First Step to Open CV (Open Computer Vision Library) Part 1

Introduction 

Hello , I am going to setup the Open CV on windows OS. Open CV is in under open-source BSD license. Originally developed by Intel and this is supports the deep learning frameworks like TensorFlow.

OpenCV's application areas include:

• 2D and 3D feature toolkits
• Egomotion estimation
• Facial recognition system
• Gesture recognition
• Human–computer interaction (HCI)
• Mobile robotics
• Motion understanding
• Object identification
• Segmentation and recognition
• Stereopsis stereo vision: depth perception from 2 cameras
• Structure from motion (SFM)
• Motion tracking
• Augmented reality

It is written by mainly C++ interface and supported C++,python,java even android package,Matlab,C# for development. Therefore this tutorial I am going to use python language.

Installations

• If you haven't already installed python get it here (My version is 2.7) and install it.
• Then Download and install OpenCV here (My version is Open CV 2) 

Configure system variable  
 

• Open python installed folder and copy the path (for ex C:\Python27)
• Then Run-> type systempropertiesadvanced
• open Environment variable -> User variable .....->path->paste the python installed path and Scripts path.(you can see it below)

 

Numpy install

"numpy" is a scientific and mathematical package and which is required to run opencv package.

• open the CMD then type pip install numpy  (Make sure you have connected to the internet)

(I have already installed )



Make the link between python and opencv package

• Go to this path opencv\build\python\2.7\x64 then copy cv2.pyd file
• paste cv2.pyd into the Python27\Lib\site-packages folder

Test

•  Open the python IDE and type import numpy and import cv2 to verify whether packages work or not. if any error is not displayed,  you are done.

First Program - Face and Eye Detection

Then I load my pyscript IDE , you can simply use python default IDE or any python IDE. I will explain this code segment in next part broadly.

import numpy as np
import cv2 as cv
face_cascade = cv.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_cascade = cv.CascadeClassifier('haarcascade_eye.xml')
img = cv.imread('praneeth.png')
gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)

faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
    cv.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
    roi_gray = gray[y:y+h, x:x+w]
    roi_color = img[y:y+h, x:x+w]
    eyes = eye_cascade.detectMultiScale(roi_gray)
    for (ex,ey,ew,eh) in eyes:
        cv.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),2)
cv.imshow('img',img)
cv.waitKey(0)
cv.destroyAllWindows()

output

References

• https://opencv.org

• https://en.wikipedia.org/wiki/OpenCV

• https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRyp5yAZXk4rDv5DELPPv3ZqhEAUMJJIFw1m-sKd0cpwDfDQS_J

• https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRhLXSKHikcgnn1rhnVzw194t2Os8TUd6139jkFTn9v3NeZuAVY