カテゴリ: 論文誌(論文単位)グループ名: 【D】産業応用部門発行日: 2019/02/01タイトル(英語): Improved Parameter Estimation Method for Bilateral Filter with Distribution Distance著者名: 真喜志 泰希（豊橋技術科学大学），市川 周一（豊橋技術科学大学），藤枝 直輝（豊橋技術科学大学），山田 親稔（沖縄工業高等専門学校），宮城 桂（沖縄工業高等専門学校）著者名(英語): Taiki Makishi (Toyohashi University of Technology), Shuichi Ichikawa (Toyohashi University of Technology), Naoki Fujieda (Toyohashi University of Technology), Chikatoshi Yamada (National Institute of Technology, Okinawa College), Kei Miyagi (National Institute of Technology, Okinawa College)キーワード: バイラテラルフィルタ，分布間距離関数，局所探索，並列化，OpenMP Bilateral Filter，distribution distance function，local search，parallelization，OpenMP要約(英語): Makishi et al. (2017) proposed a method that estimates the parameters for a bilateral filter, based on the distribution distance of images. This study proposes an improved version of the Makishi et al. (2017) method, which includes three new contributions. Firstly, our improved method was verified with two image sizes and two noise distributions. Secondly, five distribution distance functions were examined for the local search of parameter sets, where SKLD was found to be slightly superior to HD in terms of image quality and execution time. Finally, the parallelization of local search was examined for faster parameter estimation with recent multi-core processors. With a 2.8GHz Xeon processor of 10 cores, the parameter estimation times were reduced to 36ms (256x256 pixel) and 1.03 s (1024x1024 pixel).本誌: 電気学会論文誌D（産業応用部門誌） Vol.139 No.2 （2019） 特集：ドローンとロボット組み込み/サスティナブルシステム本誌掲載ページ: 104-110 p原稿種別: 論文／日本語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejias/139/2/139_104/_article/-char/ja/
