My Project 1:

 Freedom Fighter Recognition System using OpenCV:

This project uses the concept of template matching (in OpenCV) and object detection. 

The project takes a source image and a template/patch. Here the source image is a collage of freedom fighters and a template (eg Bhagat Singh). It compares both source and the template by finding the matching probability and encircles the portion in the source image with maximum matching probability.

Source Image:




Template:


Final Output:


Code:

import cv2

import numpy as np

FreedomFighters=cv2.imread("freedomfighters.jpg",cv2.IMREAD_UNCHANGED)

cv2.imshow("Image",FreedomFighters)

cv2.waitKey()

cv2.destroyAllWindows()

BhagatSingh=cv2.imread("bhagatSinghpic.jpg",cv2.IMREAD_UNCHANGED)

cv2.imshow("Image",BhagatSingh)

cv2.waitKey()

cv2.destroyAllWindows()

result=cv2.matchTemplate(FreedomFighters,BhagatSingh,cv2.TM_CCOEFF_NORMED)

min_val,max_val,min_loc,max_loc=cv2.minMaxLoc(result)

h=BhagatSingh.shape[0]

w=BhagatSingh.shape[1]

cv2.rectangle(FreedomFighters,max_loc,(max_loc[0]+w,max_loc[1]+h),(0,0,255),2)

o/p above line:

array([[[100, 109, 113],
        [100, 109, 113],
        [100, 109, 113],
        ...,
        [  0,   0, 255],
        [  0,   0, 255],
        [  0,   0, 255]],

       [[100, 109, 113],
        [100, 109, 113],
        [100, 109, 113],
        ...,
        [  0,   0, 255],
        [  0,   0, 255],
        [  0,   0, 255]],

       [[100, 109, 113],
        [100, 109, 113],
        [100, 109, 113],
        ...,
        [  0,   0, 255],
        [  0,   0, 255],
        [  0,   0, 255]],

       ...,

       [[ 96, 100, 101],
        [103, 107, 108],
        [115, 119, 120],
        ...,
        [197, 186, 194],
        [202, 191, 201],
        [204, 193, 203]],

       [[ 95,  98, 102],
        [100, 105, 106],
        [112, 116, 117],
        ...,
        [200, 187, 195],
        [210, 194, 205],
        [209, 193, 204]],

       [[ 94,  98, 103],
        [100, 107, 110],
        [108, 113, 116],
        ...,
        [200, 189, 199],
        [201, 187, 199],
        [199, 182, 195]]], dtype=uint8)

code contd

cv2.imshow("Image",FreedomFighters)
cv2.waitKey()
cv2.destroyAllWindows()




Comments

Post a Comment

Popular posts from this blog

Reaction Tester

About Reaction Tester: The user has to click the squares as fast as he/she can. The square can appear in random sizes, directions, and colors.  This project calculates the reaction time of a person in seconds by storing the start time when the square appeared on the screen and also the end time when the user clicks the square. Finally, the user's reaction time is given as an output. Deployed  Reaction Tester  Link:   Click Here Source Code- HTML: <head>     <title> Reaction Tester </title>     <link rel = "stylesheet" href = "rxn.css" > </head> <body>     <div id = "header" >         <h1> Reaction Tester </h1>         <p> Click the boxes as soon as you can... </p>     </div>     <div id = "box" ></div>     <script src = "rxn.js" >     </script> </body> C...
Read more

Suspect Detection System using Template Matching in OpenCV.

Image
 Problem statement:  To detect the suspect from a photograph of a group of people. The pic of that suspect is already stored in the form of a template/patch. The project uses the concept of template matching(in OpenCV) and object detection.  Here the source image is a photograph of a group of people and the template is an image of the suspect. It compares the source and the template by finding the matching probability and encircles the portion in the source image with the maximum matching probability. Source image: Template (Suspect Image): Output: Result:  We found the suspect in the group photograph.  Code: import cv2 import numpy as np   GroupPhotograph=cv2.imread("group.png",cv2.IMREAD_UNCHANGED)   cv2.imshow("Image",GroupPhotograph) cv2.waitKey() cv2.destroyAllWindows()   Man=cv2.imread("man.png",cv2.IMREAD_UNCHANGED)   cv2.imshow("Image",Man) cv2.waitKey() cv2.destroyAllWindows()   result=cv2.matchTemplate(GroupPhotograph,Man,cv2.T...
Read more