent the image in the spatial domain. We first address an estimation scheme for the sums of the columns and rows within the doubled block. We then propose an IDCT-free block representation scheme using the pseudo-inverse. On the basis of IDCT-free block representation, the ringing effect was significantly reduced when compared to the conventional algorithms such as Dugad-Ahuja and Mukherjee-Mitra. Finally, we propose a hybrid algorithm that uses both the Dugad-Ahuja method and the proposed method. We apply our method only to categorized blocks with vertical or horizontal edge. Otherwise, the Dugad-Ahuja method is used. The proposed algorithm does not require IDCT, which therefore makes it easy to implement in hardware. Furthermore, due to the significant reduction of the ringing effect, our method yields better performance in terms of both objective and subjective views than the conventional methods.