【database】表情識別Cohn-Kanade Database（CK+）
Cohn-Kanade Database有三個版本，第三個還沒有出，前兩個是CK和CK+，這篇文章看一下CK+這個庫。
CK+資料庫說明檔案
包含四個壓縮包。
- The Images (cohn-kanade-images.zip) - there are 593 sequences across 123 subjects which are FACS coded at the peak frame. All sequences are from the neutral face to the peak expression.
影象集-包括123個人的593條表情序列，表情序列都是從平靜到表情峰值的。在表情峰值用FACS編碼。 - The Landmarks (Landmarks.zip) - All sequences are AAM tracked with 68points landmarks for each image.
表情標記檔案-所有序列的所有影象都用68點標記的AAM標記。 - The FACS coded files (FACS_labels.zip) - for each sequence (593) there is only 1 FACS file, which is the last frame (the peak frame). Each line of the file corresponds to a specific AU and then the intensity. An example is given below.
FACS編碼檔案-593條表情序列每條都有一個FACS檔案，這個檔案標註了每條最後一幀畫面的AU值和強度。 - The Emotion coded files (Emotion_labels.zip) - ONLY 327 of the 593 sequences have emotion sequences. This is because these are the only ones the fit the prototypic definition. Like the FACS files, there is only 1 Emotion file for each sequence which is the last frame (the peak frame). There should be only one entry and the number will range from 0-7 (i.e. 0=neutral, 1=anger, 2=contempt, 3=disgust, 4=fear, 5=happy, 6=sadness, 7=surprise). N.B there is only 327 files- IF THERE IS NO FILE IT MEANS THAT THERE IS NO EMOTION LABEL (sorry to be explicit but this will avoid confusion).
表情編碼檔案-在593個表情序列中，只有327個序列是有表情編碼的，和FACS檔案一樣，也是每個序列有一個表情編碼（最後一幀畫面），表情編碼從0到7（i.e. 0=neutral, 1=anger, 2=contempt, 3=disgust, 4=fear, 5=happy, 6=sadness, 7=surprise）。
PAPER中的說明(CK+)
PAPER(CVPR 2010)：The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression
-
Participants were 18 to 50 years of age, 69% female, 81% Euro-American, 13% Afro-American, and 6% other groups.
參與者18-50歲，69%是女性，81%是歐美裔，13%非裔美國人，6%其他。 -
Image sequences for frontal views and 30-degree views were digitized into either 640x490 or 640x480 pixel arrays with 8-bit gray-scale or 24-bit color values.
影象序列是正面的或者偏離30度的視角，圖片處理成640* 490或者640* 480尺寸，畫素點為8位元灰度值或者24位元彩色值。 -
AU-Action Unit Labels
43個AU label對應的的面部動作，這些也是手動標記在FACS coded檔案中的。
-
特定的表情和一些特定的AU label的對應關係
-
兩種特徵提取
-
SPTS: The similarity normalized shape, sn, refers to the 68 vertex points in sn for both the x- and y- coordinates, resulting in a raw 136 dimensional feature vector. These points are the vertex locations after all the rigid geometric variation (translation, rotation and scale), relative to the base shape, has been removed. The similarity normalized shape sn can be obtained by synthesizing a shape instance of s, using Equation 1, that ignores the similarity parameters p. An example of the similarity normalized shape features, SPTS, is given in Figure 2. AU0 normalization was used in this work, by subtracting the features of the first frame (which was neutral).
SPTS：相似性歸一化形狀sn指的是x和y座標中的sn中的68個頂點，從而產生原始的136維特徵向量。 這些點是在相對於基本形狀的所有剛性幾何變化（平移，旋轉和縮放）被移除之後的頂點位置。
-
CAPP: The canonical normalized appearance a0 refers to where all the non-rigid shape variation has been normalized with respect to the base shape s0. This is accomplished by applying a piece-wise affine warp on each triangle patch appearance in the source image so that it aligns with the base face shape. For this study, the resulting 87×93 synthesized grayscale image was used. In previous work [3], it was shown by removing the rigid shape variation, poor performance was gained. As such, only the canonical normalized appearance features a0 were used in this paper.
CAPP：規範歸一化外觀a0指的是所有非剛性形狀變化相對於基本形狀s0歸一化的地方。 這是通過在源影象中的每個三角形貼片外觀上應用分段仿射扭曲來實現的，以使其與基面形狀對齊。 對於這項研究，使用87*93的合成灰度影象。
