200949291 六、發明說明： 【發明所屬之技術領域】 本發明係相關於一種鑑別肌膚 言，係相關於一種以肌虜的物理量 理及/或皺紋之技術。 【先前技術】 使用化妝品時之重要課題係正 化妝品而使用，並確認其使用之效 0 者的肌膚之化妝品，不僅無效果亦 此，必須避免錯選不適合使用者的 見「化妝品不適於肌膚」之怨言， 於皮虜之化妝品，換言之，常有錯 之情形。爲選擇適於肌膚的化妝品 重要因素，係在於皮膚紋理及皺紋 由此觀點，開發出各種選擇化 由皮膚複製品照明而得的皮虜溝紋 〇 (參考專利文獻1)、針對來自皮癎 影像解析之技術（參考專利文獻2 進行層次處理等影像處理之技術（ 電磁波測定來自複製品皺紋之深度 4)、使用標準尺度，以皮膚複製劑 術（參考專利文獻5)、於皮虜狀態 理畫素影像進行細線化處理，並以 指標之測定紋理之技術（參考專利 目前所知的選擇化妝品之技術中之 狀態之技術，更詳細而 爲指標之鑑別肌膚的紋 確地選出適於使用者之 果。若使用不適於使用 可能出現不適現象。因 肌膚之化妝品。較多聽 此現象亦是沒有選擇適 選不適於皮膚的化妝品 ，並確認使用的效果之 之評價。 妝品之技術。例如抽出 之圖型，並解析之技術 表面的直接影像，進行 )、針對複製拍攝影像， 參考專利文獻3 )、使用 之技術（參考專利文獻 來測定皺紋之深度之技 的單一色畫素影像或處 細線的波峰寬度間隔爲 文獻6 )等已揭示。惟， 大課題，係紋理及/或皴 • 4- 200949291 紋之鑑別結果與目視的紋理及/或皴紋之評價値是否充分 一致，以及更進一步，販售或諮詢現場可否迅速地評價等 問題，換言之，係兼具評價之客觀性和快速性。亦即，目 視的紋理及/或皺紋之評價値，即使有判定基準，觀察者於 顯微鏡下以肉眼觀察複製等，仍爲主觀判定，不僅客觀性 的維持乃一問題，其判定所需之時間的長短亦爲重要之課 題。因此，期待一種具客觀性和快速性，可得紋理及/或皴 紋的評價之鑑別技術。 〇 在此種狀況下，先前通常進行的影像解析技術之過濾 處理、二値化處理、影像信號處理或選配處理等，無法充 分地得出肌虜的溝紋或皮丘型態的特徵之資訊並定量化。 而本發明者等，發明一種由如此對象的影像而取得目標資 訊之完全新穎之技術，且使用十字二値化處理及短直線選 配之定量化技術（參考專利文獻7 )。 專利文獻 專利文獻1 :特開昭6 0 - 0 5 3 1 2 1號公報 Q 專利文獻2:特開昭64-059145號公報 專利文獻3:特開平02— 046833號公報 專利文獻4:特開平08 — 145635號公報 專利文獻5:特開2000 - 342556號公報 專利文獻6 :特開2006 — 06 1 170號公報 專利文獻7 :特開2008 — 06 1 892號公報 【發明内容】 解決發明之課題 本發明係於此狀況下進行之發明，高精準度且可迅速 200949291 地鑑別肌膚的紋理及/或皺紋，係以提供肌膚的紋理及/或皺 紋之鑑別技術爲課題。且以提供一種依據該鑑別結果來選 擇皮膚外用劑之方法爲課題。 解決課題之方法 本發明者等致力硏究一種高精準度且可迅速地鑑別肌 膚的紋理及/或皺紋之肌膚的紋理及/或皺紋之鑑別法的結 果，發現對肌膚影像進行十字二値化處理及/或短直線選配 處理所得肌虜之物理量，將其帶入預先準備的預測式而得 Q 評價値，藉此可高精準地且迅速地鑑別肌膚的紋理及/或皺 紋，而完成本發明。亦即，本發明係相關於以下所示之技 術。 (1 ) 一種肌虜之紋理及/或皺紋之鑑別法，其係包括··針 對所得的肌虜影像，進行包括十字二値化處理及/或短直線 選配處理之影像處理，而得肌虜的物理量之步驟、和將上 述步驟所得的肌膚的物理量帶入預先準備之預測式，以所 得的評價値爲皮膚的紋理及/或皺紋之評價値而鑑別之步 〇 驟。 (2) —種肌膚之紋理及/或皺紋之鑑別裝置，其係包括： 載入預先準備的預測式之手段、取得肌膚影像之手段、由 該已取得的肌虜影像，而算出肌膚的物理量之手段、由預 先準備之預測式和上述已算出之肌膚的物理量，而算出肌 膚的紋理及/或皺紋之評價値之手段、顯示上述已算出的評 價値之手段。 (3) —種肌虜之鑑別程式，其機能係包括：電腦、由已取 得的肌膚影像，而算出物理量之手段、由預先準備之預測 200949291 式和上述肌膚的物理量’而算出肌膚的紋理及/或皴紋之評 價値之手段。 (4) 一種皮膚外用劑之選擇方法，其係包括：使用如上述 (1 )之鑑別法、或（2 )之鑑別裝置而鑑別肌虜的紋理及/ 或皺紋之步驟、及 依據由上述鑑別步驟所鑑別的肌虜之紋理及/或皺紋 之評價値，若受試者的皮膚之鑑別結果係紋理及/或皺紋之 狀態不佳時，選擇一種含有爲改善紋理狀態或預防紋理狀 Q 態紊亂的成分之皮膚外用劑，若受試者的皮膚之鑑別結果 係紋理及/或皺紋之狀態佳時，選擇一種只含保濕成分之皮 膚外用劑之步驟。 發明之效果 依據本發明，可提供一種高精準度且可迅速地鑑別肌 膚的紋理及/或皺紋之鑑別肌膚的紋理及/或皺紋之技術。且 應用此技術，可提供適於使用者之皮膚外用劑。 【實施方式】 〇進行發明之型態200949291 6. INSTRUCTIONS OF THE INVENTION: TECHNICAL FIELD OF THE INVENTION The present invention relates to a technique for identifying skin, which is related to a physical measurement and/or wrinkle of tendon. [Prior Art] The important topic in the use of cosmetics is the use of cosmetics, and it is confirmed that the skin of the skin is not effective, and it is necessary to avoid the wrong choice and not suitable for the user. "Cosmetic is not suitable for the skin" The complaints, the cosmetics in the skin, in other words, often wrong. In order to select an important factor for cosmetics suitable for the skin, it is based on the viewpoint of skin texture and wrinkles, and has developed a variety of skin ridges that have been selectively illuminated by skin replicas (refer to Patent Document 1) and for images from the skin. Technique for analysis (refer to Patent Document 2, Techniques for Image Processing such as Hierarchical Processing (Electromagnetic Wave Measurement from Depth of Replica Wrinkles 4), Using Standard Scales, Skin Replica (Reference Patent Document 5), and Painting in the Skin State The image is thinned and processed by the technique of measuring the texture of the index (refer to the technology of the state of the art of selecting cosmetics which is known in the patent, and the skin of the indicator is selected in more detail to be suitable for the user. If it is not suitable for use, it may cause discomfort. Because of the skin's cosmetics, it is not recommended to choose cosmetics that are not suitable for the skin, and confirm the evaluation of the effect of use. The pattern, and the direct image of the technical surface is analyzed, for the copying of the image, reference Patent Document 3), the technique used (a single color pixel image of a technique for measuring the depth of wrinkles or a peak width interval of a fine line is referred to as Document 6), and the like have been disclosed. However, whether the large-scale subject, texture and/or 皴• 4-200949291 identification results are consistent with the visual texture and/or crepe evaluation, and further, whether the sales or consultation site can be quickly evaluated. In other words, the system has both the objectivity and speed of evaluation. That is, the evaluation of the visual texture and/or wrinkles, even if there is a criterion for judgment, the observer observes the reproduction under the microscope with the naked eye, and is still subjectively determined, and not only the maintenance of objectivity is a problem, but also the time required for the determination. The length of time is also an important issue. Therefore, an identification technique which is objective and rapid, and which can be evaluated for texture and/or crepe is expected.此种 Under such conditions, the filtering, dichotomy, image signal processing, or optional processing of image analysis techniques that were previously performed cannot fully derive the characteristics of the groove or ridge shape of the tendon. Information and quantification. The present inventors have invented a completely novel technique for obtaining target information from the image of such a target, and a quantification technique using cross dimerization processing and short straight line matching (refer to Patent Document 7). CITATION LIST Patent Literature PATENT DOCUMENT PATENT DOCUMENT PATENT DOCUMENT PATENT DOCUMENT PATENT DOCUMENT PATENT DOCUMENT PATENT DOCUMENT PATENT DOCUMENT PATENT DOCUMENT PATENT DOCUMENT In the case of the invention, the problem of the invention is solved. [Patent Document No. JP-A-2006-20061] The present invention is an invention carried out under such circumstances, and is highly accurate and can quickly identify the texture and/or wrinkles of the skin in 200949291, and is a technique for providing identification techniques for texture and/or wrinkles of the skin. Further, it is a subject to provide a method of selecting a skin external preparation based on the identification result. Solution to Problem The inventors of the present invention have focused on the result of a method of identifying the texture and/or wrinkles of a skin with high precision and which can quickly identify the texture of the skin and/or wrinkles, and found that the skin image is cross-divisioned. The physical quantity of the tendon obtained by the treatment and/or short-line matching treatment is brought into a pre-prepared predictive formula to obtain a Q evaluation 値, thereby accurately identifying the texture and/or wrinkles of the skin with high precision. this invention. That is, the present invention relates to the technique shown below. (1) A method for identifying texture and/or wrinkles of tendons, comprising: performing image processing including cross dilation treatment and/or short linear matching treatment on the obtained tendon images, and obtaining muscles The step of the physical quantity of the sputum and the physical quantity of the skin obtained by the above steps are carried into a prediction formula prepared in advance, and the obtained evaluation 値 is a step of identifying the texture and/or wrinkles of the skin. (2) A device for identifying the texture and/or wrinkles of the skin, comprising: means for loading a predictive type prepared in advance, means for obtaining a skin image, and calculating the physical quantity of the skin from the acquired image of the tendon The means for calculating the texture and/or wrinkles of the skin by the predictive formula prepared in advance and the physical quantity of the skin calculated as described above, and means for displaying the calculated evaluation. (3) The identification procedure of the tendon includes a computer, a method of calculating the physical quantity from the acquired skin image, and a texture of the skin calculated by the predicted prediction of the type 200949291 and the physical quantity of the skin described above. / or the method of evaluation of crepe. (4) A method for selecting a skin external preparation, comprising: a step of discriminating the texture and/or wrinkles of the tendon using the discrimination method according to (1) above, or (2), and based on the above discrimination Evaluation of the texture and/or wrinkles of the tendon identified by the procedure. If the subject's skin is identified as having a poor texture and/or wrinkle condition, select a Q-state to improve the texture state or prevent texture. A skin external preparation containing a disorder component, if the skin of the subject is distinguished by a texture and/or a wrinkle, a step of selecting a skin external preparation containing only the moisturizing component is selected. EFFECT OF THE INVENTION According to the present invention, it is possible to provide a technique for identifying the texture and/or wrinkles of the skin with high precision and which can quickly identify the texture and/or wrinkles of the skin. And by applying this technique, an external preparation for skin suitable for the user can be provided. [Embodiment] 〇Inventing the type of invention
I 本發明之鑑別法係可從肌膚影像來鑑別肌虜的紋理、 肌膚的皴紋或二者之狀態。 <使用於本發明的肌虜影像之取得> 本發明係使用肌虜影像。取得肌膚影像之方法，係直 接拍攝肌膚而得肌膚影像之方法，亦可爲通過採取自肌膚 的複製標本而取得肌虜影像之方法。取得影像之方法，例 如透過立體顯微鏡，以數位錄影機取得，亦可利用市售的 數位式顯微鏡。此類數位式顯微鏡例如毛利得克斯（股） 200949291 之化妝用顯微鏡或奇彥思（股）之數位顯微鏡等。 本發明中，宜爲通過上述採取自肌膚的複製標本而取 得肌膚影像之方法。藉由通過採取自肌膚的複製標本而取 得肌虜影像，因可去除肌膚表面的顏色資訊而只取得形態 資訊，故可預防污垢等干擾。又，解析上不要的肌虜表面 之凹凸（非皮虜溝紋或皮丘等級之凹凸）係因複製採取而 被消除，使解析變容易。以下所示係通過複製標本而得肌 膚影像之方法。 Q 在相對於複製標本90°之位置，設置顯微鏡之鏡頭，以 適於複製標本之角度照射光，通過顯微鏡，可取得因入射 光而產生之複製標本的表面凹凸之陰影像，作爲影像。複 製標本係指於溶劑軟化性的透明之塑膠板，塗布軟化用之 溶劑，使軟化後，將此軟化部位推到皮膚上，轉印皮膚上 的凹凸至軟化部位，藉由觀察此凹凸，而間接地觀察皮膚 上的凹凸之技術，代表性之技術係「河合法」。此技術係切 實地轉印皮膚上之凹凸，且因其凹凸之保存性亦優異，在 〇 化妝品科學之領域，係自古即廣泛使用。製作此類複製標 本之套組，係可使用既已販售之套組。相關的複製標本， 宜採取臉頰、或外眼角部位至其下方之部位1.5cmx 1.5cm。 一般的方法中，通常此類複製標本係由垂直於複製面之下 方照射光，而觀察透過光。亦即，因轉印的凹凸，使照射 的光散射，利用透過光量變少而觀察凹凸爲影像。本發明 之鑑別法中，該複製之觀察，宜於其次之條件進行。將複 製之具凹凸之面向著採像方向，以對於此面之10~40度， 尤宜20~30度之角度照射光，採取由此反射光而成之像（取 200949291 爲影像）。藉由採取如此之形態，轉印於複製面的凹凸係以 更清楚之光度差而顯現。表1係表示對於同一試驗品，改 變入射角而觀察時的清晰度之評價。評價基準係〇：清晰、 △:稍稍不清晰、X:不清晰。 表1 入射角（仰角） 凹凸之清晰度 10度 Ο-Δ 25度 〇 40度 Ο-Δ 〇 <十字二値化之影像處理> 本發明係對於上述所得之肌虜影像，進行包括十字二 値化處理及/或短直線選配處理之影像處理。關於此類的影 像處理，係記載於特開2008 — 06 1 892號公報（專利文獻7 )， 其說明如下。 最基本之影像處理法，例如自影像中分離出背景和對 〇 象物，以對象物爲形狀而取出之二値化處理法。對象物和 背景之對比係充分相合時，易於二値化處理。惟實際上， 在主要對象物和背景之交界部份，存在著微妙之濃淡變 化，因此不易設定以取得高精準度的形狀爲目的之二値化 處理之閥値。又，因照明的不均勻等而使背景的濃淡標準 變動時，固定於整體圖面之閥値，則不易取得正確之形狀。 如此，無固定之閥値’依畫素而改變閥値之動態閥値處理 (可變閥値處理）爲較佳’本十字二値化處理法係屬於動 態閥値處理法。動態閥値處理法之處理範圍，一般爲長方 200949291 形，惟本十字二値化處理法係具有適於取得皮膚溝紋形狀 之十字形狀（參考第2圖）。使用本十字二値化處理法，不 受照射複製之照明之不均勻所影響，可檢出因皮膚溝紋的 凸部位而有的影像，從粗而清晰的皮虜溝紋至微細的皮膚 溝紋之整體圖面，可得均句且高精準度之十字二値化影像 (參考第3圖）。 上述十字二値化處理，係可使用特開2008-06 1 892號公 報所記載之表皮組織定量化裝置而進行。 0 <短直線選配之影像處理> 上述短直線選配法，係爲算出已二値化的影像中的對 象物形狀之物理量之方法。先前法係以二値化影像的1畫 素爲單位，計測對象物之畫素數，而算出面積、長度、重 心等物理量，相對於此，本短直線選配法係以由複數畫素 構成之短直線（數畫素至數十畫素之長度，寬爲1畫素） 爲單位而算出物理量。具體而言，以對象範圍的端點爲短 直線之起點，若短直線的終點位於對象範圍內，則以其終 〇 點爲新起點而連結其次之短直線。若短直線的終點位於對 象範圍外，則結束連結。重複此操作，直至對象範圍被短 直線覆蓋爲止。之後，計測嵌入對象範圍的短直線之條數、 角度等，算出對象物之特徵量（參考第4圖）。依據本法， 可製得細長而連續，且具方向性的皮膚溝紋特長之短直線 選配影像（參考第5圖）。 上述短直線選配處理，係可使用特開2008-061 892號公 報所記載之表皮組織定量化裝置而進行。 上述的影像處理，雖可僅進行其中一種之影像處理， -10- 200949291 惟藉由進行二者之影像處理，可更正確地算出物理量。亦 可因應其他之需求，進行亮度變換處理、二値化處理、過 濾處理、一般影像處理（面積、周長、縱橫比、重心、針 狀比、擴大、反轉）等其他影像處理。 <紋理及/或皺紋的物理量之算出> 本發明中，進行包含上述十字二値化處理及/或短直線 選配處理之影像處理，可得肌膚影像之物理量。此物理量 係將肌膚的皮膚溝紋、皮丘等特徵定量化之物理量。如此 0 之物理量，例如以皮虜溝紋面積、皮膚溝紋平均粗度、皮 廣溝紋粗度之不齊程度、.皮膚溝紋之間隔、皮膚溝紋之平 行度、皮膚溝紋方向、皮膚溝紋密度等物理量爲始，更進 —步，例如每個角度的短直線條數中95°以上之最大條數、 每個角度的短直線條數中10°以上90°以下之最大條數、每 種粗度的短直線條數中之最大條數、每種粗度的短直線條 數中的最大條數之粗度、短直線連結數度數數値之合計 値、每種粗度的短直線條數的粗度値之合計値等更細微之 〇 物理量，本發明係從此類物理量中，算出與紋理、皺紋有 相當關係之物理量。具體而言可定義爲，皮膚溝紋面積= 處理對象之影像範圍中，皮膚溝紋的佔有面積或選配短直 線之總條數；皮膚溝紋平均粗度=(各選配開始點每種皮 膚溝紋粗度之總合/開始點總數）；皮膚溝紋粗度之不齊程 度=由皮膚溝紋粗度的粗度與條數之矩形圖算出之標準偏 差或分散；皮虜溝紋之平均間隔=ι/(皮虜溝紋面積/皮膚 溝紋之平均粗度）；皮膚溝紋之平行度=由皮膚溝紋的角度 與條數之矩形圖算出之波峰集中度或分散；皮虜溝紋之方 -11 - 200949291 向•密度=於角度0的短直線數（矩形圖之高度）/皮膚溝 紋之全長。其他物理量係可由上述算式而算出。本發明中 所得之物理量係如上述般大多存在，惟從其中選出爲算得 後述預測式之適用物理量。此類物理量之算出，係可包括 上述包含十字二値化處理及/或短直線選配處理之影像處 理，利用電腦上的程式而處理。 <預測式> 爲鑑別肌虜的紋理及/或皺紋，預先找出顯示上述肌膚 〇 物理量與肌虜的紋理及/或皺紋的目視評價値的關係之預 測式。預測式係可利用以下舉例之方法來作成。 充分考量肌膚狀態或年齡等之肌膚複製（以下稱之爲 樣品），由評價者來進行紋理及/或皺紋之目視評價。另一 方面，以上述方法算出其樣品的肌膚之物理量。其樣品數 宜爲100以上，尤宜500以上。紋理及/或皺紋之目視評價， 係參考爲判斷紋理爲良好〜差，或皺紋爲少〜多之3至10階 段基準照片，相稱於代表第三者之適當的複數評價者，宜 Ο 爲5位以上評價樣品，給予對應基準照片之評價値。上述 相稱於代表第三者之評價者，宜爲具有1年以上的美容、 審美或肌虜評價硏究之經驗，且繼續接受肌虜評價訓練 者。去除各樣品的評價値之最大値和最小値，以平均後之 値爲樣品的紋理及/或皺紋之目視評價値。 肌虜狀態的評價之肌膚的紋理、皺紋程度，係於日本 化妝品技術者會或國際化妝品技術者會聯盟（IFSCC)討 論，第三者可客觀地認識肌膚的紋理、皺紋之程度係具大 家共有之認識。第6圖及第7圖所示，係依據統計處理之 -12- 200949291 基準化的紋理（5階段評價）及皺紋（3階段評價）的基準 照片之一例。如此之基準照片係於此技術領域，作成基礎 之母集團若爲100,則可判定爲具有相當程度的信賴性之基 準照片，母集團若超過1，000時，可判定爲相當高信賴度 之基準照片，係可不考量每張基準照片的差異之水準。本 發明的上述樣品評價，係可使用依據此般的統計處理而基 準化之基準照片，作成基準照片時之母集團，宜爲1,000 以上。 0 其次，從如此而求得的紋理及/或皺紋之目視評價値與 算出的肌膚之物理量，而導出預測式。預測式係可爲將肌 膚的物理量和紋理及/或皺紋之目視評價値進行多變量解 析而得之式。多變量解析宜爲可利用說明變數和目標變數 之關係者，例如判別分析、主成分分析、因子分析、數量 化理論一類、數量化理論二類、數量化理論三類、回歸分 析（MLR、PLS、PCR、數理邏輯）、多次元尺度法、有教師 群組化、紐拉爾網絡（neural network)、協調（ensemble) 〇 學習法等，可使用免費軟體或市售軟體而製作預測式。其 中，尤宜重回歸分析、判別分析及數量化理論一類。理想 之舉例，係以肌膚的物理量爲說明變數，以上述求得的紋 理及/或皺紋之目視評價値爲目標變數，進行重回歸分析而 求重回歸式，以此重回歸式爲預測式。 如上述般，使用於預測式的算出之肌虜的物理量係有 各種物理量，惟，從提升本鑑別法的精確度之觀點，宜含 有與皮膚溝紋有關之物理量，從更進一步提升鑑別法的精 確度之觀點，尤宜含有ίο種類以上的與皮膚溝紋有關之物 -13- 200949291 理量。使用於預測式的算出之物理量之總數，宜爲ίο以上。 <鑑別步驟> 將上述肌膚的物理量帶入設定的預測式而得評價値， 藉此可進行肌虜之紋理及/或皺紋之鑑別。將從取得的影像 所算出肌膚之物理量帶入該預測式，可得肌虜之紋理及/或 皺紋之目視評價値。本專利發明係經由上述步驟，可以極 高精確度來鑑別肌虜之紋理及/或皺紋。更進一步，期待一 種新穎的高精確度之鑑別，其係將樣品之物理量或目視評 0 價値等組入數據庫，藉著更新及補正，更提升該預測式之 精確度。 <鑑別裝置一程式> 本發明的其他樣態，係進行上述步驟之程式。亦即， 一種肌虜之鑑別程式，其係包括以下使其作用：以電腦由 已取得的肌膚影像而算出物理量之手段、由預先準備之預 測式和上述已算出之肌膚的物理量，而算出肌膚的紋理及/ 或皺紋之評價値之手段。本專利發明之鑑別程式，係可安 〇 裝於個人電腦等硬體設備而使用。 更進一步，本發明的其他樣態，係進行上述步驟之鑑 別裝置。亦即，一種肌膚之紋理及/或皺紋之鑑別裝置，其 係包括：載入預先準備的預測式之手段、取得肌膚影像之 手段、由已取得的肌虜影像，而算出肌膚的物理量之手段、 由預先準備之預測式和上述已算出之肌膚的物理量，而算 出肌膚的紋理及/或皺紋之評價値之手段、顯示該已算出的 評價値之手段。 以第1 〇圖來說明上述鑑別裝置之樣態。本發明之鑑別 -14- 200949291 裝置可爲個人電腦等通用電腦，亦可爲鑑別專用之電腦。 輸入部1，係上述預測式之輸入手段，預先輸入使用於鑑 別之預測式。例如可使用鍵盤等輸入裝置。影像取得部2, 係取得肌虜影像之手段，可使用數位式錄影機或市售的數 位式顯微鏡。CPU3 (中央處理器（Central Processing Unit)) 係由已取得的肌虜影像而算出肌膚的物理量之手段、以及 由預先準備之預測式和上述已算出之肌虜的物理量，而算 出肌膚的紋理及/或皴紋之評價値之手段。安裝上述鑑別程 0 式，即可作用此般手段。RAM4 (隨機存取記憶體（Random Access Memory))係收納暫時的數據之記憶手段。顯示部5, 係輸出算得的評價値之手段，例如可爲液晶顯示器等顯示 裝置、或列表機等輸出裝置。 以第11圖來說明上述鑑別裝置之處理流程。 首先，從數位錄影機等影像取得部位，取得肌膚影像。 如已說明般，可從測試者的肌虜直接拍攝，亦可透過複製 標本》上述取得之肌膚影像，係於CPU進行十字二値化處 〇 理和短直線選配處理等影像處理，合倂算出肌虜影像之物 理量。算出的肌虜影像之物理量之種類，係依據使用於算 出預先由輸入手段輸入的預測式之物理量之種類，而適當 地設定。算出的肌膚影像之物理量，係同樣地帶入CPU中 預先輸入之預測式，而算出其評價値。算出的評價値係從 液晶顯示器等輸出手段而輸出。 本發明中，藉由預先將與肌膚的紋理有關之預測式和 與肌虜的皺紋有關之預測式個別輸入上述鑑別裝置，可一 次地鑑別肌虜之紋理和皺紋，亦可個別地鑑別。 -15- 200949291 <依據已鑑別的肌虜的紋理評價値之皮膚外用劑之選擇法 > 依據由上述鑑別法或鑑別裝置而鑑別之紋理之評價 値，可選擇適於使用肌膚影像的測試者之皮膚外用劑。使 用本發明的鑑別法或鑑別裝置，因可和專家評價肌膚時幾 乎相同的高精確度而迅速地鑑別，故依據其結果，可選擇 有助於維持、預防或改善肌虜的紋理狀態之皮膚外用劑。 皮膚外用劑之選擇，特別是在化妝品之選擇，若輸出 0 的顯示係測試者的皮膚紋理之狀態不佳之鑑別値時，選擇 一種含有爲改善紋理狀態或預防紋理狀態紊亂的成分之化 妝品，藉此可選擇適於測試者的肌膚之化妝品。此類成分 例如更新促進成分、膠原蛋白合成促進劑、去角質層促進 劑及膠原蛋白線維束再構築劑等，可含有其中1種至2種 以上。其中的膠原蛋白線維束再構築劑，係對改善紋理最 具效果。 上述更新促進成分例如視黃酸、植物甾醇苷、植物甾 〇 醇、鞘胺醇或類固醇等。上述膠原蛋白合成促進劑例如麥 芽玉米萃取物等。上述去角質層促進劑例如α -羥酸等。 膠原蛋白線維束再構築劑例如迷迭香萃取物或烏索酸衍生 物等。 另一方面，若輸出的顯示係測試者的皮膚紋理之狀態 良好之鑑別値時，藉由選擇只含保濕成分的化妝品’可維 持紋理狀態，可選擇適於測試者的肌膚之化妝量。上述保 濕成分例如肝素類似物質等。此類成分係可含於化妝品而 發揮其效果，其含量宜個別爲0.01~5.0質量％ 。當業者依 -16- 200949291 據顯示的紋理之鑑別値，而適當地選擇此類成分，藉此可 選擇適當之化妝品。其中一例，以下所示係針對下述5階 段的紋理鑑別値之化妝品成分之選擇例。此類成分不僅可 含於化妝品，當然亦可含於其他皮膚外用劑。 <紋理鑑別値一化妝品成分> 1 (佳）—保濕成分 2 _膠原蛋白合成促進劑、保濕成分 3 -膠原蛋白合成促進劑、去角質層促進劑、保濕成 〇 分 4 -膠原蛋白線維束再構築劑、膠原蛋白合成促進 劑、保濕成分 5(差）-膠原蛋白線維束再構築劑、膠原蛋白合成促進劑、 去角質層促進劑、保濕成分 <依據鑑別的肌膚的皺紋評價値之皮膚外用劑之選擇法> 依據由上述鑑別法或鑑別裝置而鑑別之皴紋之評價 値’和紋理的場合相同，可選擇適於鑑別的肌虜影像的測 〇試者 之皮膚外用劑。依據鑑別的皺紋之評價値，而選擇的 化妝品之一例’以下所示係針對下述3階段的皺紋鑑別値 之化妝品成分之選擇例。 <皺紋鑑別値-化妝品成分> 1 (佳）一保濕成分 2 —膠原蛋白合成促進劑、去角質層促進劑、保濕成 分 3(差）-膠原蛋白線維束再構築劑、膠原蛋白合成促進劑、 去角質層促進劑、保濕成分 -17- 200949291 上述化妝品之選擇中，不僅紋理或皺紋之鑑別値，亦 可組合各種肌膚特性値或皮膚表面形態之觀察結果、嗜好 性等其他指標而使用。與此類其他指標之組合亦屬於本發 明的技術之範疇。此類其他指標，具體而言，例如經表皮 水分蒸散量（TEWL )或傳導等皮膚特性値或由紙帶剝取而 得的角質層細胞之特性値（例如細胞面積、細胞體積、細 胞面積之分散、細胞之扁平度、細胞之排列規則性、角質 層之重層剝離、有核細胞之存在）、由此特性値所推斷的皮 0 膚之保水作用、皮脂分泌量、皮膚的加齡程度、黑色素產 生能、皮膚色、肌虜性及肌膚質等。其中，尤宜與紋理狀 態及皺紋狀態關係匪淺之保水作用。 以下，說明本發明的實施例，惟本發明之範圍不受限 於此。 實施例 實施例1 <爲紋理、皺紋的目視評價之處理> 〇 從30位10~50歲的女性之臉頰中央，採取複製標本， 使用毛利得克斯（股）的化妝用顯微鏡，從複製標本儲存 影像作爲數位數據。使用灌有爲進行上述影像處理的軟體 之通用個人電腦，對此影像進行干擾處理，變換爲亮度影 像後，進行十字二値化處理及短直線選配處理，算出與皮 膚溝紋有關之物理量。物理量例如皮膚溝紋面積（參考第 8圖）、皮膚溝紋平均粗度（參考第9圖）、皮虜溝紋粗度 之不齊程度、皮膚溝紋之間隔、皮虜溝紋之平行度、皮膚 溝紋方向' 皮膚溝紋密度爲始之17個物理量，並算出。從 -18- 200949291 第8圖及第9圖清楚可知，此類物理量係清楚地表示皮膚 溝紋或皮丘的凹凸之特徵，爲視覺上非常易於評價之指標。 實施例2 <紋理的目視評價之自動鑑別> _ 使用採取自女性的臉頰中央的複製標本之紋理的5階 段評價用基準照片（參考第6圖：發明者等以母集團1000 張爲依據而作成），由3位專業的肌膚評價者所評價的肌虜 的複製之數位影像及其目視評價値數據15，000張中，選擇 Q 肌膚的紋理之評價値1~5(1:佳〜5:差）之數位影像，各 評價値200張，共計1000張。上述專業的肌虜之評價者， 係具有1年以上的美容、審美或肌膚評價硏究之經驗，且 繼續接受肌虜評價訓練者。以此1000張爲對象，使用實施 例1所示之方法來算出物理量。其次，隨機地分成各500 張的A群和B群二群，使1 ~5的目視評價値各100張，以 A群的500張爲對象，紋理的目視評價作爲目標變數，17 個物理量作爲說明變數，進行重回歸分析（SPSS股份公司 Q 製）算出預測式之重回歸式（重相關係數=0.909 )。針對 剩餘的B群之5 00張影像，將已算出的物理量帶入此重回 歸式之說明變數，而鑑別紋理的目視評價値（自動鑑別 値）。使用之物理量係如表2所示，結果係如表3所示。 -19- 200949291 表2 短直線角度矩形圖係以5°刻紋由0°至180°之値 物理量名稱 物Μ定義 短直線條iL2 短讎之總條數 皮膚溝紋平均 颇溝紋酿之平均値 皮虜溝紋分tsa 颇溝紋酿之分散（不齊） 皮膚溝紋間隔·2 皮虜溝紋間隔之平均値 皮虜溝紋平行R2 每角度的短直線條數之分散 細溝紋密度分112 挪溝紋密度之分散（不齊） 歪度 90·180_2 每角度的短直線條數的、視90度至180度的矩形圖爲正規分布時之歪度 尖度 90-180J2 每角度的短直線條數的、視90度至180度的矩形圖爲正規分布時之尖度 後半最大雛 短直線角度矩形圚95。以上時之最大條數 前半最大雛 短直線角度矩形圖10。以上，90*以下時之最大條數 粗度最頻數 粗度矩形圖之最大値 最頻酿位置 酿矩形圖爲最大時之酿 連結數總計 短直廳ms數讎之總計値 前半最大±1 前半最大頻度的角度和前後±1 (5*)的角度和短直線條數總計値 前半小計 短直線角度矩形圖KT以上，90"以下之總計條數 後半小計 短直線角度矩形圖95°以上之總計條數 後半最大頻 短直線角度矩形圚95·以上時之最大條數 前半最大頻度_2 短直線角度矩形圖10。以上，90。以下時之最大條數 mmMmm 粗度矩形圖之最大値 粗度計測點IU 酿度數數據之總計値 短直線開始點最大値_2 短直線開始點集合狀態矩形圖之最大値 波峰後的粗度政2 粗度爲4至12的數據度數之總計値I The identification method of the present invention can identify the texture of the tendon, the crease of the skin, or both, from the skin image. <Acquisition of tendon image for use in the present invention> The present invention uses a tendon image. The method of obtaining the skin image is a method of directly capturing the skin and obtaining a skin image, and a method of obtaining a tendon image by taking a copy of the specimen from the skin. The method of obtaining an image, for example, by a stereo microscope, by a digital video recorder, or by using a commercially available digital microscope. Such a digital microscope is, for example, a cosmetic microscope of Maoridex (stock) 200949291 or a digital microscope of Qi Yansi (share). In the present invention, a method of obtaining a skin image by taking a copy from the skin as described above is preferred. By taking the image of the tendon taken from the replicated specimen of the skin, only the shape information can be obtained by removing the color information on the surface of the skin, so that disturbance such as dirt can be prevented. Further, the unevenness of the surface of the tendon (non-skin groove or the unevenness of the ridge grade) which is not necessary for analysis is eliminated by the copying, and the analysis is facilitated. The following is a method of obtaining a skin image by copying a specimen. Q A lens of the microscope is placed at a position 90° from the copy of the specimen, and the light is irradiated at an angle suitable for copying the specimen. The microscope can obtain a negative image of the surface unevenness of the replicated specimen due to incident light as an image. The copying specimen refers to a transparent plastic sheet which is softened by a solvent, and is coated with a solvent for softening. After softening, the softened portion is pushed onto the skin, and the unevenness on the skin is transferred to the softened portion by observing the unevenness. The technique of observing the unevenness on the skin indirectly, the representative technology is "river law". This technology is used to accurately transfer the unevenness on the skin and is excellent in the preservation of the unevenness. It is widely used in the field of cosmetic science since ancient times. To make a set of such replicated specimens, a set that is already sold can be used. For related replicate specimens, the cheeks or the outer corners of the eyes should be 1.5 cm x 1.5 cm. In a typical method, such replicated specimens are typically illuminated by directing light perpendicular to the plane of the replication surface. In other words, the unevenness of the transfer causes the scattered light to be scattered, and the amount of transmitted light is reduced to observe the unevenness as an image. In the identification method of the present invention, the observation of the replication is preferably carried out under the conditions of the second. The concave and convex portions of the replica are facing the image capturing direction, and the light is irradiated at an angle of 10 to 40 degrees, particularly preferably 20 to 30 degrees, and the image is reflected by the reflected light (photographed as 200949291). By adopting such a form, the unevenness transferred to the copying surface appears with a clearer luminosity difference. Table 1 shows the evaluation of the sharpness observed when the incident angle was changed for the same test article. Evaluation criteria: 清晰: clear, △: slightly unclear, X: unclear. Table 1 Incident angle (elevation angle) Concavity and convexity sharpness 10 degrees Ο-Δ 25 degrees 〇40 degrees Ο-Δ 〇<cross binary image processing> The present invention relates to the above-obtained tendon image, including a cross Image processing for two-dimensional processing and/or short-line matching processing. The image processing of this type is described in Japanese Laid-Open Patent Publication No. 2008-0681 (Patent Document 7), which is described below. The most basic image processing method, for example, is to separate the background and the object from the image, and to take out the binary processing method in the shape of the object. When the contrast between the object and the background is sufficiently matched, it is easy to be dichotomized. However, in fact, there is a subtle change in the boundary between the main object and the background, so it is difficult to set a valve for the purpose of obtaining a high-precision shape. Further, when the background shading standard is changed due to uneven illumination or the like, the valve is fixed to the entire surface, and it is difficult to obtain a correct shape. In this way, the valve 値' without changing the valve 値's dynamic valve 値 treatment (variable valve 値 treatment) is preferred. The present cross 値 processing method is a dynamic valve 値 processing method. The processing range of the dynamic valve 値 treatment method is generally the rectangular shape of 200949291, but the cross-division treatment method has a cross shape suitable for obtaining the shape of the skin groove (refer to Fig. 2). By using this cross-twisting treatment method, it is possible to detect images due to the convex portion of the skin groove, which is affected by the unevenness of the illumination of the irradiation, from the thick and clear skin groove to the fine skin groove. The overall picture of the grain can be obtained with a uniform and high-precision cross-twist image (refer to Figure 3). The cross-division treatment can be carried out by using the epidermal tissue quantification device described in JP-A-2008-06 1892. 0 <Short-line matching image processing> The short-line matching method described above is a method of calculating the physical quantity of the object shape in the binarized image. In the previous method, the number of pixels of the object is measured, and the number of pixels of the object is measured to calculate the physical quantity such as area, length, and center of gravity. In contrast, the short line matching method is composed of a plurality of pixels. The short straight line (the length of the number of pixels to the tens of pixels, the width is 1 pixel) calculates the physical quantity in units. Specifically, the end point of the object range is the starting point of the short line, and if the end point of the short line is within the object range, the next short line is connected with the final point as a new starting point. If the end point of the short line is outside the range of the object, the link ends. Repeat this operation until the object range is covered by a short line. After that, the number of short straight lines in the range of the embedded object, the angle, and the like are measured, and the feature amount of the object is calculated (refer to FIG. 4). According to this method, a short, continuous, and directional short-line selection of skin groove characteristics can be obtained (refer to Figure 5). The short-line matching treatment can be carried out by using the skin tissue quantification device described in JP-A-2008-061 892. Although the image processing described above can perform only one of the image processing, -10-200949291, by performing image processing of both, the physical quantity can be calculated more accurately. Other image processing such as brightness conversion processing, binarization processing, filtering processing, general image processing (area, perimeter, aspect ratio, center of gravity, needle ratio, enlargement, and inversion) can be performed in response to other needs. <Calculation of physical quantity of texture and/or wrinkles> In the present invention, image processing including the above-described cross-division processing and/or short-line matching processing is performed, and the physical quantity of the skin image can be obtained. This physical quantity is a physical quantity that quantifies the characteristics such as skin wrinkles and ridges of the skin. The physical quantity of such a 0, for example, the area of the skin groove groove, the average thickness of the skin groove, the unevenness of the skin groove width, the interval of the skin groove, the parallelism of the skin groove, the direction of the skin groove, The physical quantity such as the skin groove density is the first, and more advanced steps, for example, the maximum number of 95° or more in the number of short straight lines per angle, and the maximum number of 10° or more and 90° or less in the number of short straight lines per angle. Number, the maximum number of short straight lines for each thickness, the thickness of the largest number of short straight lines for each thickness, the total number of short straight connecting numbers, 每种, each thickness The total amount of the shortness of the number of short straight lines is equal to the physical quantity of the finer, and the present invention calculates the physical quantity which is equivalent to the texture and the wrinkles from such physical quantities. Specifically, it can be defined as the area of the skin groove = the area of the image of the treated object, the area occupied by the skin groove or the total number of short lines selected; the average thickness of the skin groove = (each of the matching start points The total thickness of the skin groove thickness / the total number of starting points); the degree of unevenness of the skin groove thickness = the standard deviation or dispersion calculated from the roughness of the skin groove thickness and the number of strips; the skin groove The average interval = ι / (the area of the skin groove / the average thickness of the skin groove); the parallelism of the skin groove = the peak concentration or dispersion calculated from the angle of the skin groove and the number of strips; The grooving pattern -11 - 200949291 Direction • Density = the number of short lines at angle 0 (the height of the rectangle) / the length of the skin groove. Other physical quantities can be calculated from the above formula. The physical quantity obtained in the present invention is often present as described above, but is selected as the applicable physical quantity from which the prediction formula described later is calculated. The calculation of such physical quantities may include the above-described image processing including cross-division processing and/or short-line matching processing, and processing using a program on a computer. <Predictive Formula> In order to discriminate the texture and/or wrinkles of the tendon, a prediction formula showing the relationship between the physical quantity of the skin and the visual evaluation of the texture and/or wrinkles of the tendon is found in advance. The predictive formula can be created by the following exemplary methods. The skin reproduction (hereinafter referred to as sample) such as skin condition or age is fully considered, and the evaluator evaluates the texture and/or wrinkles visually. On the other hand, the physical quantity of the skin of the sample was calculated by the above method. The number of samples should preferably be 100 or more, and more preferably 500 or more. The visual evaluation of texture and/or wrinkles is based on a 3 to 10 stage reference photograph for judging that the texture is good to poor, or wrinkles is less than 3, and is equivalent to a suitable plural evaluator representing a third party. The evaluation sample of the above reference photograph was given to the corresponding reference photograph. The above-mentioned evaluators who are commensurate with the third party should be experienced in aesthetic, aesthetic or tendon evaluation for more than one year and continue to receive tendon evaluation training. The maximum enthalpy and minimum enthalpy of the evaluation 各 of each sample were removed, and the average 値 was evaluated visually for the texture and/or wrinkles of the sample. The texture and wrinkles of the skin evaluated by the tendon state are discussed by the Japan Cosmetics Technician Association or the International Federation of Cosmetic Technicians (IFSCC). The third party can objectively understand the texture and wrinkles of the skin. Understanding. Figures 6 and 7 show examples of reference photographs based on statistical processing -12-200949291 benchmarking (5-stage evaluation) and wrinkles (3-stage evaluation). Such a reference photograph is in this technical field, and if the base group is 100, it can be judged as a reference photograph having a considerable degree of reliability. If the parent group exceeds 1,000, it can be judged to be a relatively high reliability. The reference photo is a measure of the difference between each reference photo. In the above-mentioned sample evaluation of the present invention, it is possible to use a reference photograph which is based on such statistical processing, and the parent group in the case of creating a reference photograph is preferably 1,000 or more. 0 Next, the physical quantity of the skin and the calculated skin are visually evaluated from the texture and/or wrinkles thus obtained, and the prediction formula is derived. The predictive expression can be obtained by multivariate analysis of the physical quantity of the skin and the visual evaluation of the texture and/or wrinkles. Multivariate analysis should be used to explain the relationship between variables and target variables, such as discriminant analysis, principal component analysis, factor analysis, quantitative theory, quantitative theory, quantitative theory, regression analysis (MLR, PLS) , PCR, mathematical logic), multi-element method, grouping of teachers, neural network, ensemble, learning, etc., can be predicted using free software or commercially available software. Among them, it is particularly important to focus on regression analysis, discriminant analysis, and quantitative theory. In an ideal example, the physical quantity of the skin is used as a explanatory variable, and the visually evaluated texture and/or wrinkles are visually evaluated as the target variable, and the heavy regression analysis is performed to obtain the regression equation, and the double regression equation is used as the predictive expression. As described above, the physical quantity of the tendon used for the calculation of the predictive formula has various physical quantities. However, from the viewpoint of improving the accuracy of the present identification method, it is preferable to contain the physical quantity related to the skin groove, thereby further enhancing the identification method. From the point of view of accuracy, it is advisable to contain substances related to skin grooves, such as ̄ ̄ ̄ ̄. The total number of physical quantities calculated for the predictive formula is preferably ίο or more. <Identification Step> The physical quantity of the skin is brought into a predetermined predictive formula to obtain an evaluation, whereby the texture and/or wrinkles of the tendon can be identified. The physical quantity of the skin calculated from the acquired image is brought into the prediction formula to obtain a visual evaluation of the texture and/or wrinkles of the tendon. Through the above steps, the patented invention can identify the texture and/or wrinkles of the tendon with great precision. Further, a novel high-accuracy discrimination is expected, which is to incorporate the physical quantity of the sample or the visual evaluation price into the database, and to improve the accuracy of the prediction by updating and correcting. <Identification device-program> Other aspects of the present invention are programs for performing the above steps. In other words, the identification program of the tendon includes the following functions: calculating the physical quantity by using a computer to obtain a physical quantity from the acquired skin image, calculating the skin from a pre-prepared predictive formula and the physical quantity of the calculated skin. The means of texture and / or wrinkle evaluation. The authentication program of the present invention can be used in a hardware device such as a personal computer. Furthermore, other aspects of the invention are the identification means for performing the above steps. That is, a device for identifying the texture and/or wrinkles of the skin, which comprises means for loading a pre-prepared predictive means, means for obtaining a skin image, and calculating the physical quantity of the skin from the acquired tendon image. A means for calculating the texture and/or wrinkles of the skin and a means for displaying the calculated evaluation by the predicted formula prepared in advance and the physical quantity of the skin calculated as described above. The mode of the above identification device will be described in the first diagram. Identification of the Invention -14- 200949291 The device can be a general-purpose computer such as a personal computer or a dedicated computer for authentication. The input unit 1 is an input means for predicting the above-described prediction formula, and the prediction formula used for discrimination is input in advance. For example, an input device such as a keyboard can be used. The image acquisition unit 2 is a means for acquiring a tendon image, and a digital video recorder or a commercially available digital microscope can be used. The CPU 3 (Central Processing Unit) calculates the physical quantity of the skin from the acquired tendon image, and calculates the texture of the skin by means of a predictive formula prepared in advance and a physical quantity of the calculated tendon. / or the method of evaluation of crepe. By installing the above-mentioned discrimination process, it can be used as such. RAM4 (Random Access Memory) is a means of storing temporary data. The display unit 5 is a means for outputting the calculated evaluation, and may be, for example, a display device such as a liquid crystal display or an output device such as a lister. The processing flow of the above authentication apparatus will be described with reference to FIG. First, a skin image is obtained by acquiring a part from an image such as a digital video recorder. As described above, it can be directly photographed from the tester's tendon, or the skin image obtained by copying the specimen can be processed by the CPU for image processing such as cross-twisting and short-line matching processing. Calculate the physical quantity of the tendon image. The type of the physical quantity of the calculated tendon image is appropriately set in accordance with the type of the physical quantity used for calculating the predictive expression input by the input means in advance. The calculated physical quantity of the skin image is also incorporated into the predictive formula input in advance in the CPU, and the evaluation result is calculated. The calculated evaluation system is output from an output means such as a liquid crystal display. In the present invention, the texture and wrinkles of the tendon can be identified once by individually inputting the predictive expression relating to the texture of the skin and the predictive expression relating to the wrinkles of the tendon in advance, or can be individually identified. -15- 200949291 <Selection of skin external preparation according to the texture of the identified tendon> According to the evaluation of the texture identified by the above identification method or the identification device, a test suitable for the use of the skin image can be selected. Skin external preparation. By using the identification method or the authentication device of the present invention, it can be quickly identified because it can be almost the same high precision as the expert evaluates the skin, and accordingly, depending on the result, the skin which helps maintain, prevent or improve the texture state of the tendon can be selected. External preparation. The choice of external preparation for skin, especially in the selection of cosmetics, if the display of output 0 is the identification of the skin texture of the tester, the selection of a cosmetic containing ingredients for improving the texture state or preventing the disorder of the texture state, This can be selected as a cosmetic suitable for the skin of the tester. Such a component, for example, a renewal-promoting component, a collagen synthesis promoter, an exfoliating layer-promoting agent, a collagen-strand-reconstruction agent, and the like may be contained in one or more of them. Among them, the collagen thread reticle reconstitutor has the most effect on improving the texture. The above-mentioned renewal promoting component is, for example, retinoic acid, phytosterol glycosides, plant sterols, sphingosine or steroids. The above collagen synthesis promoter is, for example, a malt corn extract or the like. The above exfoliating layer promoter is, for example, α-hydroxy acid or the like. A collagen nevi beam reconstitution agent such as rosemary extract or ursolic acid derivative. On the other hand, if the output is displayed in a state in which the skin texture of the tester is good, the cosmetic amount of the skin which is suitable for the tester can be selected by selecting the cosmetic containing only the moisturizing component to maintain the texture state. The above-mentioned moisturizing component is, for example, a heparin-like substance or the like. Such a component may be contained in a cosmetic to exert its effect, and the content thereof is preferably 0.01 to 5.0% by mass. The manufacturer appropriately selects such ingredients according to the identification of the textures shown in the above-mentioned paragraphs, whereby an appropriate cosmetic can be selected. As an example, the following is an example of selection of a cosmetic component for the texture identification of the following five stages. Such ingredients may be included not only in cosmetics, but also in other skin external preparations. <Texture Identification 値一化妆品 Cosmetic Ingredients> 1 (Good) - Moisturizing Ingredients 2 _ Collagen Synthesis Accelerator, Moisturizing Ingredients 3 - Collagen Synthesis Accelerator, Exfoliating Layer Promoter, Moisturizing 〇 4 - Collagen Line Dimension Bundle reconstitutor, collagen synthesis accelerator, moisturizing ingredient 5 (poor)-collagen line retinoic reconstitutor, collagen synthesis promoter, exfoliating layer promoter, moisturizing ingredient < Evaluation of wrinkles based on the identified skin値Selection method of external preparation for skin> According to the evaluation of the ridge pattern identified by the above-mentioned identification method or identification device, the skin external preparation for measuring the tendon image suitable for identification is selected in the same manner as in the case of texture. . An example of a cosmetic selected based on the evaluation of the identified wrinkles is shown below as an example of the selection of the cosmetic component of the following three-stage wrinkle discrimination. <Wrinkle Identification 値-Cosmeceutical Ingredients> 1 (Good)-Hydrating Ingredients 2 - Collagen Synthesis Accelerator, Exfoliating Layer Promoter, Moisturizing Ingredient 3 (Poor) - Collagen Line Dimensional Reconstitutor, Collagen Synthesis Promotion Agent, exfoliating layer enhancer, moisturizing ingredient -17- 200949291 The selection of the above cosmetics, not only the identification of texture or wrinkles, but also the combination of various skin characteristics, skin surface morphology observations, tastes and other indicators . Combinations with such other indicators are also within the scope of the technology of the present invention. Such other indicators, specifically, for example, skin properties such as transepidermal water evapotranspiration (TEWL) or conduction, or characteristics of stratum corneum cells obtained by stripping from a paper strip (eg, cell area, cell volume, cell area) Dispersion, flatness of cells, regularity of cells, heavy layer peeling of stratum corneum, presence of nucleated cells), water retention of skin dermatology, sebum secretion, degree of skin ageing, Melanin produces energy, skin color, tendon and skin texture. Among them, it is particularly suitable for the water retention effect which is related to the texture state and the wrinkle state. Hereinafter, the embodiments of the present invention will be described, but the scope of the present invention is not limited thereto. EXAMPLES Example 1 <Process for visual evaluation of texture and wrinkles> 复制From the center of the cheeks of 30 women aged 10 to 50, copying specimens, using a makeup microscope using Maoridex (s) Copy the specimen to store the image as digital data. This image is subjected to interference processing using a general-purpose personal computer equipped with a software for performing the above-described image processing, and converted into a luminance image, and then subjected to cross-division processing and short-line matching processing to calculate a physical quantity related to the skin groove. Physical quantity such as skin groove area (refer to Figure 8), skin groove average thickness (refer to Figure 9), unevenness of skin ridge groove thickness, skin groove spacing, skin ridge groove parallelism The skin groove direction 'The skin groove density is the first 17 physical quantities, and is calculated. As is clear from Figures 8 and 9 of -18-200949291, such physical quantities clearly indicate the characteristics of the skin groove or the unevenness of the ridge, which is an indicator that is visually very easy to evaluate. Example 2 <Automatic Identification of Visual Evaluation of Texture> _ A 5-phase evaluation reference photograph using the texture of a replica specimen taken from the center of the cheek of a woman (refer to Fig. 6: Inventor, etc. based on 1000 sheets of the parent group) In the 15,000 sheets, the texture of the skin of the skin was evaluated by the evaluation of the digital image of the skin of the skin, and the evaluation of the texture of the skin was selected from 1 to 5 (1: good ~) 5: Poor digital image, each evaluation of 200, a total of 1000. The above-mentioned professional tendon evaluators have more than one year of experience in beauty, aesthetics, or skin evaluation, and continue to receive tendon evaluation trainers. The physical quantity was calculated using the method shown in Example 1 for the purpose of 1,000 sheets. Next, it is randomly divided into 500 groups of A group and B group, and 100 points of each of 1 to 5 are evaluated, and 500 sheets of group A are targeted. The visual evaluation of the texture is used as the target variable, and 17 physical quantities are used as the target. The variables were described, and the re-regression analysis (SPSS Co., Ltd. Q system) was performed to calculate the weighted regression equation of the prediction formula (re-correlation coefficient = 0.909). For the 500 images of the remaining B groups, the calculated physical quantities are brought into the recursive explanatory variables, and the visual evaluation of the texture is identified (automatic identification 値). The physical quantities used are shown in Table 2, and the results are shown in Table 3. -19- 200949291 Table 2 Short-angle angle rectangle chart with 5° engraving from 0° to 180° 値 physical quantity name Μ definition short straight line iL2 total number of short 皮肤 皮肤 skin 平均 average average ditch pattern値 虏 虏 ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts ts Divided by 112. The density of the groove is uneven. (歪) 90.180_2 The number of short lines per angle, the 90-180 degree rectangle is the normal distribution. The sharpness is 90-180J2. The rectangular figure of the number of short straight lines, which is 90 degrees to 180 degrees, is the sharpness of the second half of the straight line and the rectangular angle of the rectangle 圚95. The maximum number of the above time The first half of the largest young short straight angle angle rectangle Figure 10. Above, the maximum number of thicknesses below 90*, the maximum frequency, the maximum number of rectangles, the maximum size, the most frequent brewing position, the number of brewing rectangles, the total number of brewing joints, the total number of short straight halls, the number of ms, the total number of the first half, the maximum of the first half, ±1, the first half Maximum frequency angle and front and rear ±1 (5*) angle and short line number total 値Front half subtotal short straight angle angle rectangle KT or more, 90"The total number of the following is the second half subtotal short straight angle angle rectangle 95° or more The number of bars in the second half of the maximum frequency is short. The angle of the rectangle 圚95· or more The maximum number of the first half maximum frequency _2 The short straight angle rectangle Figure 10. Above, 90. The maximum number of times below mmMmm The maximum thickness of the rectangle chart is the maximum thickness measurement point IU The total number of the data is 値 Short line starting point maximum 値_2 Short line starting point set state The rectangular chart is the largest after the peak wave 2 Total of data degrees with a thickness of 4 to 12値
表3 目視評價値（自動鑑別値） 1 2 3 4 5 巨 視 評 價 1 47 49 4 0 0 2 19 68 13 0 0 3 4 33 57 5 1 4 0 0 14 54 32 5 0 0 0 15 85 表3係表示本專利發明中所得的紋理之目視評價値 (自動鑑別値）與紋理的目視評價之總計表。Spearman之 -20- 200949291 相關係數爲0.887，二評價値的完全一致爲62% ，容許1 階段的不—致，爲98% ，可知本發明的紋理之鑑別法具相 當充分之精確度。 實施例3 將實施例2中的A群和B群交換’使用針對B群的影 像而製作的重回歸式（重相關係數=〇.935)，鑑別A群的 紋理之目視評價値（自動鑑別値）。結果係如表4所示。 曰視評僭値（自動鑑別値） 1 2 3 4 5 巨 視 評 價 1 29 66 5 0 0 2 8 70 21 1 0 3 2 28 60 10 0 4 0 1 39 55 5 5 0 0 4 47 49 表4 __Table 3 Visual Evaluation 値 (Automatic Identification 値) 1 2 3 4 5 Giant Vision Evaluation 1 47 49 4 0 0 2 19 68 13 0 0 3 4 33 57 5 1 4 0 0 14 54 32 5 0 0 0 15 85 Table 3 A table showing the visual evaluation of the texture obtained in the present invention (automatic identification 値) and the visual evaluation of the texture. Spearman's -20-200949291 correlation coefficient is 0.887, the second evaluation 値 is completely consistent with 62%, and the one-stage ignorance is 98%. It can be seen that the texture identification method of the present invention has relatively sufficient precision. Example 3 The group A and the group B in Example 2 were exchanged for 'regression using the image for the group B (re-correlation coefficient = 935.935), and the visual evaluation of the texture of the group A was identified (automatic identification) value). The results are shown in Table 4. Despise evaluation (automatic identification) 1 2 3 4 5 Judging evaluation 1 29 66 5 0 0 2 8 70 21 1 0 3 2 28 60 10 0 4 0 1 39 55 5 5 0 4 47 49 Table 4 __
表4係表示本專利發明中所得的紋理之目視評價値 (自動鑑別値）與紋理的目視評價之總計表。Spearman之 相關係數爲0.861，二評價値的完全一致爲53¾ ’容許1 階段的不一致，爲97% ，由此結果可知’對於未知之數據’ 可進行具高精確度之自動鑑別。 實施例4 <皴紋的目視評價之自動鑑別> 實施例2中，選擇肌虜的皺紋之評價値1~3之數位影 像，各評價値200張，共計600張，和實施例2同樣地進 行。由重回歸分析所得的重回歸視之重相關係數爲0.912， 皴紋的目視評價値（自動鑑別値）與駿'紋的目視評價値之 Spearman的相關係數爲0.705，二評價値的完全一致爲65 -21- 200949291 % ，容許1階段的不一致，爲100% ’可知本發明的皺紋之 鑑別法具相當充分之精確度。 實施例5 將實施例4中的A群和B群之數據交換，同樣地進行 自動鑑別之結果’所得的重回歸式之重相關係數= 0.820, 皺紋的目視評價値（自動鑑別値）與皺紋的目視評價値之 Spearman的相關係數爲0.880，二評價値的完全一致爲84 % ，容許1階段的不一致，爲100% ，由此結果可知，於皺 紋之評價，對於未知之數據，亦可進行具高精確度之自動 鑑別。 實施例6 <紋理的目視評價之自動鑑別> 實施例2中，以紐拉爾網絡（Neural Ware公司製）取 代重回歸分析，以A群爲對象用於教師學習，以紋理的目 視評價値作爲應對變數，藉由物理量進行學習，而得預測 式。將肌膚的物理量帶入所得的預測式，鑑別B群的紋理 之目視評價値C自動鑑別値）。結果如表5所示。 表5 目視評價値（自動鑑別値） 1 2 3 4 5 巨 視 評 價 1 48 47 5 0 0 2 18 62 19 1 0 3 0 37 55 7 1 4 0 0 15 56 29 5 0 0 0 18 82Table 4 is a table showing the visual evaluation of the texture obtained by the present invention (automatic identification 値) and the visual evaluation of the texture. Spearman's correlation coefficient is 0.861, and the second evaluation 完全 is completely consistent with 533⁄4 ‘allowing 1 phase inconsistency, which is 97%. From this result, it can be known that 'unknown data' can be automatically identified with high accuracy. Example 4 <Automatic Identification of Visual Evaluation of Python Patterns> In Example 2, the evaluation of the wrinkles of the tendon was performed on the digital images of 値1 to 3, and each of the evaluations was 200 sheets, totaling 600 sheets, and the same as in the second embodiment. Conducted. The re-regression coefficient of the re-regression analysis obtained by the re-regression analysis was 0.912, and the correlation coefficient between the visual evaluation of the crepe pattern (automatic identification 値) and the visual evaluation of the ''s pattern was 0.705, and the second evaluation was completely consistent. 65 -21- 200949291 %, allowing one-stage inconsistency, is 100% 'The wrinkle identification method of the present invention is sufficiently accurate. Example 5 The data of Group A and Group B in Example 4 were exchanged, and the result of automatic discrimination was similarly obtained. 'The re-regression coefficient of the obtained re-regression coefficient = 0.820, visual evaluation of wrinkles 自动 (automatic identification 値) and wrinkles The visual correlation evaluation of Spearman's correlation coefficient is 0.880, the second evaluation 値 is completely consistent with 84%, and the one-stage inconsistency is allowed to be 100%. From this result, it can be known that the evaluation of wrinkles can be performed for unknown data. Automatic identification with high precision. Example 6 <Automatic Identification of Visual Evaluation of Texture> In the second embodiment, the Nuol network (manufactured by Neural Ware Co., Ltd.) was used instead of the re-regression analysis, and the group A was used for the teacher learning, and the visual evaluation of the texture was performed. As a response to variables, 値 is learned by physical quantities, and predictive expressions are obtained. The physical quantity of the skin is brought into the obtained predictive formula, and the visual evaluation of the texture of the B group is identified 値C automatically identifies 値). The results are shown in Table 5. Table 5 Visual evaluation 値 (automatic identification 値) 1 2 3 4 5 Giant Vision Evaluation 1 48 47 5 0 0 2 18 62 19 1 0 3 0 37 55 7 1 4 0 0 15 56 29 5 0 0 0 18 82
表5係表示本專利發明中所得的紋理之目視評價値 (自動鑑別値）與紋理的目視評價之總計表。Sp earman 之 -22- 200949291 相關係數爲0.871，二評價値的完全一致爲62¾ ’容許1 階段的不一致，爲99% 。由此結果可知，即使使用重回歸 分析以外之多變量解析方法來作成預測式，亦可進行具高 精確度之自動鑑別。 實施例7 在實施例2中，以表6所示之3個物理量爲說明變數’ 進行重回歸分析（SPSS股份公司製）算出重回歸式（重相 關係數= 0.880)。Spearman之相關係數爲0.831’二評價値 的完全一致爲47% ，容許1階段的不一致，爲95% 。可知 ^ 雖物理量之數目少亦可進行精確度佳之鑑別，惟物理量之 數目多者，可更提升精確度。 表6 短直線角度矩形圖係以5°刻紋由0°至180°之値 物理量名稱 物理量定義 前半小計 短直線角度矩形圖10°以上，90°以下之總計條數 粗度最頻敫2 粗度矩形圖之最大値 波峰後的髓St2 粗度爲4至12的數據度數之總計値 實施例8 Q 關於紋理及皺紋的鑑別之實施例與比較例，評價之一 致率及1個樣品之評價所需時間（秒）’總結於表7及表8。 亦即，藉由目視評價的基準之3位專業的肌膚評價者（訓 練者）之紋理評價（比較例1)及皺紋評價（比較例2)， 及藉由非訓練者（說明第6、7圖的基準照片並使用而進行） 之紋理評價（比較例3 )及皺.紋評價（比較例4 )。更進一 步，實施例1〜2中，不使用十字二値化及短直線選配處理， 而進行二値化處理及細線化處理（對於標本化而得的二値 化影像中的連結圖形，進行處理成線圖形，使不失連結 -23- 200949291 性），使用由該處理所得的統計上之一般物理量，與皮丘有 關之總面積、標準偏差、總個數、單位面積、與細線波峰 間隔有關之平均値、標準偏差、標準誤差、變動係數等， 和實施例2同樣地鑑別。此紋理及皺紋的目視評價値（自 動鑑別値），分別爲比較例5及6。 表7 紋理 完全一致率（％ ) 1階段不合之一致率（％) 所需時間（秒） 實施例2 62 98 1 實施例3 53 97 1 實施例6 62 99 2 it較例1 — — 2-3 比較例3 45 82 21 比較例5 50 84 1 表8 皺紋 完全一致率（％ ) 1階段不合之一致率（％ ) 所需時間（秒） 實施例4 65 100 1 實施例5 84 100 1 比較例2 — — 2 比較例4 49 88 18 比較例6 54 89 1 <依據紋理自動鑑別値之化妝品選擇法之使用試驗> 相關於以女性測試者爲對象，依據紋理鑑別値之化妝 品選擇法之有效性，進行化妝品之長期使用試驗。 首先，根據以下所示之處方，依據一般化妝品之調製 方法，調製與肌虜的紋理狀態對應之5種類的化妝品（化 妝品1 ~ 5 )。 (化妝品1 :紋理自動鑑別値1用之化妝品） 含量 5質量％ 成分 甘油 -24- 200949291 Ο 〇 1，3- 丁二醇 5質量％ 大豆蛋白 0.1質量％ 肝素類似物質 0.1質量％ 乙醇 5質量％ 羥基苯甲酸甲酯 0.1質量％ 水 剩餘量 妝品2 :紋理自動鑑別値 2用之化妝 甘油 5質量％ 1，3_ 丁二醇 5質量％ 麥芽玉米萃取物 0.1質量％ 大豆蛋白 0.1質量％ 肝素類似物質 0.1質量％ 乙醇 5質量％ 羥基苯甲酸甲酯 0.1質量％ 水 剩餘量 妝品3 :紋理自動鑑別値 3用之化妝 甘油 5質量％ 1，3 _ 丁二醇 5質量％ 麥芽玉米萃取物 0.1質量％ 乳酸鈉 0.1質量％ 大豆蛋白 0.1質量％ 肝素類似物質 0.1質量％ 乙醇 5質量％ 羥基苯甲酸甲酯 0.1質量％ 水 剩餘量 化妝品4 :紋理自動鑑別値4用之化妝品 -25- 200949291Table 5 is a table showing the visual evaluation of the texture obtained by the present invention (automatic identification 値) and the visual evaluation of the texture. Sp earman's -22-200949291 correlation coefficient is 0.871, and the second evaluation 完全 is completely consistent with 623⁄4 ‘allowing 1 phase inconsistency, 99%. From this result, it is understood that even if a multivariate analysis method other than the re-regression analysis is used to create the prediction expression, automatic discrimination with high accuracy can be performed. [Embodiment 7] In the second embodiment, the double regression equation (manufactured by SPSS AG) was used to calculate the double regression equation (the number of heavy correlations = 0.880) by using the three physical quantities shown in Table 6 as explanatory variables. Spearman's correlation coefficient is 0.831'. The two evaluations are completely consistent with 47%, and the one-stage inconsistency is 95%. It can be seen that although the number of physical quantities is small, the accuracy can be accurately identified, but the number of physical quantities can increase the accuracy. Table 6 Short-line angle rectangle chart is defined by 5° to 180° 値 physical quantity name physical quantity first half subtotal short straight angle angle rectangle 10° or more, total number of 90° or less coarseness most frequency 敫 2 thick The total number of data degrees of the myeloid St2 thickness after the maximum crest peak of the degree histogram is 4 to 12 値 Example 8 Q Regarding the identification of texture and wrinkles, the agreement rate of evaluation and the evaluation of one sample The required time (seconds) is summarized in Tables 7 and 8. That is, the texture evaluation (Comparative Example 1) and the wrinkle evaluation (Comparative Example 2) of the three professional skin evaluators (trainers) based on the visual evaluation criteria, and the non-trainers (Notes 6, 7) Texture evaluation (Comparative Example 3) and wrinkle evaluation (Comparative Example 4) of the reference photograph of the figure were performed. Further, in the first to second embodiments, the cross-twisting process and the short-line matching process are not performed, and the binarization process and the thinning process are performed (the link pattern in the binarized image obtained by the specimen is performed. Process the line graph so that it does not lose the link -23- 200949291), use the statistical general physical quantity obtained from the treatment, the total area, standard deviation, total number, unit area, and fine line peak interval associated with the ridge The average enthalpy, standard deviation, standard error, coefficient of variation, and the like were identified in the same manner as in Example 2. The visual evaluation of the texture and wrinkles (automatic identification) was Comparative Examples 5 and 6, respectively. Table 7 Texture complete agreement rate (%) 1 phase mismatch rate (%) Time required (seconds) Example 2 62 98 1 Example 3 53 97 1 Example 6 62 99 2 it compare example 1 - 2- 3 Comparative Example 3 45 82 21 Comparative Example 5 50 84 1 Table 8 Wrinkle complete agreement rate (%) 1 phase mismatch rate (%) Time required (seconds) Example 4 65 100 1 Example 5 84 100 1 Comparison Example 2 - 2 Comparative Example 4 49 88 18 Comparative Example 6 54 89 1 <Use test for cosmetics selection method based on automatic identification of texture> Related to cosmetics selection method based on texture discrimination for female testers The effectiveness of the long-term use of cosmetics. First, according to the following points, according to the general cosmetic preparation method, five types of cosmetics (cosmetic products 1 to 5) corresponding to the texture state of the tendon are prepared. (Cosmetics 1: Texture for automatic identification of 値1 for cosmetics) Content 5 mass% Component glycerin-24- 200949291 Ο 〇1,3-1,3-butanediol 5 mass% Soy protein 0.1% by mass Heparin-like substance 0.1% by mass Ethanol 5% by mass Methyl hydroxybenzoate 0.1% by mass Water Residue Cosmetics 2 : Automatic texture identification 値 2 Cosmetic glycerin 5 mass% 1,3_ butanediol 5 mass % Malt corn extract 0.1% by mass Soy protein 0.1% by mass Heparin Similar substance 0.1% by mass Ethanol 5% by mass Methyl hydroxybenzoate 0.1% by mass Water residual makeup 3: Automatic identification of texture 値3 Cosmetic glycerin 5 mass% 1,3 _ butanediol 5 mass% Malt corn extract 0.1% by mass Sodium lactate 0.1% by mass Soy protein 0.1% by mass Heparin-like substance 0.1% by mass Ethanol 5% by mass Methyl hydroxybenzoate 0.1% by mass Water remaining amount Cosmetics 4: Texture automatic identification 値4 for cosmetics-25- 200949291
甘油 6質量％ 1，3 — 丁二醇 5質量％ 迷迭香萃取物 0.1質量％ 麥芽玉米萃取物 0.1質量％ 大豆蛋白 0.1質量％ 烏索酸硬脂醯酯 0.1質量％ 肝素類似物質 0.1質量％ 乙醇 10質量％ 羥基苯甲酸甲酯 0.1質量％ 水 剩餘量 (化妝品5 :紋理自動鑑別値 5用之化妝 甘油 7質量％ 1,3— 丁二醇 5質量％ 迷迭香萃取物 0.1質量！ 麥芽玉米萃取物 0.1質量％ 乳酸鈉 0.1質量％ 大豆蛋白 0.1質量％ 烏索酸硬脂醯酯 0.1質量％ 肝素類似物質 0.1質量％ 乙醇 1 5質量％ 羥基苯甲酸甲酯 0.1質量％ 水 剩餘量 其次，以隨機選出80位健康女性參與者（年齡32~57 歲）爲對象，分爲A和B二群使年齡分布無差異。a群係 使用實施例2求得的重回歸式，自動地算出臉頰複製標本 之紋理鑑別値，給予對應於此紋理自動鑑別値1 ~5之化妝 -26- 200949291 品1〜5。B群亦同樣地算出紋理自動鑑別値，惟，無視此紋 理自動鑑別値，而給予紋理自動鑑別値5用之化妝品5。 使A、B二群參與者使用所給予的化妝品3個月，使用後同 樣地算出紋理自動鑑別値。藉由「紋理改善値」=「使用 試驗前之紋理自動鑑別値」-「使用後之紋理自動鑑別 値」，算出紋理改善値，並算出每群之平均値。試驗期間， 若有試驗者投訴所使用之化妝品係「不適於肌膚」時，則 停止使用化妝品，而屏除於評價對象之外。結果如表9所 示。由表9可知，採用本發明的化妝品選擇法時，無不適 於肌膚之試驗者，且具有紋理改善效果。 表9 是否採用化 妝品選擇法 使用前找理鑑 別値（人數） 紋理改善値之 平均 投訴化妝品不撕 黯之人數 A群（有） 1 (5 人） 0.00 0人 2 (7人） 0.29 0人 3 (10 人） 0.60 0人 4 (11 人） 0.82 0人 5 (7 人） 1.00 0人 B群（無） 1 (6 人） 0.00 4人 2 (8人） 0.17 2人 3 (10 人） 0.56 1人 4 (9人） 0.78 0人 5 (7 人） 1.00 0人 <依據皺紋自動鑑別値之化妝品選擇法之使用試驗> 相關於以女性測試者爲對象，依據皺紋鑑別値之化妝 品選擇法之有效性，進行化妝品之長期使用試驗。 首先，根據以下所示之處方，依據一般化妝品之調製 方法，調製與肌虜的皺紋狀態對應之3種類的化妝品（化 妝品1 ~ 3 )。 -27- 200949291 Ο Ο 成分 含量 甘油 5質量％ 1,3— 丁二醇 5質量％ 麥芽玉米萃取物 0.1質量％ 大豆蛋白 0.1質量％ 肝素類似物質 0.1質量％ 乙醇 10質量％ 羥基苯甲酸甲酯 0.1質量％ 水 剩餘量 妝品2 :皺紋自動鑑別値 2用之化妝品 甘油 5質量％ 1,3— 丁二醇 5質量％ 麥芽玉米萃取物 0.1質量％ 乳酸鈉 0.1質量％ 大豆蛋白 0.1質量％ 肝素類似物質 0.1質量％ 乙醇 10質量％ 羥基苯甲酸甲酯 0.1質量％ 水 剩餘量 妝品3 :皺紋自動鑑別値 3用之化妝品 甘油 7質量％ 1，3 _ 丁二醇 5質量％ 迷迭香萃取物 0.1質量％ 麥芽玉米萃取物 0.1質量％ 乳酸鈉 0.1質量％ -28- 200949291 大豆蛋白 烏索酸硬脂醯酯 肝素類似物質 乙醇 羥基苯甲酸甲酯 水 其次，以隨機選出72位 0.1質量％ 0.1質量％ 0.1質量％ 15質量％ 0.1質量％ 剩餘量 康女性參與者（年齡30~58 歲）爲對象，分爲Α和Β二群使年齡分布無差異。Α群係Glycerin 6 mass% 1,3 - butanediol 5 mass% rosemary extract 0.1 mass% malt corn extract 0.1 mass% soy protein 0.1 mass% stearic acid decyl ester 0.1 mass% heparin analog substance 0.1 mass % Ethanol 10% by mass Hydroxybenzoic acid methyl ester 0.1% by mass Water remaining amount (Cosmetics 5: Texture automatic identification 値5 Cosmetic glycerin 7 mass% 1, 3-butanediol 5 mass% Rosemary extract 0.1 mass! Malt corn extract 0.1% by mass Sodium lactate 0.1% by mass Soy protein 0.1% by mass Stearic acid octoate 0.1% by mass Heparin-like substance 0.1% by mass Ethanol 15% by mass Hydroxybenzoic acid methyl ester 0.1% by mass Water remaining amount 80 healthy female participants (aged 32-57 years old) were randomly selected and divided into two groups, A and B, so that there was no difference in age distribution. Group a was automatically calculated using the regression formula obtained in Example 2. The texture identification of the cheek copy specimen is given to the makeup -26-200949291 item 1~5 corresponding to the texture automatic identification 値1~5. The B group also calculates the texture automatic identification 値, However, regardless of the texture, the texture is automatically identified, and the texture is automatically identified. 5 The cosmetics are used for the A and B groups of participants for 3 months, and the texture is automatically identified after use. "Texture Improvement" = "Use the texture before the test to automatically identify 値" - "Automatically identify the texture after use", calculate the texture improvement 値, and calculate the average 値 of each group. During the test, if there is a complaint from the tester When the cosmetics were "not suitable for the skin", the cosmetics were stopped and the screen was excluded from the evaluation object. The results are shown in Table 9. As can be seen from Table 9, when the cosmetic selection method of the present invention was used, it was not suitable for the skin test. And the texture improvement effect. Table 9 Whether to use the cosmetics selection method to find the identification before use (number of people) Texture improvement 値 The average complaint of cosmetics does not tear the number of people A group (Yes) 1 (5 people) 0.00 0 people 2 (7 persons) 0.29 0 people 3 (10 persons) 0.60 0 people 4 (11 persons) 0.82 0 people 5 (7 persons) 1.00 0 people B group (none) 1 (6 persons) 0.00 4 people 2 (8 persons) 0.17 2 people 3 (10 ) 0.56 1 person 4 (9 people) 0.78 0 people 5 (7 persons) 1.00 0 people <Use test for the cosmetic selection method based on automatic identification of wrinkles> Related to the female tester, based on wrinkle identification The long-term use test of cosmetics is carried out in the effectiveness of the cosmetics selection method. First, according to the following description, three kinds of cosmetics (cosmetics 1 to 3) corresponding to the wrinkle state of the tendon are prepared according to the general cosmetic preparation method. -27- 200949291 Ο Ο Component content glycerin 5 mass% 1,3 - butanediol 5 mass% malt corn extract 0.1 mass% soy protein 0.1 mass% heparin analog substance 0.1 mass% ethanol 10 mass% methyl hydroxybenzoate 0.1% by mass Water Remaining Cosmetics 2: Wrinkle Automatic Identification 値2 Cosmetic glycerin 5 mass% 1,3 - butanediol 5 mass% Malt corn extract 0.1% by mass Sodium lactate 0.1% by mass Soy protein 0.1% by mass Heparin Similar substance 0.1% by mass Ethanol 10% by mass Hydroxybenzoic acid methyl ester 0.1% by mass Water remaining amount Cosmetics 3: Automatic identification of wrinkles 値3 for cosmetics glycerin 7 mass% 1,3 _ butanediol 5 mass% rosemary extract 0.1% by mass Malt corn extract 0.1% by mass Sodium lactate 0.1% by mass -28- 200949291 Soy protein ursolic acid stearyl ester Heparin-like substance Ethyl hydroxybenzoate water followed by 72 randomly selected 0.1% by mass 0.1 Mass% 0.1% by mass 15% by mass 0.1% by mass The remaining females (aged 30 to 58 years old) are divided into Α and Β No difference in the age distribution of the population. Α群
Ο 使用實施例4求得的重回歸式，自動地算出臉頰複製標本 之皺紋鑑別値，給予對應於此皺紋自動鑑別値1〜3之化妝 品1 ~3。B群亦同樣地算出皺紋自動鑑別値，惟，無視此皺 紋自動鑑別値，而給予皺紋自動鑑別値2用之化妝品2。 使A、B二群參與者使用所給予的化妝品6個月，使用後同 樣地算出皺紋自動鑑別値。藉由「皺紋改善値」=「使用 試驗前之皺紋自動鑑別値」-「使用後之皺紋自動鑑別 値」，算出皺紋改善値，並算出每群之平均値。結果如表 10所示。由表10可知，採用本發明的化妝品選擇法時，具 有皺紋改善效果。 表10 是否採用化妝品選擇法 使用前之皺紋鑑別値（人數) 皺紋改善値之平均 A群（有） 1 (10 人） 0.00 2 (15 人） 0.27 3 (11 人） 0.45 B群（無） 1 (9 人） 0.00 2 (15 人） 0.27 3 (12 人） 0.25 應用於產業上之可能性 -29- 200949291 依據本發明，可提供一種無論於何處，均可容易地、 高精確度且迅速地鑑別肌虜之紋理或皴紋之技術。其結 果’例如於百貨公司或商店等，可提供對於肌虜或美容的 諮詢或化妝品選擇有助益之資訊。 【圖式簡單說明】 第1圖表示複製品的亮度影像之圖（圖面代替相片） 第2圖表示十字二値化處理法之圖（圖面代替相片） 第3圖表示藉由十字二値化處理之複製品之影像之圖 0 (圖面代替相片） 第4圖表示短直線選配處理法之圖（圖面代替相片） 第5圖表示藉由短直線選配處理之複製品之影像之圖 (圖面代替相片） 第6圖表示紋理的基準相片之影像（左：評價値 右：評價値5 )(圖面代替相片） 第7圖表示皴紋的基準相片之影像（左：評價値1， 右：評價値3)(圖面代替相片） Q 第8圖表示十字二値化處理及短直線選配處理後的物 理量之皮膚溝紋的面積之圖（圖面代替相片） 第9圖表示十字二値化處理及短直線選配處理後的物 理量之皮膚溝紋平均粗度之圖（圖面代替相片） 第10圖表示鑑別裝置之構成例之圖》 第11圖相關於鑑別裝置的處理之流程圖》 【主要元件符號說明】 無0 -30-Using the re-regression equation obtained in Example 4, the wrinkle discrimination 脸 of the cheek replica specimen was automatically calculated, and the cosmetics 1 to 3 corresponding to the wrinkle automatic discrimination 値 1 to 3 were given. The B group also calculates the automatic identification of wrinkles in the same manner. However, the wrinkles are automatically identified to identify the wrinkles, and the wrinkles are automatically identified. The two groups of participants A and B were given the cosmetics for 6 months, and the wrinkles were automatically identified after use. By "wrinkle improvement 値" = "automatic identification of wrinkles before use test" - "automatic identification of wrinkles after use", the wrinkle improvement 算出 is calculated, and the average 値 of each group is calculated. The results are shown in Table 10. As is apparent from Table 10, the use of the cosmetic selection method of the present invention has a wrinkle improving effect. Table 10 Whether the use of cosmetic selection method before wrinkle identification 値 (number of people) Wrinkle improvement 平均 average group A (Yes) 1 (10 persons) 0.00 2 (15 persons) 0.27 3 (11 persons) 0.45 B group (none) 1 (9 persons) 0.00 2 (15 persons) 0.27 3 (12 persons) 0.25 Industrially applicable possibilities -29- 200949291 According to the present invention, it is possible to provide an easy, high-accuracy and rapidity regardless of where A technique for identifying the texture or crepe of a tendon. The results, such as in department stores or stores, can provide information on the consultation or cosmetic selection of tendons or beauty. [Simple description of the drawing] Figure 1 shows the image of the brightness image of the replica (the picture instead of the photo). Figure 2 shows the picture of the cross-division process (the picture instead of the photo). Figure 3 shows the cross with the cross. Figure 0 of the image of the reproduced copy (the picture replaces the photo) Figure 4 shows the picture of the short line matching method (the picture instead of the photo) Figure 5 shows the image of the copy processed by the short line matching Figure (picture instead of photo) Figure 6 shows the image of the reference photo of the texture (left: evaluation 値 right: evaluation 値 5) (picture instead of photo) Figure 7 shows the image of the reference photo of the crepe (left: evaluation値1, Right: Evaluation 値3) (Picture instead of photo) Q Figure 8 shows the area of the skin groove of the physical quantity after the cross-twisting process and the short-line matching process (the picture instead of the photo) The figure shows the average thickness of the skin groove of the physical quantity after the cross dimerization process and the short line matching process (the picture instead of the photo) Fig. 10 shows the structure of the identification device. Fig. 11 relates to the identification device Flow chart of processing Symbol Description None 0-30-