1、image filtering：linear——box filter，gaussian filter
non-linear——median filter、Bilateral filter、Guided Image Filter
functions:Texture Match,Model Match,etc;Notation:when do the template match,there are some preprocessing like zero-mean
other methods to do the match：based on the distance——such as:SSD（shotrest square distance）
2、Fourier frequency：refer to the note before——Image Enhance in frequency
3、Image pyramid——Gaussian/Laplacian
Gaussian pyramid——step1：Gaussian smooth
step2：down-sampling
step3：Loop step1&step2
Laplacian pyramid——step1：Gaussian smooth
step2：upsampling
step3：the image before step1 substract the image after step2
step4：loop step1、2、3
4、Image interpolation：nearest/linear etc.
5、Image Blending:refer to the note——Image blending
6、Edge Detection：Canny/Pb boundary detector/Structed Random Forest classifier to judge wheter it is the edge[it is based on the patch level rather than the pixel level]/crisp Boundary Detector
Notation:when doing the operation based on the gradient ,remember smooth the image first!
7、Thresholding operate——Binary image
8、Morphological operators：refer to the folder：the chapter “Reading Book note3” in《OpenCV practical notes》
9、Interesting points corresponding&alignment
a、finding Corner——Harris（rotation invariant），due to based on the gradient operation，it has the illumination invariant but without scale invariant.
b、some feature descriptor:SIFT,HOG,BOW etc.
c、MSER:refer to watershed algorithm overview
10、Fitting and alignment
a、Least square line fitting
b、Total least squares（PCA）——Rotation invariant
***a、b are sensitive to unnormal noise points
c、Hough transfer:refer to" Line Detected by Hough"
d、RANSAC
e、ICP(Iterative closest points)
11、Common transformations：translation/rotation/aspect/affine/perspective——refer to the folder：the chapter “Reading Book note 4” in《OpenCV practical notes》
12、Segmentation&grouping：ways
a、cluster：K-means/mean-shift
b、boundaries（watershed）
c、graph（graph cut，grab cut）
d、labeling
e、gestalt cues（based on the perception information of some shape）
13、Object Detection with statistical template：
a、Examplar-based：K-NN
b、Linear classifier：Logistic regression,Linear SVM
c、None-Linear classifer：Decision Trees/Boosted Decision Trees/Kernelized SVM
d、Generative classifier：Naive Bays
SUMMARIZATION:
