粒子群優化與二維Otsu演算法於影像二元化閥值選取研究;Image Threshold selection based on PSO and 2D-Otsu Algorithm

NCUIR > College of Electrical Engineering & Computer Science > Executive Master of Communication Engineering > Electronic Thesis & Dissertation > Item 987654321/59902

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/59902

Title:	粒子群優化與二維Otsu演算法於影像二元化閥值選取研究;Image Threshold selection based on PSO and 2D-Otsu Algorithm
Authors:	張瑞芳;Chang,Juei-Feng
Contributors:	通訊工程學系在職專班
Keywords:	Otsu法;圖像分割;Homeland security
Date:	2013-03-05
Issue Date:	2013-06-19 15:25:02 (UTC+8)
Publisher:	國立中央大學
Abstract:	圖像分割中的閥值選取是一個相當重要的技術，也延伸到許多領域當中，如特徵辨識、生物醫學影像等等，而選取的方法包含許多，P參數法、最大熵閥值法、Otsu法等都是可以作為選取閥值的方法。閥值選取基本上是一個像素分佈的問題，基於可以依像素特性將圖像分為兩類:一個是屬於目標部份，另一個則是背景部分，判斷的依據則為像素的灰階數值小於或等於閥值分為一類，像素的灰階數值大於閥值分為一類，此一技術已被提出且廣泛使用。針對Otsu法的延伸-二維的Otsu法(2D-Otsu)可以在當灰階直方圖並未具有雙峰值的特性存在條件下，得到一個較好的分割閥值，將目標及背景區隔開來，但須經過較複雜的計算過程。而PSO演算法是一個人工智慧演算法，具有參數少，收斂速度快等特性，可以成功地結合二維的Otsu法加速搜尋圖像分割閥值。Threshold selecting is a significant technique for image segmentation, which is applied broadly in many fields such as character recognition, analysis of biologic images etc. The method mainly includes P-tile method , the maximum entropy method , Otsu and so on. It is essentially a pixels classification problem. Its basic objective is to classify the pixels of a given image into two classes: one is those pertaining to an object and another is those pertaining to the background. While one includes pixels with gray values that are below or equal to a certain threshold, the other includes those with gray values above the threshold. As an extension of Otsu algorithm, two-dimensional Otsu algorithm (2D-Otsu) can give good result for those objects whose histogram does not have two peaks which represent objects and background, however, it costs complex computation. Particle swarm optimization (PSO) is a swarm intelligence optimization algorithm as a set few parameters, better global search capability, search results more stable and widely used. So we combined successfully these two algorithms to get ideal segmentation result with lesscomputation cost.
Appears in Collections:	[Executive Master of Communication Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	908	View/Open

社群 sharing

Loading...