一种基于改进FMM的移动设备图像补孔算法

Int. J. Comput. Sci. Math. Pub Date : 2019-07-04 DOI:10.1504/IJCSM.2019.10022399

Huiqin Wang, DongJuan Fang, Congcong Wang, Jianqiu Jin

{"title":"一种基于改进FMM的移动设备图像补孔算法","authors":"Huiqin Wang, DongJuan Fang, Congcong Wang, Jianqiu Jin","doi":"10.1504/IJCSM.2019.10022399","DOIUrl":null,"url":null,"abstract":"During the warping operation with DIBR, the hole will be generated through the synthesis of 3D image. For mobile device, it has lower performance so that the hole inpainting cannot be completed in real-time. In order to overcome this shortcoming, we propose an image hole inpainting algorithm with improved FMM for mobile devices. The algorithm fills the hole after 3D image warping by DIBR. First, we mark the colour image and the corresponding holes. Then, we preserve the original image foreground edge information by the improved expanded core of traditional FMM. Finally, we implement the algorithm on mobile device. Experimental results show that the improved FMM proposed in this paper is better than the traditional FMM.","PeriodicalId":399731,"journal":{"name":"Int. J. Comput. Sci. Math.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"An image hole inpainting algorithm with improved FMM for mobile devices\",\"authors\":\"Huiqin Wang, DongJuan Fang, Congcong Wang, Jianqiu Jin\",\"doi\":\"10.1504/IJCSM.2019.10022399\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"During the warping operation with DIBR, the hole will be generated through the synthesis of 3D image. For mobile device, it has lower performance so that the hole inpainting cannot be completed in real-time. In order to overcome this shortcoming, we propose an image hole inpainting algorithm with improved FMM for mobile devices. The algorithm fills the hole after 3D image warping by DIBR. First, we mark the colour image and the corresponding holes. Then, we preserve the original image foreground edge information by the improved expanded core of traditional FMM. Finally, we implement the algorithm on mobile device. Experimental results show that the improved FMM proposed in this paper is better than the traditional FMM.\",\"PeriodicalId\":399731,\"journal\":{\"name\":\"Int. J. Comput. Sci. Math.\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-07-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Int. J. Comput. Sci. Math.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1504/IJCSM.2019.10022399\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Comput. Sci. Math.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1504/IJCSM.2019.10022399","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

在使用DIBR进行翘曲操作时，将通过三维图像的合成生成孔洞。对于移动设备，它的性能较低，无法实时完成补孔。为了克服这一缺点，我们提出了一种基于改进FMM的移动设备图像补孔算法。该算法填补了三维图像经DIBR变形后的空洞。首先，我们标记彩色图像和相应的孔。然后，利用改进的传统FMM扩展核保留原始图像前景边缘信息。最后，我们在移动设备上实现了该算法。实验结果表明，本文提出的改进FMM比传统的FMM有更好的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

An image hole inpainting algorithm with improved FMM for mobile devices

During the warping operation with DIBR, the hole will be generated through the synthesis of 3D image. For mobile device, it has lower performance so that the hole inpainting cannot be completed in real-time. In order to overcome this shortcoming, we propose an image hole inpainting algorithm with improved FMM for mobile devices. The algorithm fills the hole after 3D image warping by DIBR. First, we mark the colour image and the corresponding holes. Then, we preserve the original image foreground edge information by the improved expanded core of traditional FMM. Finally, we implement the algorithm on mobile device. Experimental results show that the improved FMM proposed in this paper is better than the traditional FMM.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Int. J. Comput. Sci. Math.

自引率

0.00%

发文量