Bootstrap

OpenCV-Python入门 下

鼠标操作与响应

  • 鼠标Callback函数
    在这里插入图片描述
    在这里插入图片描述

  • 应用:使用鼠标进行矩形绘制
    在这里插入图片描述

b1 = cv.imread(r"..\dataset\Image\The_Witcher_Lover.jpg")
img = np.copy(b1)
x1 = -1
x2 = -1
y1 = -1
y2 = -1

def mouse_drawing(event, x, y, falgs, param):
    global x1, y1, x2, y2
    if event == cv.EVENT_LBUTTONDOWN:
        x1 = x
        y1 = y
    if event == cv.EVENT_MOUSEMOVE:
        if x1 < 0 or y1 < 0:
            return
        x2 = x
        y2 = y
        dx = x2 - x1
        dy = y2 - y1
        if dx > 0 and dy > 0:
            b1[:,:,:] = img[:,:,:]
            cv.rectangle(b1, (x1, y1), (x2, y2), (0, 0, 255), 2, 8, 0)
    if event == cv.EVENT_LBUTTONUP:
        x2 = x
        y2 = y
        dx = x2 - x1
        dy = y2 - y1
        if dx > 0 and dy > 0:
            b1[:,:,:] = img[:,:,:]
            cv.rectangle(b1, (x1, y1), (x2, y2), (0, 0, 255), 2, 8, 0)
        x1 = -1
        x2 = -1
        y1 = -1
        y2 = -1

def mouse_demo():
    cv.namedWindow("mouse_demo", cv.WINDOW_AUTOSIZE)
    cv.setMouseCallback("mouse_demo", mouse_drawing)
    while True:
        cv.imshow("mouse_demo", b1)
        c = cv.waitKey(10)
        if c == 27:
            break
    cv.destroyAllWindows()

图像像素类型转换与归一化

  • 归一化方法支持
    在这里插入图片描述
  • 归一化函数

cv.normalize(src, dst[, alpha[, beta[, norm_type[, dtype[, mask]]]]] ) -> dst
src表示输入图像, dst表示输出图像,alpha, beta 默认是1, 0,是归一化的区间值
norm_type默认是NORM_L2,norm_type常用是NORM_MINMAX

  • 注意:在这里插入图片描述
def norm_demo():
    image_uint8 = cv.imread(r"..\dataset\Image\The_Witcher_Lover.jpg")
    cv.imshow("input", image_uint8)
    img_f32 = np.float32(image_uint8)
    cv.imshow("imgf32", img_f32)
    cv.normalize(img_f32, img_f32, 1, 0, cv.NORM_MINMAX)
    cv.imshow("norm_imgf32", img_f32)
    cv.waitKey(0)
    cv.destroyAllWindows()

图像几何变换

在这里插入图片描述

  • 平移变换
    在这里插入图片描述
  • 放缩变换在这里插入图片描述
  • 旋转变换
    在这里插入图片描述
  • 旋转矩阵获取函数

cv.getRotationMatrix2D
Center表示旋转中心, angle表示度数,大于零表示逆时针旋转, scale表示放缩尺度大小

  • 几个旋转操作函数

cv.flip(src, flipCode[, dst] ) ->dst
cv.rotate(src, rotateCode[, dst] ) -> dst
src表示输入图像
flipCode支持0水平、1垂直,-1对角线翻转,rotateCode支持旋转90°,180°,270°

def affine_demo():
    image = cv.imread(r"..\dataset\Image\The_Witcher_Lover.jpg")
    h, w, c = image.shape
    cx = int(w / 2)
    cy = int(h / 2)
    cv.imshow("image", image)

    M = np.zeros((2, 3), dtype=np.float32)
    M[0, 0] = 3
    M[1, 1] = 3
    M[0, 2] = 0
    M[1, 2] = 0
    dst = cv.warpAffine(image, M, (int(w*3), int(h*3)))
    cv.imshow("rescale-demo", dst)

    M = cv.getRotationMatrix2D((w/2, h/2), 45.0, 1.0)
    dst = cv.warpAffine(image, M, (w, h))
    cv.imshow("rotate-demo", dst)

    dst = cv.flip(image, 0)
    cv.imshow("flip-demo", dst)

    cv.waitKey(0)
    cv.destroyAllWindows()

视频读写处理

  • 视频标准与格式

SD(Standard Definition)标清480P
HD(High Definition)高清720P/1080P
UHD(Ultra High Definition)超高清4K/2160P
分辨率表示
SD-640x480, 704x480, 720x480, 848x480等
HD-960x720,1280x720,1440x1080,1920x1080
UHD-4K,2160P

  • 视频读取函数
    在这里插入图片描述
  • 视频文件保存

cv.VideoWriter( filename, fource, fps, framesize[, isColor]-> <videoWriter object>
filename保存文件名称,fourcc编码方式,fps帧率,frameSize 视频帧大小,与实现大小相符

  • 查询视频属性
    在这里插入图片描述
def video_demo():
    cap = cv.VideoCapture("vtest.avi")
    # query video file metadata
    fps = cap.get(cv.CAP_PROP_FPS)
    frame_w = cap.get(cv.CAP_PROP_FRAME_WIDTH)
    frame_h = cap.get(cv.CAP_PROP_FRAME_HEIGHT)
    print(fps, frame_w, frame_h)
    # encode mode
    fourcc = cap.get(cv.CAP_PROP_FOURCC)
    # create video writer
    writer = cv.VideoWriter("output.mp4", int(fourcc), fps, (int(frame_w), int(frame_h)))
    # loop read frame until last frame
    while True:
        ret, frame = cap.read()
        if ret is not True:
            break
        cv.imshow("frame", frame)
        c = cv.witKey(1)
        if c == 27:
            break
        writer.write(frame)

图像直方图

  • 图像直方图函数

hist = cv.calcHist([image], [i], None, [32], [0, 256])
image输入图像,i表示通道索引,mask=None,histSize表示bin的个数,表示通道的取值范围0~256

def image_hist():
    image = cv.imread(r"..\dataset\Image\The_Witcher_Lover.jpg")
    cv.imshow("input", image)
    color = ('blue', 'green', 'red')
    for i, color in enumerate(color):
        hist = cv.calcHist([image], [i], None, [32], [0, 256])
        print(hist)
        plt.plot(hist, color=color)
        plt.xlim([0, 32])
    plt.show()
    cv.waitKey(0)
    cv.destroyAllWindows()

图像直方图均衡化

  • 直方图均衡化原理
    在这里插入图片描述

  • 直方图均衡化函数

cv.equalizeHist(src[, dst]) -> dst
src必须是八位单通道图像,dst返回结果图像,类型与src保持一致

def eq_demo():
    image = cv.imread(r"..\dataset\Image\The_Witcher_Lover.jpg", cv.IMREAD_GRAYSCALE)
    cv.imshow("input", image)
    hist = cv.calcHist([image], [0], None, [32], [0, 256])
    print(hist.dtype)
    plt.plot(hist, color="gray")
    plt.xlim([0, 32])
    plt.show()
    cv.waitKey(0)

    eqimg = cv.equalizeHist(image)
    hist = cv.calcHist([eqimg], [0], None, [32], [0, 256])
    print(hist.dtype)
    plt.plot(hist, color="gray")
    plt.xlim([0, 32])
    plt.show()
    cv.waitKey(0)
    cv.destroyAllWindows()

图像卷积操作

  • 图像卷积的定义
    在这里插入图片描述
  • 卷积的边缘填充

边缘处理,边缘填充的方式
cv.BORDER_DEFAULT gfedcb|abcdefgh|gfedcba
cv.BORDER_WRAP cdefgh|abcdefgh|abcdefg
cv.BORDER_CONSTANT iiiiii|abcdefgh|iiiiiii

  • 卷积模糊函数

v.blur( src, ksize[, dst[, anchor[, borderType]]]) -> dst
src表示输入图像 CV_8U, CV_32F or CV_64F
Ksize卷积核大小
Anchor锚定位置
borderType边缘处理方式

def conv_demo():
    image = cv.imread("lena.png")
    dst = np.copy(image)
    cv.imshow("input", image)
    h, w, c = image.shape
    for row in range(1, h-1, 1):
        for col in range(1, w-1, 1):
            m = cv.mean(image[row-2 : row+2, col-2:col+2])
            dst[row, col] = (int(m[0]), int(m[1]), int(m[2]))
    cv.imshow("conv-demo", dst)

    blured = cv.blur(image, (5, 5), anchor=(-1, -1))
    cv.imshow("blur-demo", blured)

    cv.waitKey(0)
    cv.destroyAllWindows()

高斯模糊

  • 高斯模糊函数

cv.GaussianBlur(src, ksize, sigmaX[, dst[, sigmaY[, borderType]]]) ->dst
ksize必须是正数而且是奇数
sigmaX高斯核函数X方向标准方差,sigmaY高斯核函数Y方向标准方差,默认0,表示跟sigmaX相同,
ksize为0表示从sigmaX计算生成ksize,ksize大于0表示从ksize计算生成sigmaX

  • 均值模糊与高斯模糊
    均值模糊 – 卷积核权重系数相同
    高斯模糊 – 卷积核根据高斯函数生成,权重系数不同
def conv_demo():
    image = cv.imread("lena.png")
    cv.imshow("input", image)

    g1 = cv.GaussianBlur(image, (0, 0), 15)
    g2 = cv.GaussianBlur(image, (15, 15), 15)
    cv.imshow("GaussianBlur-demo1", g1)
    cv.imshow("GaussianBlur-demo2", g2)

    cv.waitKey(0)
    cv.destroyAllWindows()

像素重映射

  • 像素重映射
    把像素点P(x,y)重新映射到一个新的位置P’(x’, y’)
  • 像素重映射函数

cv.remap(src, map1, map2, interpolation[, dst[, borderMode[, borderValue]]] ) -> dst
src表示图像
map1表示x,y方向映射规则,或者x方向映射
map2如果map1表示x,y映射时为空,否则表示y
表示映射时候的像素插值方法,支持:INTER_NEAREST 、NTER_LINEAR 、NTER_CUBIC

def remap_demo():
    image = cv.imread("lena.png")
    cv.namedWindow("remap-demo", cv.WINDOW_AUTOSIZE)
    cv.createTrackbar("remap-type", "remap-demo", 0, 3, trackbar_callback)
    h, w, c = image.shape
    cv.imshow("input", image)
    map_x = np.zeros((h, w), dtype=np.float32)
    map_y = np.zeros((h, w), dtype=np.float32)
    while True:
        pos = cv.getTrackbarPos("remap-type", "remap-demo")
        #倒立
        if pos == 0:
            for i in range(map_x.shape[0]):
                map_x[i, :] = [x for x in range(map_x.shape[1])]
            for j in range(map_x.shape[1]):
                map_y[:, j] = [map_y.shape[0] - y for y in range(map_y.shape[0])]
        #镜像
        elif pos == 1:
            for i in range(map_x.shape[0]):
                map_x[i, :] = [map_x.shape[1] - x for x in range(map_x.shape[1])]
            for j in range(map_x.shape[1]):
                map_y[:, j] = [y for y in range(map_y.shape[0])]
        #对角线对称
        elif pos == 2:
            for i in range(map_x.shape[0]):
                map_x[i, :] = [map_x.shape[1] - x for x in range(map_x.shape[1])]
            for j in range(map_x.shape[1]):
                map_y[:, j] = [map_y.shape[0] - y for y in range(map_y.shape[0])]
        #放大两倍
        elif pos == 3:
            for i in range(map_x.shape[0]):
                map_x[i, :] = [int(x/2) for x in range(map_x.shape[1])]
            for j in range(map_x.shape[1]):
                map_y[:, j] = [int(y/2) for y in range(map_y.shape[0])]

        dst = cv.remap(image, map_x, map_y, cv.INTER_LINEAR)
        cv.imshow("remap-demo", dst)
        c = cv.waitKey(100)
        if c == 27:
            break
    cv.waitKey(0)
    cv.destroyAllWindows()

图像二值化

  • 图像二值化的定义
    图像二值化就是将图像上的像素点的灰度值设置为0或255,也就是将整个图像呈现出明显的黑白效果的过程。图像的二值化使图像中数据量大为减少,从而能凸显出目标的轮廓,是一种简单的图像分割方法。
    进行二值化有多种方式,其中最常用的就是采用阈值法(Thresholding)进行二值化。阈值法又分为全局阈值(Global Method)和局部阈值(Local Method),又称自适应阈值(Adaptive Thresholding)。
    在这里插入图片描述
  • 二值化函数

cv.threshold( src, thresh, maxval, type[, dst]) -> retval, dst
src表示输入图像,thresh表示阈值,maxval表示最大值
type表示二值化THRESH_BINARY或者二值化反THRESH_BINARY_INV
retval表示返回阈值,dst返回的二值图像

def binary_demo():
    #灰度图像
    image = cv.imread(r"..\dataset\Image\The_Witcher_Lover.jpg")
    gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
    cv.imshow("gray", gray)

    #手动阈值,二值化
    ret1, binary1 = cv.threshold(gray, 127, 255, cv.THRESH_BINARY)
    cv.imshow("binary1", binary1)

    #求均值,二值化
    m = cv.mean(gray)[0]
    ret2, binary2 = cv.threshold(gray, m, 255, cv.THRESH_BINARY)
    cv.imshow("binary2", binary2)

    cv.waitKey(0)
    cv.destroyAllWindows()

全局与自适应二值化

  • 全局二值化

OTSU法/大津法
在这里插入图片描述

三角法
图像处理之三角法图像二值化

cv.threshold( src, thresh, maxval, type[, dst])->retval, dst
type表示二值化
THRESH_BINARY | THRESH_OTSU
THRESH_BINARY | THRESH_TRIANGLE
THRESH_BINARY_INV | THRESH_OTSU
表示不同的全局二值化方法

  • 自适应二值化

cv.adaptiveThreshold(src, maxValue, adaptiveMethod, thresholdType, blockSize, C[, dst] ) -> dst
cv.ADAPTIVE_THRESH_MEAN_C
cv.ADAPTIVE_THRESH_GAUSSIAN_C
blockSize必须为奇数
C表示要减去的权重,可以是正数,负数,0

def binary_demo():
    #灰度图像
    image = cv.imread(r"..\dataset\Image\The_Witcher_Lover.jpg")
    gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
    cv.imshow("gray", gray)

    #大津法,
    ret1, binary1 = cv.threshold(gray, 0, 255, cv.THRESH_BINARY | cv.THRESH_OTSU)
    cv.imshow("otsu", binary1)

    #三角法
    ret2, binary2 = cv.threshold(gray, 0, 255, cv.THRESH_BINARY | cv.THRESH_TRIANGLE)
    cv.imshow("triangle", binary2)

    # 自适应法
    binary3 = cv.adaptiveThreshold(gray, 255, cv.ADAPTIVE_THRESH_GAUSSIAN_C, cv.THRESH_BINARY_INV, 25, 10)
    cv.imshow("adaptive", binary3)

    cv.waitKey(0)
    cv.destroyAllWindows()

实时人脸检测

  • OpenCV3.3之前基于HAAR/LBP级联检测
    OpenCV3.3开始支持深度学习人脸检测
    支持人脸检测模型caffe/tensorflow
    OpenCV4.5.4 支持人脸检测+landmark
    模型下载地址:https://gitee.com/opencv_ai/opencv_tutorial_data
  • 相关函数
    读取模型:readNetFromTensorflow
    转换为blob对象:blobFromImage
    设置输入:setInput
    推理预测:forward
;