【千律】OpenCV基础：灰度图反向投影

灰度图反向投影

1.计算感兴趣区域的灰度直方图 hist

2.将直方图的像素点个数缩放到 0-255

3.对于目标图像各位置的灰度值为w(i,j)，其反向投影图的灰度值为hist(w(i,j))

4.计算目标图像的反向投影图

注：反向投影图与感兴趣区域的形状无关，只与其颜色分布有关

import cv2 as cv
import numpy as np
import matplotlib.pyplot as plt


# 封装图片显示函数
def image_show(image):
    if image.ndim == 2:
        plt.imshow(image, cmap='gray')
    else:
        image = cv.cvtColor(image, cv.COLOR_BGR2RGB)
        plt.imshow(image)
    plt.show()



if __name__ == '__main__':

    # 读取灰度图
    img_lenna = cv.imread('lenna.png', 0)

    # 截取感兴趣区域
    img_part = img_lenna[200: 300, 200: 300]

    # 计算感兴趣区域的直方图
    img_hist = cv.calcHist([img_part], [0], None, [256], [0, 256])

    # 直方图放缩
    img_hist = cv.normalize(img_hist, None, 0, 255, cv.NORM_MINMAX)

    # 反向投影结果
    img_back = cv.calcBackProject([img_lenna], [0], img_hist, [0, 255], 1)

    # 显示结果
    image_show(img_back)

import cv2 as cv
import numpy as np
import matplotlib.pyplot as plt


# 封装图片显示函数
def image_show(image):
    if image.ndim == 2:
        plt.imshow(image, cmap='gray')
    else:
        image = cv.cvtColor(image, cv.COLOR_BGR2RGB)
        plt.imshow(image)
    plt.show()



if __name__ == '__main__':

    # 读取灰度图
    img_lenna = cv.imread('lenna.png', 0)

    # 截取感兴趣区域
    img_part = img_lenna[200: 300, 200: 300]

    # 计算感兴趣区域的直方图
    img_hist = cv.calcHist([img_part], [0], None, [256], [0, 256])

    # 直方图放缩
    img_hist = cv.normalize(img_hist, None, 0, 255, cv.NORM_MINMAX)

    # 反向投影结果
    img_back = img_hist[img_lenna].astype(np.uint8)

    # 显示结果
    image_show(img_back)