step-1_find-faces.py

import sys
import dlib
from skimage import io

# Take the image file name from the command line
file_name = sys.argv[1]

# Create a HOG face detector using the built-in dlib class
face_detector = dlib.get_frontal_face_detector()

win = dlib.image_window()

# Load the image into an array
image = io.imread(file_name)

# Run the HOG face detector on the image data.
# The result will be the bounding boxes of the faces in our image.
detected_faces = face_detector(image, 1)

print("I found {} faces in the file {}".format(len(detected_faces), file_name))

# Open a window on the desktop showing the image
win.set_image(image)

# Loop through each face we found in the image
for i, face_rect in enumerate(detected_faces):

	# Detected faces are returned as an object with the coordinates 
	# of the top, left, right and bottom edges
	print("- Face #{} found at Left: {} Top: {} Right: {} Bottom: {}".format(i, face_rect.left(), face_rect.top(), face_rect.right(), face_rect.bottom()))

	# Draw a box around each face we found
	win.add_overlay(face_rect)
	        
# Wait until the user hits <enter> to close the window	        
dlib.hit_enter_to_continue()

I tried to run it on Windows and python 3.6 but got syntax error.
Users\user1> python face.py
Traceback (most recent call last):
File "C:\Users\user1\Desktop\face.py", line 6, in
file_name = sys.argv[1]
IndexError: list index out of range
Appreciate if there is any help ,hints :-(

################################################
################################################

Thank you very much t for your nice comments. yes I missed the arg destination file.
It is sorted out. :-)

Instead of

file_name = sys.argv[1] change to your image path file_name = "Your Image path"

This means that you have to run python from the commandline like so:

python step-1_find-faces.py "imagefiles"

The sys.argv[1]means you need to parse a image to the file. If you have a image named 'cat.jpg' in the working directory, try
python face.py cat.jpg

Hey I got "module 'dlib' has no attribute 'image_window'" and I followed https://gist.github.com/ageitgey/629d75c1baac34dfa5ca2a1928a7aeaf to install dlib. using mac 10.12.6. Do you have any idea what I did wrong?

How can I connect this to webcam so that it can detect my face?

@ni3-k:
There's a video series from sentdex that goes over using a (albeit different) machine learning model to draw bounding boxes over an image using a webcam. You should be able to use all of the code from this project, while just using the openCV functions he puts in during the video to grab the image from the webcam.

I found this series really helpful when making my first real-time object recognition project; hopefully you will find it helpful too, even though it is using a different ML model.

Where can I see the continuation of the article (code)? :)

RuntimeError: Unsupported image type, must be 8bit gray or RGB image

please help and if I keep the image file in the folder of the python file and pass the file_name="example.jpg" will it work?

How to show HoG features?

Where is the Hog representation

I am unable to install dlib . The following error is shown
CMake Error in CMakeLists.txt:
Generator

  NMake Makefiles

does not support platform specification, but platform

  x64

was specified.

CMake Error: CMAKE_C_COMPILER not set, after EnableLanguage
CMake Error: CMAKE_CXX_COMPILER not set, after EnableLanguage
-- Configuring incomplete, errors occurred!

Seems to work well with images on human face, added one cat image where it was not able to identify face. Any hint what is wrong?

After giving the command in anaconda promt the image window is not opening.
Can you please help me out in this?
Please reply me as soon as possible.

@FightForCS
Do you know how to show HoG features now?
I want to see HOG image.

@elhoussinetalab
Do you find the HOG image?
I want to know how to show the HOG image.

Do you know how to show HOG fetures?

Hey I got "module 'dlib' has no attribute 'image_window'" and I followed https://gist.github.com/ageitgey/629d75c1baac34dfa5ca2a1928a7aeaf to install dlib. using mac 10.12.6. Do you have any idea what I did wrong?
You can uninstall dlib absolutely, and install the dlib again.(If this can't help you, you can install the other version to try it)

Its not working for all images ,only faces from particular images of human are being detected

How can I connect this to webcam so that it can detect my face?

If you're using OpenCV use this function

import cv2

v1 = cv2.VideoCapture(0) # 0 -- indicates your webcam
print(v1.isOpened()) # Returns bool value based on the video capture object

I have successfully run this script and it return an image with a box in face. But I just want a HOG image just like that:

How can I get it?

from skimage.feature import hog
from skimage import exposure
import cv2


image = cv2.imread('/your/image/path')
fd, hog_image = hog(image, orientations=8, pixels_per_cell=(16, 16),
                    cells_per_block=(1, 1), visualize=True, multichannel=True)

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4), sharex=True, sharey=True)

ax1.axis('off')
ax1.imshow(image, cmap=plt.cm.gray)
ax1.set_title('Input image')

# Rescale histogram for better display
hog_image_rescaled = exposure.rescale_intensity(hog_image, in_range=(0, 10))

ax2.axis('off')
ax2.imshow(hog_image_rescaled, cmap=plt.cm.gray)
ax2.set_title('Histogram of Oriented Gradients')
plt.show()

from skimage.feature import hog
from skimage import exposure
import cv2


image = cv2.imread('/your/image/path')
fd, hog_image = hog(image, orientations=8, pixels_per_cell=(16, 16),
                    cells_per_block=(1, 1), visualize=True, multichannel=True)

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4), sharex=True, sharey=True)

ax1.axis('off')
ax1.imshow(image, cmap=plt.cm.gray)
ax1.set_title('Input image')

# Rescale histogram for better display
hog_image_rescaled = exposure.rescale_intensity(hog_image, in_range=(0, 10))

ax2.axis('off')
ax2.imshow(hog_image_rescaled, cmap=plt.cm.gray)
ax2.set_title('Histogram of Oriented Gradients')
plt.show()

Hi, you forgot to add: "from matplotlib import pyplot as plt".

@Dankrou yeah it was on a different kernel but thanks for pointing that out.

import os
import sys
import dlib
from skimage import io, exposure
from skimage.feature import hog
import cv2
import matplotlib.pyplot as plt

main = os.path.abspath(sys.argv[0])
file_name = os.path.abspath(os.path.join(os.path.dirname(main), "examples","faces","2.jpg"))

Contruye histograma de un rostros para identificación

image = cv2.imread(file_name)
fd, hog_image = hog(image, orientations=8, pixels_per_cell=(16, 16),
cells_per_block=(1, 1), visualize=True, channel_axis=2)

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4), sharex=True, sharey=True)

ax1.axis('off')
ax1.imshow(image, cmap=plt.cm.gray)
ax1.set_title('Input image')

Rescale histogram for better display

hog_image_rescaled = exposure.rescale_intensity(hog_image, in_range=(0, 20))

ax2.axis('off')
ax2.imshow(hog_image_rescaled, cmap=plt.cm.gray)
ax2.set_title('Histogram of Oriented Gradients')
plt.show()

Its working.

…

On Fri, 26 May 2023, 17:18 Daruin Herrera, ***@***.***> wrote: ***@***.**** commented on this gist. ------------------------------ import os import sys import dlib from skimage import io, exposure from skimage.feature import hog import cv2 import matplotlib.pyplot as plt main = os.path.abspath(sys.argv[0]) file_name = os.path.abspath(os.path.join(os.path.dirname(main), "examples","faces","2.jpg")) Contruye histograma de un rostros para identificación image = cv2.imread(file_name) fd, hog_image = hog(image, orientations=8, pixels_per_cell=(16, 16), cells_per_block=(1, 1), visualize=True, channel_axis=2) fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4), sharex=True, sharey=True) ax1.axis('off') ax1.imshow(image, cmap=plt.cm.gray) ax1.set_title('Input image') Rescale histogram for better display hog_image_rescaled = exposure.rescale_intensity(hog_image, in_range=(0, 20)) ax2.axis('off') ax2.imshow(hog_image_rescaled, cmap=plt.cm.gray) ax2.set_title('Histogram of Oriented Gradients') plt.show() — Reply to this email directly, view it on GitHub <https://gist.github.com/ageitgey/1c1cb1c60ace321868f7410d48c228e1#gistcomment-4580744> or unsubscribe <https://github.com/notifications/unsubscribe-auth/AE5NYIOG5RA6PNC4JJ6W4O3XIDCUDBFKMF2HI4TJMJ2XIZLTSKBKK5TBNR2WLJDHNFZXJJDOMFWWLK3UNBZGKYLEL52HS4DFQKSXMYLMOVS2I5DSOVS2I3TBNVS3W5DIOJSWCZC7OBQXE5DJMNUXAYLOORPWCY3UNF3GS5DZVRZXKYTKMVRXIX3UPFYGLK2HNFZXIQ3PNVWWK3TUUZ2G64DJMNZZDAVEOR4XAZNEM5UXG5FFOZQWY5LFVAZTQMJQGQ4TQMFHORZGSZ3HMVZKMY3SMVQXIZI> . You are receiving this email because you commented on the thread. Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub> .

OpenCV vesion:

import cv2
import dlib
import numpy as np

# Take the image file name from the command line
file_name = "./image.png"

# Create a HOG face detector using the built-in dlib class
face_detector = dlib.get_frontal_face_detector()

# Load the image into an array
image = cv2.imread(file_name)

# Run the HOG face detector on the image data.
# The result will be the bounding boxes of the faces in our image.
detected_faces = face_detector(image, 1)

print("I found {} faces in the file {}".format(len(detected_faces), file_name))

# Loop through each face we found in the image
for i, face_rect in enumerate(detected_faces):
    # Detected faces are returned as an object with the coordinates 
    # of the top, left, right and bottom edges
    print("- Face #{} found at Left: {} Top: {} Right: {} Bottom: {}".format(i, face_rect.left(), face_rect.top(), face_rect.right(), face_rect.bottom()))

    # Draw a box around each face we found
    cv2.rectangle(image, (face_rect.left(), face_rect.top()), (face_rect.right(), face_rect.bottom()), (0, 255, 0), 2)

# Display the image with the detected faces
cv2.imshow('Detected Faces', image)

# Wait until the user hits <enter> to close the window
cv2.waitKey(0)
cv2.destroyAllWindows()