Develop Reference

Keypoint detection not working when keypoints are a certain colour

I'm using keypoint detection to find text within a game.
The background in the below images is dynamic, it's always a vaguely moving star-lit sky that you can barely see.
The detection works well when the text is white:
However, when the text is purple (unpredictable when this happens) the detection fails entirely:
Both the object I'm looking to detect and the image I'm running detection on are identical, screenshots are taken directly from within the game of the text i.e. the above. And then run on the exact same location the original screenshot were taken from.
The below code I've written using the official documentation I found here and here as a guide but it's very light on explaining itself.
Question: Is this an inherent limitation or is there something I can do to adjust to detect keypoints within the purple image?
import cv2 as cv
import win32gui, win32con, win32ui
import numpy as np
import glob
def get_haystack_image():
w, h = 1920, 1080
hwnd = None
wDC = win32gui.GetWindowDC(hwnd)
dcObj = win32ui.CreateDCFromHandle(wDC)
cDC = dcObj.CreateCompatibleDC()
dataBitMap = win32ui.CreateBitmap()
dataBitMap.CreateCompatibleBitmap(dcObj, w, h)
cDC.SelectObject(dataBitMap)
cDC.BitBlt((0, 0), (w, h), dcObj, (0, 0), win32con.SRCCOPY)
signedIntsArray = dataBitMap.GetBitmapBits(True)
img = np.frombuffer(signedIntsArray, dtype='uint8')
img.shape = (h, w, 4)
dcObj.DeleteDC()
cDC.DeleteDC()
win32gui.ReleaseDC(hwnd, wDC)
win32gui.DeleteObject(dataBitMap.GetHandle())
img = img[...,:3]
img = np.ascontiguousarray(img)
return img
def loadImages(directory):
# Intialise empty array
image_list = []
# Add images to array
for i in directory:
img = cv.imread(i, cv.IMREAD_UNCHANGED)
image_list.append((img, i))
return image_list
def preProcessNeedle(image_list):
needle_kp1_desc = []
for i in image_list:
img = i[0]
orb = cv.ORB_create(edgeThreshold=0, patchSize=32)
keypoint_needle, descriptors_needle = orb.detectAndCompute(img, None)
needle_kp1_desc.append((keypoint_needle, descriptors_needle, img))
return needle_kp1_desc
def match_keypoints(descriptors_needle, keypoint_haystack, min_match_count):
orbHaystack = cv.ORB_create(edgeThreshold=0, patchSize=32, nfeatures=3000)
keypoints_haystack, descriptors_haystack = orbHaystack.detectAndCompute(keypoint_haystack, None)
FLANN_INDEX_LSH = 6
index_params = dict(algorithm=FLANN_INDEX_LSH, table_number=6, key_size=12, multi_probe_level=1)
search_params = dict(checks=50)
try:
flann = cv.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(descriptors_needle, descriptors_haystack, k=2)
except cv.error:
return None, None, [], []
good = []
points = []
for pair in matches:
if len(pair) == 2:
if pair[0].distance < 0.7*pair[1].distance:
good.append(pair[0])
if len(good) > min_match_count:
for match in good:
points.append(keypoints_haystack[match.trainIdx].pt)
return keypoints_haystack, good, points
def shipDetection(needle_kp1_desc):
res = False
# Object Detection
for i, img in enumerate(needle_kp1_desc):
kp1 = img[0]
descriptors_needle = img[1]
needle_img = img[2]
# get an updated image of the screen & crop it
keypoint_haystack = get_haystack_image()
keypoint_haystack = keypoint_haystack[40:110, 850:1000]
kp2, matches, match_points, ship_avoided = match_keypoints(kp1, descriptors_needle, keypoint_haystack, min_match_count=40)
# display the matches
match_image = cv.drawMatches(needle_img, kp1, keypoint_haystack, kp2, matches, None)
cv.imshow('Keypoint Search', match_image)
cv.moveWindow("Keypoint Search",1940,30)
cv.waitKey(1)
if match_points:
# removed code as irrelevant to detection but left comments in
# find the center point of all the matched features
# account for the width of the needle image that appears on the left
# drawn the found center point on the output image
# display the processed image
cv.imshow('Keypoint Search', match_image)
cv.waitKey(1)
res = True
break
return res
ships_to_avoid = loadImages(glob.glob(r"C:\Users\*.png"))
needle_kp1_desc = preProcessNeedle(ships_to_avoid)
if shipDetection(needle_kp1_desc):
# do something with the output

Isolating the red channel, converting to grayscale and applying binary thresholding has normalised the results, they're all now a consistent "white" which my detection is successfully identifying.
apply_thresholding will perform this pre-processing to a folder, move the images from image_dir to output_dir then it'll delete the un-processes images from image_dir.
def apply_thresholding():
# get directory path where the images are stored
image_dir = r"C:\Users\pre"
# get directory path where you want to save the images
output_dir = r"C:\Users\post"
#iterate through all the files in the image directory
for _, _, image_names in os.walk(image_dir):
#iterate through all the files in the image_dir
for image_name in image_names:
# check for extension .png
if '.png' in image_name:
# get image read path(path should not contain spaces in them)
filepath = os.path.join(image_dir, image_name)
# get image write path
dstpath = os.path.join(output_dir, image_name)
print(filepath, dstpath)
# read the image
image = cv.imread(filepath)
r = image.copy()
# set blue and green channels to 0
r[:, :, 0] = 0
r[:, :, 1] = 0
# convert to grayscale now we've dropped b and g channels
gray = cv.cvtColor(r, cv.COLOR_BGR2GRAY)
# Apply binary thersholding
(T, thresh) = cv.threshold(gray, 40, 255, cv.THRESH_BINARY)
# write the image in a different path with the same name
cv.imwrite(dstpath, thresh)
files = glob.glob(r"C:\Users\pre\*")
for f in files:
os.remove(f)
I then applied the same channel isolation, grayscale conversion and binary thresholding to my detection area.
def get_haystack_image():
w, h = 1920, 1080
hwnd = None
wDC = win32gui.GetWindowDC(hwnd)
dcObj = win32ui.CreateDCFromHandle(wDC)
cDC = dcObj.CreateCompatibleDC()
dataBitMap = win32ui.CreateBitmap()
dataBitMap.CreateCompatibleBitmap(dcObj, w, h)
cDC.SelectObject(dataBitMap)
cDC.BitBlt((0, 0), (w, h), dcObj, (0, 0), win32con.SRCCOPY)
signedIntsArray = dataBitMap.GetBitmapBits(True)
img = np.frombuffer(signedIntsArray, dtype='uint8')
img.shape = (h, w, 4)
dcObj.DeleteDC()
cDC.DeleteDC()
win32gui.ReleaseDC(hwnd, wDC)
win32gui.DeleteObject(dataBitMap.GetHandle())
img = img[...,:3]
img = np.ascontiguousarray(img)
r = img.copy()
# set blue and green channels to 0
r[:, :, 0] = 0
r[:, :, 1] = 0
# convert to grayscale now we've dropped b and g channels
gray = cv.cvtColor(r, cv.COLOR_BGR2GRAY)
# Apply binary thersholding
(T, img) = cv.threshold(gray, 40, 255, cv.THRESH_BINARY)
return img

Enrollment of new faces into face recognition dataset (opencv, face_recognition)

I have a face recognition code(Entire code given at the end) that works perfectly fine with the existing dataset.
But I wanted it to also add new faces into the dataset(Enrollments), after asking for a user input for the name of the new person in the frame [like this: new_name = print(Who is this?)]. So then I could create a new folder by the entered name, and store the face inside the frame. This is what I did:
new_name = input("Who is this?")
path_2 = os.path.join('Images',new_name)
os.mkdir(path_2)
print("Directory '% s' created" % new_name)
for (x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0,0,255),
thickness = 2)
cv2.putText(frame, new_name, (x, y), cv2.FONT_HERSHEY_SIMPLEX,
0.75, (0, 255, 0), 2)
sub_face = frame[y:y+h, x:x+w]
FaceFileName = new_name + str(y+x) + ".jpg"
cv2.imwrite(os.path.join(path_2,FaceFileName),sub_face)
cv2.imshow("Frame",frame)
#if cv2.waitKey(1) & 0xFF == ord('q'):
# break
This worked fine with new people. But now I had to do something for unrecognized faces of known people.
In this case, we would already have a folder by the entered name. We must append the image into the existing folder by the entered name.
So for this I tried the below code: (Did not work)
else: # To store the unknown new face with name
new_name = input("Who is this?")
# If the new_name entered already exists as a folder
if os.path.isfile(new_name):
print(new_name,"folder already exists")
frame = imutils.resize(frame, width = 400)
rects = detector.detectMultiScale(cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY),
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30))
FaceFileName = new_name + str(y+x) + ".jpg"
for (x, y, w, h) in rects:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.imshow("Frame",frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("k"):
p = os.path.join([new_name,FaceFileName.format(str(total).zfill(5))])
# cv2.imwrite(os.path.join(path_2,FaceFileName),sub_face)
cv2.imwrite(p, orig)
total += 1
print("Image saved")
elif key == ord("q"):
break
# If the new_name does not exist as a folder new folder has to be created
else:
path_2 = os.path.join('Images',new_name)
os.mkdir(path_2)
print("Directory '% s' created" % new_name)
frame = imutils.resize(frame, width = 400)
rects = detector.detectMultiScale(cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY),
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30))
FaceFileName = new_name + str(y+x) + ".jpg"
for (x, y, w, h) in rects:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.imshow("Frame",frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("k"):
p = os.path.join([path_2,FaceFileName.format(str(total).zfill(5))])
# cv2.imwrite(os.path.join(path_2,FaceFileName),sub_face)
cv2.imwrite(p, orig)
total += 1
print("Image saved")
I am getting the error:
Who is this?Vishwesh
Traceback (most recent call last):
File "C:\Users\Vishw\databs.py", line 117, in <module>
os.mkdir(path_2)
FileExistsError: [WinError 183] Cannot create a file when that file already exists: 'Images\\Vishwesh'
[ WARN:0] global C:\Users\runneradmin\AppData\Local\Temp\pip-req-build-sgoydvi3\opencv\modules\videoio\src\cap_msmf.cpp (438) `anonymous-namespace'::SourceReaderCB::~SourceReaderCB terminating async callback
Complete code is given below. Let me know what is wrong with the code. Kindly help!
Note: I included the above codes under the # Face recognition on LIVE WEBCAM FEED section and as else statement for the "if True in matches:"
Here is my entire code:
# Extracting features from face
from imutils import paths
import face_recognition
import pickle
import cv2
import os
#Get paths of each file in folder named Images
#Images here contains my data(folders of various persons)
imagePaths = list(paths.list_images('Images'))
knownEncodings = []
knownNames = []
# loop over the image paths
for (i, imagePath) in enumerate(imagePaths):
# extract the person name from the image path
name = imagePath.split(os.path.sep)[-2]
# load the input image and convert it from BGR (OpenCV ordering)
# to dlib ordering (RGB)
image = cv2.imread(imagePath)
rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
#Use Face_recognition to locate faces
boxes = face_recognition.face_locations(rgb,model='hog')
# compute the facial embedding for the face
encodings = face_recognition.face_encodings(rgb, boxes)
# loop over the encodings
for encoding in encodings:
knownEncodings.append(encoding)
knownNames.append(name)
#save emcodings along with their names in dictionary data
data = {"encodings": knownEncodings, "names": knownNames}
#use pickle to save data into a file for later use
f = open("face_enc", "wb")
f.write(pickle.dumps(data))
f.close()
# Face recognition on LIVE WEBCAM FEED
import face_recognition
import pickle
import cv2
import os
#find path of xml file containing haarcascade file
cascPathface = os.path.dirname(
cv2.__file__) + "/data/haarcascade_frontalface_default.xml"
# load the harcaascade in the cascade classifier
faceCascade = cv2.CascadeClassifier(cascPathface)
# load the known faces and embeddings saved in last file
data = pickle.loads(open('face_enc', "rb").read())
print("Streaming started")
video_capture = cv2.VideoCapture(0)
# loop over frames from the video file stream
while True:
# grab the frame from the threaded video stream
ret, frame = video_capture.read()
orig = frame.copy()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = faceCascade.detectMultiScale(gray,
scaleFactor=1.05,
minNeighbors=3,
minSize=(60, 60),
flags=cv2.CASCADE_SCALE_IMAGE)
# convert the input frame from BGR to RGB
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
# the facial embeddings for face in input
encodings = face_recognition.face_encodings(rgb)
names = []
# loop over the facial embeddings incase
# we have multiple embeddings for multiple fcaes
for encoding in encodings:
#Compare encodings with encodings in data["encodings"]
#Matches contain array with boolean values and True for the embeddings it matches closely
#and False for rest
matches = face_recognition.compare_faces(data["encodings"],encoding)
#set name =unknown if no encoding matches
name = "Unknown"
# check to see if we have found a match
if True in matches:
# Find positions at which we get True and store them
matchedIdxs = [i for (i, b) in enumerate(matches) if b]
counts = {}
# loop over the matched indexes and maintain a count for
# each recognized face face
for i in matchedIdxs:
#Check the names at respective indexes we stored in matchedIdxs
name = data["names"][i]
#increase count for the name we got
counts[name] = counts.get(name, 0) + 1
#set name which has highest count
name = max(counts, key=counts.get)
else: # To store the unknown new face with name
new_name = input("Who is this?")
# If the new_name entered already exists as a folder
if os.path.isfile(new_name):
print(new_name,"folder already exists")
frame = imutils.resize(frame, width = 400)
rects = detector.detectMultiScale(cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY),
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30))
FaceFileName = new_name + str(y+x) + ".jpg"
for (x, y, w, h) in rects:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.imshow("Frame",frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("k"):
p = os.path.join([new_name,FaceFileName.format(str(total).zfill(5))])
# cv2.imwrite(os.path.join(path_2,FaceFileName),sub_face)
cv2.imwrite(p, orig)
total += 1
print("Image saved")
elif key == ord("q"):
break
# If the new_name does not exist as a folder new folder has to be created
else:
path_2 = os.path.join('Images',new_name)
os.mkdir(path_2)
print("Directory '% s' created" % new_name)
frame = imutils.resize(frame, width = 400)
rects = detector.detectMultiScale(cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY),
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30))
FaceFileName = new_name + str(y+x) + ".jpg"
for (x, y, w, h) in rects:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.imshow("Frame",frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("k"):
p = os.path.join([path_2,FaceFileName.format(str(total).zfill(5))])
# cv2.imwrite(os.path.join(path_2,FaceFileName),sub_face)
cv2.imwrite(p, orig)
total += 1
print("Image saved")
# update the list of names
names.append(name)
# loop over the recognized faces
for ((x, y, w, h), name) in zip(faces, names):
# rescale the face coordinates
# draw the predicted face name on the image
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.putText(frame, name, (x, y), cv2.FONT_HERSHEY_SIMPLEX,
0.75, (0, 255, 0), 2)
cv2.imshow("Frame", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
cv2.destroyAllWindows()

So, your issue is rather related to file operations then to face recognition...
Try to check if folder alreday exists before trying to create it:
path_2 = os.path.join('Images',new_name)
if not os.path.exists(path_2):
os.mkdir(path_2)

Using the idea given by #Bohdan:
else: # To store the unknown new face with name
new_name = input("Who is this?")
path_2 = os.path.join('Images',new_name)
for (x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0,0,255),
thickness = 2)
cv2.putText(frame, new_name, (x, y), cv2.FONT_HERSHEY_SIMPLEX,
0.75, (0, 255, 0), 2)
sub_face = frame[y:y+h, x:x+w]
FaceFileName = new_name + str(y+x) + ".jpg"
if not os.path.exists(path_2):
os.mkdir(path_2)
print("Directory '% s' created" % new_name)
cv2.imwrite(os.path.join(path_2,FaceFileName),sub_face)
# To store unrecognised faces of known people
else:
cv2.imwrite(os.path.join(path_2,FaceFileName),sub_face)
Code works perfectly fine!

multi-threaded face detection opencv

I have a script for single-threaded sequential face detection in a photo, and a script for cutting out faces. How do I convert to multithreading? So that the images are not processed sequentially, but simultaneously, parallel to each other.
import os
import cv2
import numpy as np
# Define paths
base_dir = os.path.dirname(__file__)
prototxt_path = os.path.join(base_dir + 'data/deploy.prototxt')
caffemodel_path = os.path.join(base_dir + 'data/weights.caffemodel')
# Read the model
model = cv2.dnn.readNetFromCaffe(prototxt_path, caffemodel_path)
# Create directory 'updated_images' if it does not exist
if not os.path.exists('updated_images'):
print("New directory created")
os.makedirs('updated_images')
# Loop through all images and save images with marked faces
for file in os.listdir(base_dir + 'images'):
file_name, file_extension = os.path.splitext(file)
if (file_extension in ['.png','.jpg']):
print("Image path: {}".format(base_dir + 'images/' + file))
image = cv2.imread(base_dir + 'images/' + file)
(h, w) = image.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 1.0, (300, 300), (104.0, 177.0, 123.0))
model.setInput(blob)
detections = model.forward()
# Create frame around face
for i in range(0, detections.shape[2]):
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
confidence = detections[0, 0, i, 2]
# If confidence > 0.5, show box around face
if (confidence > 0.5):
cv2.rectangle(image, (startX, startY), (endX, endY), (255, 255, 255), 2)
cv2.imwrite(base_dir + 'updated_images/' + file, image)
print("Image " + file + " converted successfully")
I tried to push the face detection and selection into def and then monitor the parallel streams through pool and map, but I am very weak in this, and obviously did something wrong. The script just stopped working.

Here is how I would do it:
import os
import cv2
import numpy as np
import threading
base_dir = os.path.dirname(__file__)
prototxt_path = os.path.join(base_dir + 'data/deploy.prototxt')
caffemodel_path = os.path.join(base_dir + 'data/weights.caffemodel')
model = cv2.dnn.readNetFromCaffe(prototxt_path, caffemodel_path)
if not os.path.exists('updated_images'):
print("New directory created")
os.makedirs('updated_images')
def process(file, base_dir):
print("Image path: {}".format(base_dir + 'images/' + file))
image = cv2.imread(base_dir + 'images/' + file)
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 1.0, (300, 300), (104.0, 177.0, 123.0))
model.setInput(blob)
detections = model.forward()
h, w = image.shape[:2]
for i in range(detections.shape[2]):
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
startX, startY, endX, endY = box.astype("int")
confidence = detections[0, 0, i, 2]
if confidence > 0.5:
cv2.rectangle(image, (startX, startY), (endX, endY), (255, 255, 255), 2)
cv2.imwrite(base_dir + 'updated_images/' + file, image)
print("Image " + file + " converted successfully")
for file in os.listdir(base_dir + 'images'):
file_name, file_extension = os.path.splitext(file)
if file_extension in ['.png','.jpg']:
thread = threading.Thread(target=process, args=(file, base_dir))
thread.start()
Most of it is the same as your code, except a large chunk is now in a function. I also took the liberty of removing some redundant code, such as how you don't need parenthesis to unpack an iterable, nor do you need parenthesis to do if statements.
As I don't have the files you open in your code, I'm unable to test it out, hence if there are any problems, there might be something I missed, so feel free to ping me if that happens.

writing pgm images with cv2.imwrite()

I want to write my detected images with caffe pre-trained model in openCV and it works with jpg or other similar formats but it's showing an error
SystemError: <built-in function imwrite> returned NULL without setting an error
and here is my code
import os
import cv2
import numpy
from imutils import paths
# DIR_PATH = os.path.dirname(os.path.realpath('dataset/'))
DIR_PATH = (list(paths.list_images('dataset')))
print(DIR_PATH)
if not os.path.exists('Output'):
os.makedirs('Output')
MODEL = cv2.dnn.readNetFromCaffe('deploy.prototxt', 'weights.caffemodel')
# print(DIR_PATH)
for file in DIR_PATH:
filename, file_extension = os.path.splitext(file)
if (file_extension in ['.png', '.jpg', '.pgm', '.jpeg']):
image = cv2.imread(file)
(h, w) = image.shape[:2]
print("Proccess one started ")
blob = cv2.dnn.blobFromImage(cv2.resize(
image, (300, 300)), 1.0, (300, 300), (104.0, 177.0, 123, 0))
MODEL.setInput(blob)
detections = MODEL.forward()
print("Proccess Two started ")
COUNT = 0
for i in range(0, detections.shape[2]):
box = detections[0, 0, i, 3:7] * numpy.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
confidence = detections[0, 0, i, 2]
if confidence > 0.165:
cv2.rectangle(image, (startX, startY),
(endX, endY), (0, 255, 0), 2)
COUNT = COUNT + 1
export_name = filename.split("\\")
print(export_name)
if file_extension == '.pgm' :
cv2.imwrite('Output/'+export_name[1]+export_name[2], image, 0)
else:
cv2.imwrite('Output/'+export_name[1]+file_extension, image)
print("Face detection complete for image " +
file + " (" + str(COUNT) + ") faces found!")
and also I've checked my values.
images with PGM format has been loading but and detecting faces but the number of faces is too much and it's not writing at all with cv2.imwrite
here is the exact problem
if file_extension == '.pgm' :
cv2.imwrite('Output/'+export_name[1]+export_name[2], image, 0)
else:
cv2.imwrite('Output/'+export_name[1]+file_extension, image)

OpenCV does not read paths in OS paths or PathLib formats, it reads a string so change your code to:
if file_extension == '.pgm':
fname = 'Output/{}{}'.format(export_name[1],export_name[2])
cv2.imwrite(fname, image, 0)
else:
fname = 'Output/{}{}'.format(export_name[1],file_extension)
cv2.imwrite(fname, image)

Face Recoginition Python open cv

Is there any way i can make my own train set for face recognition in python ? To be more specific i want to make a train set like an AT&T Face database. I want my camera to take 20 images of each person(30 max) and store it in the separate folders by the name of each person.
import cv2, sys, numpy, os
size = 4
fn_haar = 'haarcascade_frontalface_default.xml'
fn_dir = 'att_faces'
fn_name = sys.argv[1]
path = os.path.join(fn_dir, fn_name)
if not os.path.isdir(path):
os.mkdir(path)
(im_width, im_height) = (112, 92)
haar_cascade = cv2.CascadeClassifier(fn_haar)
webcam = cv2.VideoCapture(0)
# The program loops until it has 20 images of the face.
count = 0
while count < 20:
(rval, im) = webcam.read()
im = cv2.flip(im, 1, 0)
gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
mini = cv2.resize(gray, (gray.shape[1] / size, gray.shape[0] / size))
faces = haar_cascade.detectMultiScale(mini)
faces = sorted(faces, key=lambda x: x[3])
if faces:
face_i = faces[0]
(x, y, w, h) = [v * size for v in face_i]
face = gray[y:y + h, x:x + w]
face_resize = cv2.resize(face, (im_width, im_height))
pin=sorted([int(n[:n.find('.')]) for n in os.listdir(path)
if n[0]!='.' ]+[0])[-1] + 1
cv2.imwrite('%s/%s.png' % (path, pin), face_resize)
cv2.rectangle(im, (x, y), (x + w, y + h), (0, 255, 0), 3)
cv2.putText(im, fn_name, (x - 10, y - 10), cv2.FONT_HERSHEY_PLAIN,
1,(0, 255, 0))
count += 1
cv2.imshow('OpenCV', im)
key = cv2.waitKey(10)
if key == 27:
break

For this, you just need to provide a particular path to save all the image with (.png) or (.bmp) or (.jpg) extension in a sorted manner.
# train.py
import cv2, sys, numpy, os
size = 4
fn_haar = 'haarcascade_frontalface_default.xml'
fn_dir = 'face_data'
fn_name = sys.argv[0]
path = os.path.join(fn_dir, fn_name)
(im_width, im_height) = (112, 92)
haar_cascade = cv2.CascadeClassifier(fn_haar)
webcam = cv2.VideoCapture(0)
# Generate name for image file
pin=sorted([int(n[:n.find('.')]) for n in os.listdir(path)
if n[0]!='.' ]+[0])[-1] + 1
# Beginning message
print("\n\033[94mThe program will save 20 samples. \
Move your head around to increase while it runs.\033[0m\n")
# The program loops until it has 20 images of the face.
count = 0
pause = 0
count_max = 20
while count < count_max:
# Loop until the camera is working
rval = False
while(not rval):
# Put the image from the webcam into 'frame'
(rval, frame) = webcam.read()
if(not rval):
print("Failed to open webcam. Trying again...")
# Get image size
height, width, channels = frame.shape
# Flip frame
frame = cv2.flip(frame, 1, 0)
# Convert to grayscale
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Scale down for speed
mini = cv2.resize(gray, (int(gray.shape[1] / size), int(gray.shape[0] / size)))
# Detect faces
faces = haar_cascade.detectMultiScale(mini)
# We only consider largest face
faces = sorted(faces, key=lambda x: x[3])
if faces:
face_i = faces[0]
(x, y, w, h) = [v * size for v in face_i]
face = gray[y:y + h, x:x + w]
face_resize = cv2.resize(face, (im_width, im_height))
# Draw rectangle and write name
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 3)
cv2.putText(frame, fn_name, (x - 10, y - 10), cv2.FONT_HERSHEY_PLAIN,
1,(0, 255, 0))
# Remove false positives
if(w * 6 < width or h * 6 < height):
print("Face too small")
else:
# To create diversity, only save every fith detected image
if(pause == 0):
print("Saving training sample "+str(count+1)+"/"+str(count_max))
# Save image file
cv2.imwrite('%s/%s.png' % (path, pin), face_resize)
pin += 1
count += 1
pause = 1
if(pause > 0):
pause = (pause + 1) % 5
cv2.imshow('OpenCV', frame)
key = cv2.waitKey(10)
if key == 27:
break
This code will help you to get the cropped images from the webcam and store them in a directory name as face_data for training purpose.
In case, you don't want to train your dataset from webcam, you can simply do one thing:
that just create a directory and create 5-6 sub-directory in it as in Happy, Sad, Angry, Neutral, Calm, etc.
Download the images and put them in corresponding folders for training purpose, now follow this code.
## This program first ensures if the face of a person exists in the given image or
not then if it exists, it crops
## the image of the face and saves to the given directory.
## Importing Modules
import cv2
import os
directory = "C:\\Users\\hp"
## directory where the images to be saved:
f_directory = "C:\\Users\\hp\\face_data/"
def facecrop(image):
## Crops the face of a person from an image!
## OpenCV XML FILE for Frontal Facial Detection using HAAR CASCADES.
facedata=
"C:\\opencv\\build\\etc\\haarcascades\\haarcascade_frontalface_default.xml"
cascade = cv2.CascadeClassifier(facedata)
## Reading the given Image with OpenCV
img = cv2.imread(image)
try:
minisize = (img.shape[1],img.shape[0])
miniframe = cv2.resize(img, minisize)
faces = cascade.detectMultiScale(miniframe)
for f in faces:
x, y, w, h = [ v for v in f ]
cv2.rectangle(img, (x,y), (x+w,y+h), (0,255,0), 2)
sub_face = img[y:y+h, x:x+w]
f_name = image.split('/')
f_name = f_name[-1]
## Change here the Desired directory.
cv2.imwrite(f_directory + f_name, sub_face)
print ("Writing: " + image)
except:
pass
if __name__ == '__main__':
images = os.listdir(directory)
i = 0
for img in images:
file = directory + img
print (i)
facecrop(file)
i += 1