Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/6157
標題: 類神經模糊技術於乾癬影像分割之應用
Segmentation of Psoriasis Images Using Neuro-Fuzzy Techniques
作者: 方良慧
Fang, Ling Whang
關鍵字: image segmentation;影像分割;psoriasis image;texture analysi;neuro-fuzzy classifier;乾癬影像;紋理分析;類神經模糊分類器
出版社: 電機工程學系
摘要: 
本文使用類神經模糊技術,在治療評估系統中,設計一套全自動乾癬影像的分割演算法。由於乾癬是一種慢性疾病,因此,追蹤患者的情況並選擇適當的療法十分重要。此系統自動將乾癬影像分割為正常皮膚及病變區域,然後在不同時刻估計某一病人乾癬的面積,以提供治療進展的定量測量,並且給予醫生客觀的指標,選擇對某一病人最適切的療法,避免在評估過程中受到個人因素的影響。本文主要涵蓋特徵抽取與影像分割法兩大技術。使用彩色影像中色調與飽和度兩分量的二維直方圖以及灰階影像的模糊紋理頻譜,作為特徵向量以找出影像中均勻的區域,使用這些區域訓練模糊類神經分類器,來獲得更精確的分割效果。當影像分割為正常皮膚及乾癬區域後,可以很容易計算出乾癬區域的面積,提供治療評估系統所需的參數。我們也將實現另一應用於數位皮膚炎影像分割的二維彩色群集演算法,作為比較並驗證我們的方法具有較佳的評估效果。

In this paper, we develop an automatic method for psoriasis image se- gmentation using neuro-fuzzy techniques, which can be used in an therapy evaluation system. Since the psoriasis is a chronic disease, it is important to track the condition of the patient to select proper treatment. The psoriasis images are segmented into normal skin regions and abnormal regions auto-
matically. The areas of each kind of regions of a patient at different moments can then be estimated. This information can be used to give a quantitative measure of the progress of the treatment. The provided information can avoid the variation of the human factor in the evaluation procedure and can offer a objective index for the doctor to select the most suitable treatment for the patient. The essential techniques required include feature extraction and image segmentation (classifi- cation) methods. The 2D histogram of the hue and saturation components of the color image and the fuzzy reduced texture spectrum of the gray-level image are used as the feature vectors to locate the homogeneous regions. Then these regions will be used to train the neuro-fuzzy classifier to obtain a more accurate segmentation. After the image is segmented into normal and psoriasis regions, the area of psoriasis regions can be easily calculated to obtain the information required for the therapy evaluation system. For comparison, we also implement a 2D color clustering algorithm which was used to segment digiti- zed dermatoscopic images. In the experiments, our proposed approach provides better performance.
URI: http://hdl.handle.net/11455/6157
Appears in Collections:電機工程學系所

Show full item record
 

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.