import cv2import numpy as npimg = cv2.imread("../chapter3/qipan.png")gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)edges = cv2.Canny(gray, 50, 120)min_line_lenghth = 200max_line_gap = 30lines = cv2.Houg

import cv2import numpy as npimg = cv2.imread("../chapter3/hammer.jpg", cv2.IMREAD_UNCHANGED)ret, thresh = cv2.threshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY), 127, 255, cv2.THRESH_BINARY)contou

Haar特征+Adaboost级联分类器以 Haar特征分类器为基础的对象检测技术是一种非常有效的对象检测技术，多用于人脸检测、行人检测等。Haar-like特征是计算机视觉领域一种常用的特征描述算子，也称为Haar特征。Haar特征就是用下图中黑色矩形所有像素值的和减去白色矩形所有像素值的和。Haar特征可以在检测窗口中由放大+平移产生一系列子特征。在论文《Rapid Object Detect

imutils.py封装读取和显示图片方法import cv2import matplotlib.pyplot as pltimport numpy as npdef show(image):plt.imshow(image)plt.axis('off')plt.show()def imread(image):image = cv2.imread(image)image = cv2.cvtColo

图像加法将原图像所有像素值+100， 若超过255则赋为255原图image = imread('test.jpg')# 生成跟图片形状相同的并且全为100的数据M = np.ones(image.shape, dtype='uint8')*100# 所有的像素加100image = cv2.add(image, M)show(image)像素值-100后图像整体发白图像减法将原图像所有像素值-1

视频分解import cv2cap = cv2.VideoCapture("E:/code/conputer_visual/data/1.mp4") #获取一个视频句柄isOpened = cap.isOpened()#判断当前句柄是否可以打开fps = cap.get(cv2.CAP_PROP_FPS)#获取帧率width = int(cap.get(cv2.CAP_PROP_FRAME_WID

#油画特效# 1 gray 2 分割成x*x的小方块 3 0-255划分成几个等级， 将2步结果映射到这个等级上import cv2import numpy as npimg = cv2.imread("E:/code/conputer_visual/data/0.jpg", 1)imginfo = img.shapeheight = imginfo[0]width = imginfo[1]cv2

#浮雕效果# newp = gray0 - gray1 + 150import cv2import numpy as npimport randomimport mathimg = cv2.imread("E:/code/conputer_visual/data/0.jpg", 1)imginfo = img.shapeheight = imginfo[0]width = imginfo[1]cv

import cv2img = cv2.imread("E:/code/conputer_visual/data/0.jpg", 1)img_info = img.shapedst = img[100:200, 100: 200]cv2.imshow("img_window", dst)cv2.waitKey()剪切出原题的宽度从100到200像素，高度从100到200像素

jpg格式的有损压缩（牺牲图片质量）img = cv2.imread("E:/code/conputer_visual/data/0.jpg", 1)#param2为压缩参数，50代表压缩比例，该值范围在0-100，越小代表压缩力度越大cv2.imwrite("E:/code/conputer_visual/data/2.jpg", img, [cv2.IMWRITE_JPEG_QUALITY,