- 學位論文
利用影像EXIF資訊預測感興趣區域並自動化分割方法
Automatic Segmentation of ROI by using Image EXIF information
摘要
近年來由於數位相機(Digital Camera)的普及與功能的逐漸完善，對於過去傳統影像的分析通常都必須對整張影像進行處理，增加其影像處理的時間與複雜度，故本研究是利用數位相機所記錄的拍攝參數來協助分析與分割影像，由於利用相機交換資料的影像格式(EXIF)參數可以準確地確認對焦點的位置，且一般而言對焦位置通常為拍攝者感興趣之區域，故本研究利用此一特點將針對相機可交換資料的影像格式(EXIF)參數中的相關資訊進行自動興趣區域的影像分割，當數位相機拍攝出各種不同的影像來紀錄畫面，拍攝過程中必須將相關重要參數記綠；例如相機與拍攝目標之間的位置、快門、感光度、曝光補償、閃光燈、焦距擷取、拍攝日期、機種型號等數據，因此本研究透過相機據參數提出更有效的自動化分割感興趣區域方法。
並列摘要
In recent years, due to the popularity of the digital camera and provide full functionality. Traditional image processing treats to do for the entire image. The means to cause time and complexity increase. Therefore our research that image analysis and segmentation is use by the parameter of digital camera. By the EXIF metadata parameter information, it can be clearly confirmed by focus position. Normally the focus position can be confirmed by photographer’s interest. So that our research that automated segment region of interest of image is use information of exchangeable image file format. There are two important factors that between the objectives of the camera and filming location and metadata parameter of digital camera. The Exchangeable image file format contains shutter, sensitivity, expansion time, flash, focal length extraction, shot date, machine models and other data. The research proposes and effective method to automatic segment by using of digital camera images EXIF information.