Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 40bfe41

Browse files
Merge pull request avinashkranjan#682 from anubhav201241/master
Modification in Face-Detection/face-detect.py
2 parents 7fb586a + 389835b commit 40bfe41

File tree

4 files changed

+45598
-0
lines changed

4 files changed

+45598
-0
lines changed

‎Face-Detection/v2/README.md‎

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
<h1 align="center">Face Detection</h1>
2+
Detects the Face, eyes and the nose
3+
4+
---------------------------------------------------------------------
5+
6+
7+
## Modules Used
8+
- `OpenCV`
9+
- `Python`
10+
- `Google Colab`
11+
12+
## How it works
13+
- Firstly, you have to enter the correct path where the file is located.
14+
- Then it will convert your video frame by frame into grayscale
15+
- After running the code it will detects face, eye and mid part in the live video capturing.
16+
- It will show rectangle boxes which is detecting your face and eyes and detects your nose by a dot(.)
17+
18+
#### By [Anubhav](https://github.com/anubhav201241)

‎Face-Detection/v2/face_detectv2.py‎

Lines changed: 53 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
1+
#Face and Eye Detection
2+
import cv2
3+
4+
#PATH of the FILE
5+
CLASSIFIER_PATH = "./Facedetection/v2/haarcascade_frontalface_default.xml"
6+
EYEDETECTION_PATH = "./Facedetection/v2/haarcascade_eye.xml"
7+
8+
# Live video capturing
9+
cam = cv2.VideoCapture(0)
10+
11+
# Initializing classifier
12+
face_classifier = cv2.CascadeClassifier(CLASSIFIER_PATH)
13+
EYE_DETECTION = cv2.CascadeClassifier(EYEDETECTION_PATH)
14+
15+
while (True):
16+
17+
_, frame = cam.read()
18+
19+
# Converting to grayscale image
20+
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
21+
22+
# Returns coordinates of all faces in the frame
23+
faces = face_classifier.detectMultiScale(gray, 1.3, 5)
24+
# Cycle through each coordinate list
25+
for (x, y, w, h) in faces:
26+
27+
# Extracting mid points of bounding box
28+
mid_x = int(x + h/2)
29+
mid_y = int(y + h/2)
30+
31+
# Drawing - "bounding box"
32+
frame = cv2.rectangle(frame, (x, y), (x + h, y + h), (255, 0, 0), 2)
33+
# 'x-coordinate' on live feed
34+
frame = cv2.putText(frame, str(x), (x, y), cv2.FONT_HERSHEY_DUPLEX, 0.7, (0, 0, 255), 2)
35+
# "." represent mid part in face
36+
frame = cv2.putText(frame, ".", (mid_x, mid_y), cv2.FONT_HERSHEY_DUPLEX, 0.7, (0, 0, 255), 2)
37+
38+
#Detects The Eyes
39+
eyes = EYE_DETECTION.detectMultiScale(gray, 1.3, 5)
40+
for (ex,ey,ew,eh) in eyes:
41+
cv2.rectangle(frame, (ex,ey), (ex+eh, ey+eh), (0,255,0), 2)
42+
43+
44+
# Displaying video feed with detected faces
45+
cv2.imshow('Frame', frame)
46+
47+
# Reading for keyboard interrupts
48+
key = cv2.waitKey(1)
49+
if (key == 27):
50+
break
51+
52+
cam.release()
53+
cv2.destroyAllWindows()

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /