三、openCV学习笔记（Image Processing）

（一） Image Filtering

    使用Filter时注意边界可能需要插值，borderInterpolate()。

   BaseColumnFilter: filters with single-column kernels.

   BaseFilters:2D image filters using 2D kernels.

   BaseRowFilter:filters with single-row kernels.

   FilterEngine:apply an arbitrary filtering operation to an image.

   bilateralFilter:

   adaptiveBilateralFilter:

   blur: Blurs an image using the normalized box filter.

   broderInterpolate: Computes the source location of an extrapolated pixel.

   boxFilter: Blurs an image using the box filter.

   buildPyramid:Constructs the Gaussian pyramid for an image.

   copyMakeBroder: Forms a border around an image.

   createBoxFilter:

   createDerivFilter: Returns an engine for computing image derivatives.

   createGaussianFilter:Returns an engine for smoothing images with the Gaussian filter.

   createLinearFilter:

   createMorphologyFilter:

   createSeparableFilter:

   dilate:

   erode:

   filter2D: Convolves an image with the kernel.

   GaussianBlur:

   getDerivKernels:

   getGaussianKernels:

   getKernelType:

   getStructuringElement:

   medianBlur:

   morphologyEx:Performs advanced morphological transformations.

   Laplacian:

   pyrDown: Blurs an image and downsamples it.

   pyrUp: Upsamples an image and then blurs it.

   pyrMeanShiftFiltering:

   sepFilter2D:

   Smooth:

   Sobel:

   Scharr:

详细介绍：http://docs.opencv.org/2.4.9/modules/imgproc/doc/filtering.html

（二）Geometric Image Transformations

注意：Extrapolation of non-existing pixels.

            Interpolation of pixel values.

           包括一些空间变换。

详细介绍：http://docs.opencv.org/2.4.9/modules/imgproc/doc/geometric_transformations.html#undistortpoints

（三）Miscellaneous Image Transformations

        adaptive threshold: Applies an adaptive threshold to an array.

        cvtColor: Converts an image from one color space to another.

        distanceTransform: Calculates the distance to the closest zero pixel for each pixel of the source image.

        floodFill: Fills a connected component with the given color.

        intergral: Calculates the integral of an image.

        threshold:

        watershed: Performs a marker-based image segmentation using the watershed algorithm.

        grabCut: 不知道干啥的。

详细介绍：http://docs.opencv.org/2.4.9/modules/imgproc/doc/miscellaneous_transformations.html#

（四）Histogram

详细介绍：http://docs.opencv.org/2.4.9/modules/imgproc/doc/histograms.html#

（五）Structural Analysis and Shape descriptors

        moment: ???

        findContours:

        approxPolyDP: Approximates a polygonal curve(s) with the specified precision.

        ApproxChains: Approximates Freeman chain(s) with a polygonal curve.

        arcLength: Calculates a contour perimeter or a curve length.

        boundingRect: Calculates the up-right bounding rectangle of a point set.

        coutourArea: Calculates a contour area.

        convexHull: Finds the convex hull of a point set.

        convexityDefects: Finds the convexity defects of a contour.

        fitEllipse:

        fitLine:

        isContourConvext: Tests a contour convexity.

        minAreaRect: Finds a rotated rectangle of the minimum area enclosing the input 2D point set.

        minEnclosingCircle: Finds a circle of the minimum area enclosing a 2D point set.

        matchShapes: Compares two shapes.

        pointPolygonTest: Performs a point-in-contour test.

 详细介绍：http://docs.opencv.org/2.4.9/modules/imgproc/doc/structural_analysis_and_shape_descriptors.html#

（六）Motion analysis and Object tracking

详细介绍：http://docs.opencv.org/2.4.9/modules/imgproc/doc/motion_analysis_and_object_tracking.html#

（七）Feature Detection

        Canny

        conerEigenValsAndVecs:Calculates eigenvalues and eigenvectors of image blocks for corner detection.

        cornerHarris:Harris edge detector.

        cornerMinEigenVal: Calculates the minimal eigenvalue of gradient matrices for corner detection.

        cornerSubPix: Refines the corner locations.

        goodFeaturesToTrack: Determines strong corners on an image.

        HoughCircles: Finds circles in a grayscale image using the Hough transform.

        HoughLines: Finds lines in a binary image using the standard Hough transform.

        HoughLinesP: Finds line segments in a binary image using the probabilistic Hough transform.

        preCornerDetect: Calculates a feature map for corner detection.

详细介绍：http://docs.opencv.org/2.4.9/modules/imgproc/doc/feature_detection.html#  

（八）Object Detection

       matchTemplate: Compares a template against overlapped image regions.