标题:Artificial multi-bee-colony algorithm for K-Nearest-Neighbor fields search
作者:Wang, Yunhai ;Qian, Yiming ;Li, Yang ;Gong, Minglun ;Banzhaf, Wolfgang
作者机构:[Wang, Yunhai ] Shandong University, Shandong, China;[Li, Yang ;Gong, Minglun ;Banzhaf, Wolfgang ] Memorial University, St. John's, Canada;[Qian, Yimi 更多
会议名称:2016 Genetic and Evolutionary Computation Conference, GECCO 2016
会议日期:20 July 2016 through 24 July 2016
来源:GECCO 2016 - Proceedings of the 2016 Genetic and Evolutionary Computation Conference
出版年:2016
页码:1037-1044
DOI:10.1145/2908812.2908835
关键词:Artificial bee colony algorithm; Image matching; K-NNF search; Patch match algorithm
摘要:Searching the k-nearest matching patches for each patch in an input image, i.e., computing the k-nearest-neighbor fields (k-NNF), is a core part of various computer vision/graphics algorithms. In this paper, we show that k-NNF can be efficiently computed using a novel artificial multi-bee-colony (AMBC) algorithm, where each patch uses a dedicated bee colony to search for its k-nearest matches. As a population-based algorithm, AMBC is capable of escaping local optima. The added communication among different colonies further allows good matches to be quickly propagated across the image. In addition, AMBC makes no assumption about the neighborhood structure or communication direction, making it directly applicable to image sets and suitable for parallel processing. Quantitative evaluations show that AMBC can find solutions that are much closer to the ground truth than the generalized PatchMatch algorithm does. It also outperforms the PatchMatch Graph over image sets. © 2016 ACM.
收录类别:EI;SCOPUS
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84985905638&doi=10.1145%2f2908812.2908835&partnerID=40&md5=72f0c1556598e1f069b2b6bfb00b7535
TOP