A BLIND IMAGE INPAINTING MODEL INTEGRATED WITH RATIONAL FRACTAL INTERPOLATION INFORMATION

IF 3.3 3区数学 Q1 MATHEMATICS, INTERDISCIPLINARY APPLICATIONS Fractals-Complex Geometry Patterns and Scaling in Nature and Society Pub Date : 2023-11-11 DOI:10.1142/s0218348x23501293

ZUN LI, AIMIN CHEN, XIAOMENG SHEN, TONGJUN MIA

引用次数: 0

Abstract

Aiming to solve the problem of blind image inpainting, this study proposed a blind image inpainting model integrated with rational fractal interpolation information. First, wavelet decomposition and closed operations were adopted to obtain masks and transform blind inpainting into non-blind inpainting. Then, on the basis of similar structural groups, rational fractal interpolation functions were introduced to complete the restoration. On the one hand, this model can sufficiently express the texture features of the image with high fidelity. On the other hand, it can better represent the structural features of the image, avoid serrated edges, enhance the restoration effect, and approximate the original image. The experimental results show that the restoration effect of this model can reserve texture details and ensure edges without distortion, possessing great practical application value.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于有理分形插值信息的盲图像补图模型

针对图像盲补问题，提出了一种结合有理分形插值信息的图像盲补模型。首先，采用小波分解和闭合运算得到掩模，将盲补图转化为非盲补图;然后，在相似结构群的基础上，引入有理分形插值函数完成复原。一方面，该模型能够充分表达图像的纹理特征，保真度高;另一方面，它可以更好地代表图像的结构特征，避免锯齿状边缘，增强恢复效果，近似原始图像。实验结果表明，该模型的恢复效果能够保留纹理细节，保证边缘不失真，具有较大的实际应用价值。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Fractals-Complex Geometry Patterns and Scaling in Nature and Society 数学-数学跨学科应用

CiteScore

7.40

自引率

23.40%

发文量

319

审稿时长

>12 weeks

期刊介绍： The investigation of phenomena involving complex geometry, patterns and scaling has gone through a spectacular development and applications in the past decades. For this relatively short time, geometrical and/or temporal scaling have been shown to represent the common aspects of many processes occurring in an unusually diverse range of fields including physics, mathematics, biology, chemistry, economics, engineering and technology, and human behavior. As a rule, the complex nature of a phenomenon is manifested in the underlying intricate geometry which in most of the cases can be described in terms of objects with non-integer (fractal) dimension. In other cases, the distribution of events in time or various other quantities show specific scaling behavior, thus providing a better understanding of the relevant factors determining the given processes. Using fractal geometry and scaling as a language in the related theoretical, numerical and experimental investigations, it has been possible to get a deeper insight into previously intractable problems. Among many others, a better understanding of growth phenomena, turbulence, iterative functions, colloidal aggregation, biological pattern formation, stock markets and inhomogeneous materials has emerged through the application of such concepts as scale invariance, self-affinity and multifractality. The main challenge of the journal devoted exclusively to the above kinds of phenomena lies in its interdisciplinary nature; it is our commitment to bring together the most recent developments in these fields so that a fruitful interaction of various approaches and scientific views on complex spatial and temporal behaviors in both nature and society could take place.