Abstract: To achieve medium level visual region texture substitution in multi-regions contour curves, a multi-region image reconstruction algorithm was proposed. Firstly, the segmented region and index list of original image were extracted. Secondly, the polynomial coefficients representing region structure feature were got by piecewise iterative curve fitting and the smallest region texture sample was selected. Finally, the reconstructed region contour and synthesized region texture were used to achieve regional restoration. The proposed algorithm can be done successfully for images with massive textures. The experimental results show that it can reduce the amount of data required by image reconstruction and be applied to reconstruct the still background of image and video.

Key words: Human Visual System (HSV), image texture substitution, texture synthesis, curve fitting, multi-region

摘要： 为在多区域轮廓曲线中实现中等水平视觉的区域纹理替换，提出了一种多区域图像重建算法。该算法首先提取原始图像的分割区域及其索引号列表；其次根据分段迭代曲线拟合方法获得代表区域结构特征的多项式系数，并选取最小的区域纹理样本；最后利用重建的区域轮廓与合成的区域纹理实现区域恢复。该算法能成功实现包含大量纹理的自然场景图像重建，实验结果表明降低了图像重建所需数据量，适用于图像与视频的静止背景重建。

关键词: 人类视觉系统, 图像纹理替换, 纹理合成, 曲线拟合, 多区域