计算机视觉图像处理基础知识（下）

2021-12-21 22:30:01 阅读：155 来源： 互联网

标签：gray plt img show res cv2 基础知识图像处理视觉

计算机视觉图像处理Opencv基础知识 (附详解代码)下

-此部分内容为在学习唐宇迪老师课程中，自己微调后部分知识以及代码，想更多了解移步唐老师课程。*
计算机视觉图像处理基础知识(上)

Canny边缘检测算法

1.滤波：高斯滤波
2.计算梯度强度及方向 sobel算子
3.非极大值抑制
4.双阈值
5.抑制孤立弱边缘

img = cv2.imread('eagle.jpg',cv2.IMREAD_GRAYSCALE)
v1 = cv2.Canny(img,80,150)
v2 = cv2.Canny(img, 50,100)
res = np.hstack((v1,v2))
cv_show(res,'res')

图像金字塔

img = cv2.imread('pyr.jpg')
cv_show(img,'img')
print(img.shape)

#上采样（对比金字塔，从上而下）
up = cv2.pyrUp(img)
cv_show(up,'up')
print(up.shape)

#下采样（对比金字塔，从下而上）
down = cv2.pyrDown(img)
cv_show(img,'img')
print(down.shape)

down2 = cv2.pyrDown(down)
cv_show(down2,'down2')
print(down2.shape)

up2 = cv2.pyrUp(down2)
up_down = cv2.pyrDown(up2)
cv_show(up_down, 'up_down')

cv_show(np.hstack((down2,up_down)),'up_down2')

拉普拉斯金字塔
Li = Gi - PyrUp(PyrDown(Gi))

img = cv2.imread('giraffe.jpg')
down = cv2.pyrDown(img)
up_down = cv2.pyrUp(down)
l_1 = img - up_down
cv_show(l_1,'l_1')

图像轮廓

img = cv2.imread('eagle.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray,127,255,cv2.THRESH_BINARY)
cv_show(thresh,'thresh')

contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
#绘制轮廓
#传入绘制图像，轮廓，轮廓索引，颜色模式，线条厚度
#一定要使用copy，否则原图会改变
draw_img = img.copy()
res = cv2.drawContours(draw_img, contours, -1,(0,0,255),2)
cv_show(res,'res')

轮廓特征

cnt = contours[1]   #取第i+1个轮廓
#面积
cv2.contourArea(cnt)
#周长
cv2.arcLength(cnt,True)

轮廓近似

img = cv2.imread('pipi.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 127,255,cv2.THRESH_BINARY)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt = contours[-1]

draw_img = img.copy()
res = cv2.drawContours(draw_img, [cnt], -1, (0,0,255),2)
cv_show(res,'res')

epsilon = 0.05*cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt,epsilon,True)

draw_img = img.copy()
res = cv2.drawContours(draw_img, [approx], -1,(0,0,255),2)
cv_show(res,'res')

边界矩阵

img = cv2.imread('pipi.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt = contours[2]
x,y,w,h = cv2.boundingRect(cnt)
img = cv2.rectangle(img,(x,y),(x+w, y+h),(0,255,0),2)
cv_show(img,'img')

area = cv2.contourArea(cnt)
x, y, w, h = cv2.boundingRect(cnt)
rect_area = w * h
extent = float(area) / rect_area
print('轮廓面积与边界矩形比',extent)

模板匹配

#原理类似于卷积
img = cv2.imread('eagle.jpg',0)
template = cv2.imread('eagle_head.png',0)
h,w = template.shape[:2]

#模板匹配方法
methods = ['cv2.TM_CCOEFF', 'cv2.TM_CCOEFF_NORMED','cv2.TM_CCORR',
           'cv2.TM_CCORR_NORMED', 'cv2.TM_SQDIFF', 'cv2.TM_SQDIFF_NORMED']
res = cv2.matchTemplate(img, template, cv2.TM_SQDIFF)

for meth in methods:
    img2 = img.copy()
    
    #匹配方法的真值
    method = eval(meth)
    print(method)
    res = cv2.matchTemplate(img, template, method)
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
    
    #如果是平方差匹配TM_SQDIFF或归一化平方差匹配TM_SQDIFF_NORMED，取最小值
    if method in [cv2.TM_SQDIFF, cv2.TM_SQDIFF_NORMED]:
        top_left = min_loc
    else:
        top_left = max_loc
    bottom_right = (top_left[0] + w, top_left[1] + h)
    #画矩形
    cv2.rectangle(img2, top_left, bottom_right, 255, 2)
    
    plt.subplot(121), plt.imshow(res, cmap = 'gray')
    plt.xticks([]), plt.yticks([])   #隐藏坐标轴
    plt.subplot(122), plt.imshow(img2, cmap = 'gray')
    plt.xticks([]), plt.yticks([])
    plt.suptitle(meth)
    plt.show()

匹配多个对象

#匹配多个对象
img_rgb = cv2.imread('circle.jpg')
img_gray = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)
template = cv2.imread('circle_1.png',0)
h, w = template.shape[:2]

res = cv2.matchTemplate(img_gray, template, cv2.TM_CCOEFF_NORMED)
threshold = 0.8   
#取匹配程度大于80%的坐标
loc = np.where(res >= threshold)
for pt in zip(*loc[::-1]):     # *表示可选参数
    bottom_right = (pt[0] + w, pt[1] + h)
    cv2.rectangle(img_rgb, pt, bottom_right, (0, 0, 255), 2)

cv2.imshow('img_rgb', img_rgb)
cv2.waitKey(0)

img = cv2.imread('eagle.jpg', 0)
hist = cv2.calcHist([img],[0],None,[256],[0,256])
hist.shape

plt.hist(img.ravel(),256);
plt.show()

img = cv2.imread('eagle.jpg')
color = ('b','g','r')
for i, col in enumerate(color):
    histr = cv2.calcHist([img],[i],None, [256],[0,256])
    plt.plot(histr,color = col)
    plt.xlim([0,256])

mask操作

#创建mask
mask = np.zeros(img.shape[:2], np.uint8)
mask[100:300, 100:400] = 255
cv_show(mask, 'mask')

img = cv2.imread('eagle.jpg', 0)
cv_show(img, 'img')

masked_img = cv2.bitwise_and(img, img, mask = mask)   #与操作
cv_show(masked_img, 'masked_img')

hist_full = cv2.calcHist([img],[0],None,[256],[0,256])
hist_mask = cv2.calcHist([img],[0],mask,[256],[0,256])

plt.subplot(221), plt.imshow(img,'gray')
plt.subplot(222), plt.imshow(mask,'gray')
plt.subplot(223), plt.imshow(masked_img, 'gray')
plt.subplot(224), plt.plot(hist_full), plt.plot(hist_mask)
plt.xlim([0,256])
plt.show()

直方图均衡化

clahe = cv2.createCLAHE(clipLimit = 2.0, tileGridSize = (8,8))
res_clahe = clahe.apply(img)
res = np.hstack((img, equ, res_clahe))
cv_show(res, 'res')

傅里叶变换

open-cv中的cv2.dft()以及cv2.idft(),输入图像需要先转换成np.float32格式

img = cv2.imread('eagle.jpg',0)
img_float32 = np.float32(img)
dft = cv2.dft(img_float32, flags = cv2.DFT_COMPLEX_OUTPUT)
dft_shift = np.fft.fftshift(dft)
# 得到灰度图能表示的形式
magnitude_spectrum = 20 * np.log(cv2.magnitude(dft_shift[:,:,0],dft_shift[:,:,1]))
plt.subplot(121), plt.imshow(img, cmap = 'gray')
plt.title('Input Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122), plt.imshow(magnitude_spectrum, cmap = 'gray')
plt.title('Magnitude Spectrum'), plt.xticks([]), plt.yticks([])
plt.show()    # 亮点是低频点，高频点呈发散型

#低通滤波器
img = cv2.imread('eagle.jpg',0)
img_float32 = np.float32(img)
dft = cv2.dft(img_float32, flags = cv2.DFT_COMPLEX_OUTPUT)
dft_shift = np.fft.fftshift(dft)
rows, cols = img.shape
crow, ccol = int(rows/2), int(cols/2)   #找中心位置

#低通滤波
mask = np.zeros((rows, cols, 2), np.uint8)
mask[crow - 30 : crow + 30, ccol - 30 : ccol + 30] = 1

#IDFT
fshift = dft_shift * mask
f_ishift = np.fft.ifftshift(fshift)
img_back = cv2.idft(f_ishift)
img_back = cv2.magnitude(img_back[:,:,0],img_back[:,:,1])

plt.subplot(121), plt.imshow(img, cmap = 'gray')
plt.title('Input Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122), plt.imshow(img_back, cmap = 'gray')
plt.title('Result'), plt.xticks([]), plt.yticks([])
plt.show()

#高通滤波器
img = cv2.imread('eagle.jpg',0)
img_float32 = np.float32(img)
dft = cv2.dft(img_float32, flags = cv2.DFT_COMPLEX_OUTPUT)
dft_shift = np.fft.fftshift(dft)

rows, cols = img.shape
crow, ccol = int(rows/2), int(cols/2)   #取中心位置，用以复原

#高通滤波
mask = np.ones((rows, cols, 2), np.uint8)
mask[crow-30:crow+30, ccol-30:ccol+30] = 0

#IDFT
fshift = dft_shift * mask
f_ishift = np.fft.ifftshift(fshift)
img_back = cv2.idft(f_ishift)
img_back = cv2.magnitude(img_back[:,:,0], img_back[:,:,1])

plt.subplot(121), plt.imshow(img, cmap = 'gray')
plt.title('Input Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122), plt.imshow(img_back, cmap = 'gray')
plt.title('Result'), plt.xticks([]), plt.yticks([])
plt.show()

图像特征-Harris角点检测

图像类型：float32
blockSize: 角点检测中指定区域的大小
ksize: Sobel求导中使用的窗口大小
k: 取值参数为[0，4，0.06]

img = cv2.imread('chess.jpg')
print('img.shape',img.shape)

#将gray图像的numpy格式转换为float32格式
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#gray = np.float32(gray)
print(gray.shape)
print(type(gray))

dst = cv2.cornerHarris(gray, 2, 3, 0.04)
print('dst.shape:',dst.shape)

img[dst > 0.01 * dst.max()] = [0, 0, 255]
cv2.imshow('dst',img)
cv2.waitKey(0)
cv2.destroyAllWindows()

Scale Invariant Feature Transform (SIFT) 图像尺度空间

# SIFT适用于cv2  3.4.1版本以下
cv2.__version__

img = cv2.imread('eagle.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# SIFT尺度变换理论，利用高斯模糊等理论。
sift = cv2.xfeatures2d.SIFT_create()
# kp表示关键特征点的提取
kp = sift.detect(gray, None)

img = cv2.drawKeypoints(gray, kp, img)
cv2.imshow('drawKeypoints', img)
cv2.waitKey(0)
cv2.destroyAllWindows()

# 计算特征点
kp, des = sift.compute(gray, kp)
print(np.array(kp).shape)

特征匹配 Brute- Force蛮力匹配

# 尺度处理，提取特征点
sift = cv2.xfeatures2d.SIFT_create()

# 计算两副图像中的特征点
kp1, des1 = sift.detectAndCompute(img1, None)
kp2, des2 = sift.detectAndCompute(img2,None)

# CrossCheck 表示两个特征点要互相匹配的话，如：A图中的第i个特征点与B图中的第j个特征点最近，且B对A亦然
#NORM_L2: 归一化数组的欧几里得距离
bf = cv2.BFMatcher(crossCheck = True)

#进一步做1对1的匹配
matches = bf.match(des1,des2)
matches = sorted(matches, key = lambda x : x.distance)

img3 = cv2.drawMatches(img1, kp1, img2, kp2, matches[:10], None, flags = 2)
cv_show('img3', img3)

#K对最佳匹配
bf = cv2.BFMatcher()
matches = bf.knnMatch(des1, des2, k=2)

good = []
for m, n in matches:
    if m.distance < 0.75 * m.distance:
        good.append([m])

img3 = cv2.drawMatchesKnn(img1, kp1, img2, kp2, good, None, flags = 2)
cv_show('img3', img3)

背景建模

帧差法、混合高斯模型、光流估计、Lucas-Kanade算法

标签：gray,plt,img,show,res,cv2,基础知识,图像处理,视觉
来源： https://blog.csdn.net/weixin_46236212/article/details/122074237

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。

ICode9