Python-OpenCV 处理图像（四）（五）：图像直方图和反向投影图像中边界和轮廓检测

当我们想比较两张图片相似度的时候，可以使用这一节提到的技术

直方图对比
反向投影

关于这两种技术的原理可以参考我上面贴的链接，下面是示例的代码：

0x01. 绘制直方图

import cv2.cv as cvdef drawGraph(ar,im, size): #Draw the histogram on the imageminV, maxV, minloc, maxloc = cv.MinMaxLoc(ar) #Get the min and max valuehpt = 0.9 * histsizefor i in range(size):intensity = ar[i] * hpt / maxV #Calculate the intensity to make enter in the imagecv.Line(im, (i,size), (i,int(size-intensity)),cv.Scalar(255,255,255)) #Draw the linei += 1#---- Gray image
orig = cv.LoadImage("img/lena.jpg", cv.CV_8U)histsize = 256 #Because we are working on grayscale pictures which values within 0-255hist = cv.CreateHist([histsize], cv.CV_HIST_ARRAY, [[0,histsize]], 1)cv.CalcHist([orig], hist) #Calculate histogram for the given grayscale picturehistImg = cv.CreateMat(histsize, histsize, cv.CV_8U) #Image that will contain the graph of the repartition of values
drawGraph(hist.bins, histImg, histsize)cv.ShowImage("Original Image", orig)
cv.ShowImage("Original Histogram", histImg)
#---------------------#---- Equalized image
imEq = cv.CloneImage(orig)
cv.EqualizeHist(imEq, imEq) #Equlize the original imagehistEq = cv.CreateHist([histsize], cv.CV_HIST_ARRAY, [[0,histsize]], 1)
cv.CalcHist([imEq], histEq) #Calculate histogram for the given grayscale picture
eqImg = cv.CreateMat(histsize, histsize, cv.CV_8U) #Image that will contain the graph of the repartition of values
drawGraph(histEq.bins, eqImg, histsize)cv.ShowImage("Image Equalized", imEq)
cv.ShowImage("Equalized HIstogram", eqImg)
#--------------------------------cv.WaitKey(0)

0x02. 反向投影

import cv2.cv as cvim = cv.LoadImage("img/lena.jpg", cv.CV_8U)cv.SetImageROI(im, (1, 1,30,30))histsize = 256 #Because we are working on grayscale pictures
hist = cv.CreateHist([histsize], cv.CV_HIST_ARRAY, [[0,histsize]], 1)
cv.CalcHist([im], hist)cv.NormalizeHist(hist,1) # The factor rescale values by multiplying values by the factor
_,max_value,_,_ = cv.GetMinMaxHistValue(hist)if max_value == 0:max_value = 1.0
cv.NormalizeHist(hist,256/max_value)cv.ResetImageROI(im)res = cv.CreateMat(im.height, im.width, cv.CV_8U)
cv.CalcBackProject([im], res, hist)cv.Rectangle(im, (1,1), (30,30), (0,0,255), 2, cv.CV_FILLED)
cv.ShowImage("Original Image", im)
cv.ShowImage("BackProjected", res)
cv.WaitKey(0)

————————————————————————————————————————————————分割线————————————————————————————————————————————————





关于边缘检测的基础来自于一个事实，即在边缘部分，像素值出现”跳跃“或者较大的变化。如果在此边缘部分求取一阶导数，就会看到极值的出现。而在一阶导数为极值的地方，二阶导数为0，基于这个原理，就可以进行边缘检测。关于 Laplace 算法原理，可参考

Laplace 算子

0x01. Laplace 算法

下面的代码展示了分别对灰度化的图像和原始彩色图像中的边缘进行检测：

import cv2.cv as cvim=cv.LoadImage('img/building.png', cv.CV_LOAD_IMAGE_COLOR)# Laplace on a gray scale picture
gray = cv.CreateImage(cv.GetSize(im), 8, 1)
cv.CvtColor(im, gray, cv.CV_BGR2GRAY)aperture=3dst = cv.CreateImage(cv.GetSize(gray), cv.IPL_DEPTH_32F, 1)
cv.Laplace(gray, dst,aperture)cv.Convert(dst,gray)thresholded = cv.CloneImage(im)
cv.Threshold(im, thresholded, 50, 255, cv.CV_THRESH_BINARY_INV)cv.ShowImage('Laplaced grayscale',gray)
#------------------------------------# Laplace on color
planes = [cv.CreateImage(cv.GetSize(im), 8, 1) for i in range(3)]
laplace = cv.CreateImage(cv.GetSize(im), cv.IPL_DEPTH_16S, 1)
colorlaplace = cv.CreateImage(cv.GetSize(im), 8, 3)cv.Split(im, planes[0], planes[1], planes[2], None) #Split channels to apply laplace on each
for plane in planes:cv.Laplace(plane, laplace, 3)cv.ConvertScaleAbs(laplace, plane, 1, 0)cv.Merge(planes[0], planes[1], planes[2], None, colorlaplace)cv.ShowImage('Laplace Color', colorlaplace)
#-------------------------------------cv.WaitKey(0)

效果展示原图灰度化图片检测原始彩色图片检测

0x02. Sobel 算法

Sobel 也是很常用的一种轮廓识别的算法。关于 Sobel 导数原理的介绍，可参考

Sobel 导数

以下是使用 Sobel 算法进行轮廓检测的代码和效果

import cv2.cv as cvim=cv.LoadImage('img/building.png', cv.CV_LOAD_IMAGE_GRAYSCALE)sobx = cv.CreateImage(cv.GetSize(im), cv.IPL_DEPTH_16S, 1)
cv.Sobel(im, sobx, 1, 0, 3) #Sobel with x-order=1soby = cv.CreateImage(cv.GetSize(im), cv.IPL_DEPTH_16S, 1)
cv.Sobel(im, soby, 0, 1, 3) #Sobel withy-oder=1cv.Abs(sobx, sobx)
cv.Abs(soby, soby)result = cv.CloneImage(im)
cv.Add(sobx, soby, result) #Add the two results together.cv.Threshold(result, result, 100, 255, cv.CV_THRESH_BINARY_INV)cv.ShowImage('Image', im)
cv.ShowImage('Result', result)cv.WaitKey(0)

处理之后效果图（感觉比Laplace效果要好些）

0x03. cv.MorphologyEx

cv.MorphologyEx 是另外一种边缘检测的算法

import cv2.cv as cvimage=cv.LoadImage('img/build.png', cv.CV_LOAD_IMAGE_GRAYSCALE)#Get edges
morphed = cv.CloneImage(image)
cv.MorphologyEx(image, morphed, None, None, cv.CV_MOP_GRADIENT) # Apply a dilate - Erodecv.Threshold(morphed, morphed, 30, 255, cv.CV_THRESH_BINARY_INV)cv.ShowImage("Image", image)
cv.ShowImage("Morphed", morphed)cv.WaitKey(0)

0x04. Canny 边缘检测

Canny 算法可以对直线边界做出很好的检测；关于 Canny 算法原理的描述，可参考：

Canny 边缘检测

import cv2.cv as cv
import mathim=cv.LoadImage('img/road.png', cv.CV_LOAD_IMAGE_GRAYSCALE)pi = math.pi #Pi valuedst = cv.CreateImage(cv.GetSize(im), 8, 1)cv.Canny(im, dst, 200, 200)
cv.Threshold(dst, dst, 100, 255, cv.CV_THRESH_BINARY)#---- Standard ----
color_dst_standard = cv.CreateImage(cv.GetSize(im), 8, 3)
cv.CvtColor(im, color_dst_standard, cv.CV_GRAY2BGR)#Create output image in RGB to put red lineslines = cv.HoughLines2(dst, cv.CreateMemStorage(0), cv.CV_HOUGH_STANDARD, 1, pi / 180, 100, 0, 0)
for (rho, theta) in lines[:100]:a = math.cos(theta) #Calculate orientation in order to print themb = math.sin(theta)x0 = a * rhoy0 = b * rhopt1 = (cv.Round(x0 + 1000*(-b)), cv.Round(y0 + 1000*(a)))pt2 = (cv.Round(x0 - 1000*(-b)), cv.Round(y0 - 1000*(a)))cv.Line(color_dst_standard, pt1, pt2, cv.CV_RGB(255, 0, 0), 2, 4) #Draw the line#---- Probabilistic ----
color_dst_proba = cv.CreateImage(cv.GetSize(im), 8, 3)
cv.CvtColor(im, color_dst_proba, cv.CV_GRAY2BGR) # idemrho=1
theta=pi/180
thresh = 50
minLength= 120 # Values can be changed approximately to fit your image edges
maxGap= 20lines = cv.HoughLines2(dst, cv.CreateMemStorage(0), cv.CV_HOUGH_PROBABILISTIC, rho, theta, thresh, minLength, maxGap)
for line in lines:cv.Line(color_dst_proba, line[0], line[1], cv.CV_RGB(255, 0, 0), 2, 8)cv.ShowImage('Image',im)
cv.ShowImage("Cannied", dst)
cv.ShowImage("Hough Standard", color_dst_standard)
cv.ShowImage("Hough Probabilistic", color_dst_proba)
cv.WaitKey(0)

原图使用 Canny 算法处理之后标记出标准的直线标记出所有可能的直线

0x05. 轮廓检测

OpenCV 提供一个 FindContours 函数可以用来检测出图像中对象的轮廓：

import cv2.cv as cvorig = cv.LoadImage('img/build.png', cv.CV_LOAD_IMAGE_COLOR)
im = cv.CreateImage(cv.GetSize(orig), 8, 1)
cv.CvtColor(orig, im, cv.CV_BGR2GRAY)
#Keep the original in colour to draw contours in the endcv.Threshold(im, im, 128, 255, cv.CV_THRESH_BINARY)
cv.ShowImage("Threshold 1", im)element = cv.CreateStructuringElementEx(5*2+1, 5*2+1, 5, 5, cv.CV_SHAPE_RECT)cv.MorphologyEx(im, im, None, element, cv.CV_MOP_OPEN) #Open and close to make appear contours
cv.MorphologyEx(im, im, None, element, cv.CV_MOP_CLOSE)
cv.Threshold(im, im, 128, 255, cv.CV_THRESH_BINARY_INV)
cv.ShowImage("After MorphologyEx", im)
# --------------------------------vals = cv.CloneImage(im) #Make a clone because FindContours can modify the image
contours=cv.FindContours(vals, cv.CreateMemStorage(0), cv.CV_RETR_LIST, cv.CV_CHAIN_APPROX_SIMPLE, (0,0))_red = (0, 0, 255); #Red for external contours
_green = (0, 255, 0);# Gren internal contours
levels=2 #1 contours drawn, 2 internal contours as well, 3 ...
cv.DrawContours (orig, contours, _red, _green, levels, 2, cv.CV_FILLED) #Draw contours on the colour imagecv.ShowImage("Image", orig)
cv.WaitKey(0)

效果图：原图识别结果

0x06. 边界检测


from: https://segmentfault.com/a/1190000003742455https://segmentfault.com/a/1190000003742461

全选<button href="javascript:void(0);" _xhe_href="javascript:void(0);" class="copyCode btn btn-xs" data-clipboard-text="" import="" cv2.cv="" as="" cv"="" data-toggle="tooltip" data-placement="bottom" title="" style="color: rgb(255, 255, 255); font-style: inherit; font-variant: inherit; font-stretch: inherit; font-size: 12px; line-height: 1.5; font-family: inherit; margin: 0px 0px 0px 5px; overflow: visible; cursor: pointer; vertical-align: middle; border: 1px solid transparent; white-space: nowrap; padding-right: 5px; padding-left: 5px; border-radius: 3px; -webkit-user-select: none; box-shadow: rgba(0, 0, 0, 0.0980392) 0px 1px 2px; background-image: none; background-color: rgba(0, 0, 0, 0.74902);">复制放进笔记

import cv2.cv as cvim = cv.LoadImage("img/build.png", cv.CV_LOAD_IMAGE_GRAYSCALE)dst_32f = cv.CreateImage(cv.GetSize(im), cv.IPL_DEPTH_32F, 1)neighbourhood = 3
aperture = 3
k = 0.01
maxStrength = 0.0
threshold = 0.01
nonMaxSize = 3cv.CornerHarris(im, dst_32f, neighbourhood, aperture, k)minv, maxv, minl, maxl = cv.MinMaxLoc(dst_32f)dilated = cv.CloneImage(dst_32f)
cv.Dilate(dst_32f, dilated) # By this way we are sure that pixel with local max value will not be changed, and all the others willlocalMax = cv.CreateMat(dst_32f.height, dst_32f.width, cv.CV_8U)
cv.Cmp(dst_32f, dilated, localMax, cv.CV_CMP_EQ) #compare allow to keep only non modified pixel which are local maximum values which are corners.threshold = 0.01 * maxv
cv.Threshold(dst_32f, dst_32f, threshold, 255, cv.CV_THRESH_BINARY)cornerMap = cv.CreateMat(dst_32f.height, dst_32f.width, cv.CV_8U)
cv.Convert(dst_32f, cornerMap) #Convert to make the and
cv.And(cornerMap, localMax, cornerMap) #Delete all modified pixelsradius = 3
thickness = 2l = []
for x in range(cornerMap.height): #Create the list of point take all pixel that are not 0 (so not black)for y in range(cornerMap.width):if cornerMap[x,y]:l.append((y,x))for center in l:cv.Circle(im, center, radius, (255,255,255), thickness)cv.ShowImage("Image", im)
cv.ShowImage("CornerHarris Result", dst_32f)
cv.ShowImage("Unique Points after Dilatation/CMP/And", cornerMap)cv.WaitKey(0)