Python-OpenCV 处理图像（六）(七)（八）：对象识别 图像灰度化处理 图像二值化处理

为了加快处理速度，在图像处理算法中，往往需要把彩色图像转换为灰度图像。

0x00. 灰度图

R=G=B

R=G=B

import cv2.cv as cv
image = cv.LoadImage('mao.jpg')
b = cv.CreateImage(cv.GetSize(image), image.depth, 1)
g = cv.CloneImage(b)
r = cv.CloneImage(b)

cv.Split(image, b, g, r, None)
cv.ShowImage('a_window', r)

cv.WaitKey(0)

image = cv.LoadImage('mao.jpg')
new = cv.CreateImage(cv.GetSize(image), image.depth, 1)
for i in range(image.height):
for j in range(image.width):
new[i,j] = max(image[i,j][0], image[i,j][1], image[i,j][2])
cv.ShowImage('a_window', new)
cv.WaitKey(0)

image = cv.LoadImage('mao.jpg')
new = cv.CreateImage(cv.GetSize(image), image.depth, 1)
for i in range(image.height):
for j in range(image.width):
new[i,j] = (image[i,j][0] + image[i,j][1] + image[i,j][2])/3
cv.ShowImage('a_window', new)
cv.WaitKey(0)

image = cv.LoadImage('mao.jpg')
new = cv.CreateImage(cv.GetSize(image), image.depth, 1)
for i in range(image.height):
for j in range(image.width):
new[i,j] = 0.3 * image[i,j][0] + 0.59 * image[i,j][1] +  0.11 * image[i,j][2]
cv.ShowImage('a_window', new)
cv.WaitKey(0)

image = cv.LoadImage('mao.jpg')
new = cv.CreateImage(cv.GetSize(image), image.depth, 1)
for i in range(image.height):
for j in range(image.width):
new[i,j] = image[i,j][1]
cv.ShowImage('a_window', new)
cv.WaitKey(0)

—————————————傲娇的分割线———————————————

0x00. 特征识别

GoodFeaturesToTrack

extractSURF

import cv2.cv as cv
import math

im = cv.LoadImage("img/church.png", cv.CV_LOAD_IMAGE_GRAYSCALE)
im2 = cv.CloneImage(im)

# Goodfeatureto track algorithm
eigImage = cv.CreateMat(im.height, im.width, cv.IPL_DEPTH_32F)
tempImage = cv.CloneMat(eigImage)
cornerCount = 500
quality = 0.01
minDistance = 10

corners = cv.GoodFeaturesToTrack(im, eigImage, tempImage, cornerCount, quality, minDistance)

radius = 3
thickness = 2

for (x,y) in corners:
cv.Circle(im, (int(x),int(y)), radius, (255,255,255), thickness)

cv.ShowImage("GoodfeaturesToTrack", im)

#SURF algorithm
hessthresh = 1500 # 400 500
dsize = 0 # 1
layers = 1 # 3 10

keypoints, descriptors = cv.ExtractSURF(im2, None, cv.CreateMemStorage(), (dsize, hessthresh, 3, layers))
for ((x, y), laplacian, size, dir, hessian) in keypoints:
cv.Circle(im2, (int(x),int(y)), cv.Round(size/2), (255,255,255), 1)
x2 = x+((size/2)*math.cos(dir))
y2 = y+((size/2)*math.sin(dir))
cv.Line(im2, (int(x),int(y)), (int(x2),int(y2)), (255,255,255), 1)

cv.ShowImage("SURF ", im2)

cv.WaitKey(0)

0x01. 人脸识别

#import library - MUST use cv2 if using opencv_traincascade
import cv2

# rectangle color and stroke
color = (0,0,255)       # reverse of RGB (B,G,R) - weird
strokeWeight = 1        # thickness of outline

# set window name
windowName = "Object Detection"

# load an image to search for faces
img = cv2.imread("mao.jpg")

# load detection file (various files for different views and uses)
cascade = cv2.CascadeClassifier("haarcascade_frontalface_alt.xml")

# preprocessing, as suggested by: http://www.bytefish.de/wiki/opencv/object_detection # img_copy = cv2.resize(img, (img.shape[1]/2, img.shape[0]/2))
# gray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
# gray = cv2.equalizeHist(gray)

# detect objects, return as list
rects = cascade.detectMultiScale(img)

# display until escape key is hit
while True:

# get a list of rectangles
for x,y, width,height in rects:
cv2.rectangle(img, (x,y), (x+width, y+height), color, strokeWeight)

# display!
cv2.imshow(windowName, img)

# escape key (ASCII 27) closes window
if cv2.waitKey(20) == 27:
break

# if esc key is hit, quit!
exit()

0x00. 图像二值化

0x01. 图像二值化处理

import cv2.cv as cv
image = cv.LoadImage('mao.jpg')

new = cv.CreateImage(cv.GetSize(image), image.depth, 1)
for i in range(image.height):
for j in range(image.width):
new[i,j] = max(image[i,j][0], image[i,j][1], image[i,j][2])

cv.Threshold(new, new, 10, 255, cv.CV_THRESH_BINARY_INV)
cv.ShowImage('a_window', new)
cv.WaitKey(0)

0x02. cv.Threshold

cv.Threshold(src, dst, threshold, maxValue, thresholdType)

参数说明：

src：原始数组 (单通道 , 8-bit of 32-bit 浮点数)。
dst：输出数组，必须与 src 的类型一致，或者为 8-bit。
threshold：阈值
maxValue：使用 CV_THRESH_BINARY 和 CV_THRESH_BINARY_INV 的最大值。
threshold_type：阈值类型
threshold_type=CV_THRESH_BINARY:
如果 src(x,y)>threshold ,dst(x,y) = max_value; 否则,dst（x,y）=0;
threshold_type=CV_THRESH_BINARY_INV:
如果 src(x,y)>threshold,dst(x,y) = 0; 否则,dst(x,y) = max_value.
threshold_type=CV_THRESH_TRUNC:
如果 src(x,y)>threshold，dst(x,y) = max_value; 否则dst(x,y) = src(x,y).
threshold_type=CV_THRESH_TOZERO:
如果src(x,y)>threshold，dst(x,y) = src(x,y) ; 否则 dst(x,y) = 0.
threshold_type=CV_THRESH_TOZERO_INV:如果 src(x,y)>threshold，dst(x,y) = 0 ; 否则dst(x,y) = src(x,y).