Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning
===============================
利用判别特征導向的詞典庫學習來進行病理學圖像分類
文章發表于 IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 35, NO. 3, MARCH 2016
總體思路：提取特征 –> 對特征進行分類
本文提出了一種提取特征的算法DFDL（ Discriminative
Feature-oriented Dictionary Learning），用于學習某一類别特定的詞典庫，用于圖檔分類或者病理學圖像評分。本實驗在3個實驗集（乳腺癌，腎肺脾ADL，腦惡性良性腫瘤TCGA）上做測試。
主要算法思想，每一類生成一個詞典，詞典的子空間可以生成該類的特征表示；任何其他類别的表示都跟這個表示距離很大。類似于類内間距最小，類間間距最大的KNN聚類方法。
方法流程：
論文筆記：Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary LearninHistopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning 
論文筆記：Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary LearninHistopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning 論文筆記：Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary LearninHistopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning Y 是某一類，Y拔是互補類， D 是字典，s是 i 類的稀缺表示，yl 是真是label， 是以生成該式：
論文筆記：Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary LearninHistopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning 利用多次疊代求解。
主要步驟如下：
論文筆記：Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary LearninHistopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning 論文筆記：Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary LearninHistopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning 學習到的詞典：
論文筆記：Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary LearninHistopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning 
