Hisakazu Kikuchi

Edge-based image synthesis model and its application to image coding

In this paper, a new image synthesis model based on the wavelet bases is proposed. In the proposed model, images are approximated from the sum of synthesis functions that are shifted to image edges. By applying the proposed model to sketch-based image coding, any iterative image recovery procedure is not required for image decoding. In the design of the synthesis functions, we define the synthesis functions as linear combinations of the wavelet bases. The coefficients for each wavelet base are yield from the iterative procedure. Vector quantization is applied to the vectors of the coefficients to limit the number of synthesis functions, We apply the proposed synthesis model to the sketch-based image coding. In coding experiments, we show the image coding by eight synthesis functions and its comparison with base-line JPEG.

Edge-based image synthesis model and its synthesis function design by the wavelet transform

In this paper, a new image synthesis model based on a set of wavelet bases is proposed. In the proposed model, images are approximated by the sum of synthesis functions that are translated to image contour positions. By applying the proposed model to sketch-based image coding, no iterative image recovery procedure is required for image decoding. In the design of the synthesis functions, we define the synthesis functions as linear combinations of wavelet bases. The coefficients for each wavelet base are obtained from an iterative procedure. The vector quantization is applied to the vectors of the coefficients to limit the number of the synthesis functions. We apply the proposed synthesis model to the sketch-based image coding. Image coding experiments by eight synthesis functions and a comparison with the orthogonal transform methods are also given.