查詢結果分析
來源資料
頁籤選單縮合
題 名 | 中醫望診系統(2):舌診影像系統在上消化道病症之研究=The Application of Tongue Viewing System in the Illness of Upper Alimentary Canal |
---|---|
作 者 | 蘇振隆; | 書刊名 | 中醫藥年報 |
卷 期 | 17:1 1999.05[民88.05] |
頁 次 | 頁333-438 |
分類號 | 413.241 |
關鍵詞 | 舌影像; 舌診影像系統; 影像處理; 舌特徵資料庫上消化道病症; Tongue image; Tongue viewing system; Image processing tongue-characteristic database; Upper GI disorder; |
語 文 | 中文(Chinese) |
中文摘要 | 近幾年來,中醫舌診客觀化、科學化的研究廣泛地受到重視,而其中又以中醫舌 診電腦化的舌特徵分析為研究發展的重點。本研究即是利用影像處理的技術,建立了一套舌 診影像系統,並且針對健康人及上消化道病症患者進行舌象的取樣與分析,找出之間舌特徵 的差異性。本系統之硬體設備架設於一可移動的診查臺上,主要包括有: 個人電腦、CCD 彩 色攝影機、影像擷取卡、燈光設備。在軟體工具部份,採用 Delphi 3.0 程式發展軟體來撰 寫影像分析處理程式及舌特徵病歷資料庫程式。而整個影像分析處理流程,依序有影像校正 、影像單位換算、影像分割、舌色與苔色之分析、舌形之分析、苔質之分析等處理步驟,其 中主要以 HSI 彩色座標模型為舌色與苔色分類的依據, 並且利用傅利葉頻譜分析方法來評 估舌苔的厚薄與判別腐苔、膩苔的紋理特性。此外,可將上述處理步驟的分析結果存入舌特 徵病歷資料庫之中,以便於資料的保存與管理。本系統針對 45 位健康人及 55 位上消化道 病症患者的舌影像進行舌特徵之分析,結果發現:兩者主要的差異在於上消化道病症患者特 徵病歷資料庫之中,以便於資料的保存與管理。本系統針對 45 位健康人及 55 位上消化道 病症患者的舌影像進行舌特徵之分析,結果發現:兩者主要的差異在於上消化道病症患者的 舌苔所佔百分比,明顯地大於健康人的舌苔所佔百分比,並且舌苔多集中分佈於舌中間部位 (即脾胃區 ), 其中又以白苔為主。 根據統計有 85% 的健康人其脾胃區中的白苔百分比為 40% 以下,有 65% 的上消化道病症患者其脾胃區中的自苔百分比在 40% 以上。上消化道病 症患者的舌寬、舌長、舌面積和健康人的舌形分佈是一致的。舌長大致分佈在 4.5~6.5cm, 舌寬大致分佈在 4~5cm,而舌面積大致分佈在 15~25cm �插C有 38% 的上消化道病症患者出 現自膩苔, 越大於健康人的 6.6%; 而有 5.5% 的上消化道病症患者出現黃膩苔,健康人之 中則完全沒有黃膩苔的出現。另外,健康人的舌苔厚薄分佈以薄白苔為主,上消化道病症患 者則以薄白苔、薄黃苔、厚黃苔為主。我們採用白苔、黃苔、苔質、舌溫分佈等舌特徵,對 健康人及上消化道病症患者進行分類辨識,而最佳辨識率可達 85.1%。本研究中所發展的舌 診影像系統,僅提供了望診中的舌診資訊,而中醫診斷主要以「四診合參」為依據,因此, 若在未來的研究中能夠加入其他中醫診斷系統的分析結果,將可提供中醫師更詳盡的病情訊 息,進而輔助中醫師做出更精準的病症診斷。 |
英文摘要 | In recent years, the studies in scientific and objective Chinese tongue diagnosis have been widely emphasized. Quantitative analysis of tongue images with a computer is a trend in the study of tongue diagnosis. In this research, a complete tongue viewing system was established by using image processing technology. This system can be used for analyzing and finding the difference of tongue characters between healthy men and upper Gl disorder patients. This system set on a moveable consulting chassis, mainly including a personal computer, a frame grabber, color CCD cameras, and the light equipment. The software which combined image processing programs and application programs of tongue-characteristic database was developed by using Delphi 3.0. The tongue image was processed by image calibration, sizes conversion, image segmentation, color analysis of tongue and coating, shape analysis of tongue, and analysis of coating properties in that order. The color classification for tongue and coating was depended on the HSI color model. And, Fourier spectrum was used to estimate the thickness of coating and distinguish between grimy coating and crusted coating. Moreover, the analyzed results could be saved to tongue- characteristic database for convenience of the preservation and management of patient's history. After the system was completely constructed, the difference of tongue characters was generalized by sampling 45 healthy men and 55 Upper Gl disorder patients. The results showed that the significant difference of that patient's coating percentage was larger than normal, and coating was almost located in the middle of tongue which corresponding to stomach area. There were 85% healthy men whose white coating in their middle of tongue which was less than 40%. But there were 65% patients whose white coating in their middle of tongue which was beyond 40%. Patient's tongue shapes were identical with normal. Most of tongues were 4.5-6.5 cm for the length, 4-5 cm for the width, and 15-25 cm �� for the tongue area. There were 38% patients who have white-grimy coating, and which was far greater than normal (6.6%). There were 5.5% patients who have yellow-grimy coating, but none appeared in normal. Besides, the majority of normal tongue thickness was thin-white coating, but which of patient's tongue thickness was thin-white, thin-yellow, or thick-yellow coating. According to tongue characters the system recognition rate for identifying the normal and patient groups approached 85.1%. The developed tongue viewing system only provided tongue diagnostic information. However, the principles of traditional Chinese medicine diagnosis were based on four diagnostic processes which were viewing, learning, inquiring, and examining. Therefore, the system could be integrated with other Chinese diagnostic systems in the future. It would be practical to help doctors to diagnose illness more accurately. |
本系統中英文摘要資訊取自各篇刊載內容。