最近兩周由于忙于個人項目，一直未發言了，實在是太荒涼了。。。。，上周由于項目，見到Python的應用極為廣泛，用起來也特別順手，于是小編也開始著手學習Python,…下面我就匯報下今天的學習成果吧

小編運行環境unbuntu 14.0.4

首先我們先安裝一下Python唄，我用的2.7，其實特別簡單，一行指令就ＯＫ

sudo apt-get install python-dev

一般安裝系統的時候其實python已經自帶了，這步基本可以不用做，ＯＫ，我們繼續往下走吧，安裝python-opencv ,稍后我們需要用到opencv的庫，一行指令即可，這也是小編特別喜歡linux的原因：

sudo apt-get install python-opencv

完成之后我們開始操作吧，首先同樣的我們打開攝像頭露個臉唄，不多說，上代碼， vim pythonpractice.py 打開vim，copy以下代碼即可（友情提示　python是有嚴格的縮進的，下面我都是四個空格縮進，各位不要復制錯了）:lo

lmport cv2import numpy as np#添加模塊和矩陣模塊cap=cv2.VideoCapture(0)＃打開攝像頭，若打開本地視頻，同opencv一樣，只需將０換成("×××.avi")while(1): # get a frame  ret, frame = cap.read() # show a frame  cv2.imshow("capture", frame)  if cv2.waitKey(1) & 0xFF == ord('q'):    breakcap.release()cv2.destroyAllWindows()#釋放并銷毀窗口

保存退出

python pythonpractice.py

小臉蛋即可出現在你的屏幕上了，下面稍微添加幾行有意思的代碼吧，實現藍色背景檢測，我這有瓶藍色脈動，正好做個小實驗。

import cv2import numpy as npcap = cv2.VideoCapture(0)# set blue threshlower_blue=np.array([78,43,46])upper_blue=np.array([110,255,255])while(1): # get a frame and show  ret, frame = cap.read()  cv2.imshow('Capture', frame) # change to hsv model  hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV) # get mask  mask = cv2.inRange(hsv, lower_blue, upper_blue)  cv2.imshow('Mask', mask) # detect blue  res = cv2.bitwise_and(frame, frame, mask=mask)  cv2.imshow('Result', res)  if cv2.waitKey(1) & 0xFF == ord('q'):    breakcap.release()cv2.destroyAllWindows()

同樣python pythonpractice.py 運行一下，可以把手機換成藍色背景檢測以下，下面時間就交給各位理解了，代碼很簡單，只有簡單的幾行程序。

下面有個復雜點顏色識別的代碼

#!/usr/bin/python# -*- coding: utf-8 -*-import cv2import numpy as npimport timereadlower=np.array([156,179,144])readupper=np.array([180,255,255])readlower1 = np.array([0, 128, 146])readupper2 = np.array([5, 255, 255])lowerarry=[[readlower,readupper,'red'],[readlower1,readupper2,'red1']]capture=cv2.VideoCapture('4.mp4')while True: ret,frame=capture.read() print frame.shape frame=cv2.resize(frame,(640,480)) if ret==False:  print("video is erro") #cv2.imshow('xiaorun',frame) hsv=cv2.cvtColor(frame,cv2.COLOR_BGR2HSV) for colormin,colermax,name in lowerarry:  mask=cv2.inRange(hsv,colormin,colermax)  #res = cv2.bitwise_and(frame, frame, mask=mask) #mask=cv2.erode(mask,None,iterations=1) mask=cv2.dilate(mask,None,iterations=25) ret, binary = cv2.threshold(mask,15, 255, cv2.THRESH_BINARY) cv2.imshow('result',binary) kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (21, 7)) closed = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel) cv2.imshow('closed', closed) #erode = cv2.erode(closed, None, iterations=4) #cv2.imshow('erode', erode) dilate = cv2.dilate(closed, None, iterations=50) cv2.imshow('dilate', dilate) _,contours, hierarchy = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) #res=_.copy() for con in contours:  x, y, w, h = cv2.boundingRect(con) # 將輪廓分解為識別對象的左上角坐標和寬、高  # 在圖像上畫上矩形（圖片、左上角坐標、右下角坐標、顏色、線條寬度）  cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0,0), 3) cv2.imshow('res',frame) key=cv2.waitKey(1) if key==ord('q'):  break