def main():
# Initialize some variables
face_locations = []
process_this_frame = True
# Create a new named window
kWinName = "Face detection demo"
# Open a video file or an image file or a camera stream
cap = cv.VideoCapture(args.input if args.input else 0)
while cv.waitKey(1) < 0:
# Save program start time
start_time = time.time()
# Read frame
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
# Resize frame of video to 1/4 size for faster face recognition processing
small_frame = cv.resize(frame, (0, 0), fx=args.scale, fy=args.scale)
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_small_frame = small_frame[:, :, ::-1]
if args.skip:
# Only process every other frame of video to save time
if process_this_frame:
# Find all the faces and face encodings in the current frame of video
face_locations = face_recognition.face_locations(
rgb_small_frame)
process_this_frame = not process_this_frame
else:
face_locations = face_recognition.face_locations(rgb_small_frame)
# Display the results
drawDetection(frame, face_locations, args.scale)
# Calculate processing time
label = "Process time: %.2f ms" % ((time.time() - start_time) * 1000)
print("[INFO] " + label)
if args.info:
cv.putText(frame, label, (0, 30), cv.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 255, 255))
# Display the frame
cv.imshow(kWinName, frame)
# Save results
if args.save and args.input:
saveResult(frame, "detection")
# Release handle to the webcam
cap.release()
cv.destroyAllWindows()
def main():
# pytesseract config
config = "-l eng --oem 1 --psm 3"
# Create a new named window
kWinName = "OCR demo with tesseract"
# Open a video file or an image file or a camera stream
cap = cv.VideoCapture(args.input if args.input else 0)
while cv.waitKey(1) < 0:
# Save program start time
start_time = time.time()
# Read frame
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
# Put OCR information
text = pytesseract.image_to_string(frame, config=config)
if len(text) > 0:
cv.putText(frame, text, (0, 60), cv.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 255, 255))
print("[INFO] text '{}' found".format(text))
else:
print("[INFO] No text found")
# Calculate processing time
label = "Total process time: %.2f ms" % (
(time.time() - start_time) * 1000)
print("[INFO] " + label)
if args.info:
cv.putText(frame, label, (0, 30), cv.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 255, 255))
# Display the frame
cv.imshow(kWinName, frame)
# Save results
if args.save and args.input:
saveResult(frame, "tess")
def main():
# Read and store arguments
confThreshold = args.thr
nmsThreshold = args.nms
inpWidth = args.width
inpHeight = args.height
# Load network
net = cv.dnn.readNet(args.model)
print("[INFO] East model loaded from {}".format(args.model))
# Create a new named window
kWinName = "Text detection demo with EAST"
outNames = []
outNames.append("feature_fusion/Conv_7/Sigmoid")
outNames.append("feature_fusion/concat_3")
# Open a video file or an image file or a camera stream
cap = cv.VideoCapture(args.input if args.input else 0)
while cv.waitKey(1) < 0:
# Save program start time
start_time = time.time()
# Read frame
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
# Get frame height and width
height_ = frame.shape[0]
width_ = frame.shape[1]
rW = width_ / float(inpWidth)
rH = height_ / float(inpHeight)
# Create a 4D blob from frame.
blob = cv.dnn.blobFromImage(
frame,
1.0,
(inpWidth, inpHeight),
(123.68, 116.78, 103.94),
swapRB=True,
crop=False,
)
# Run the model
net.setInput(blob)
outs = net.forward(outNames)
t, _ = net.getPerfProfile()
label = "Inference time: %.2f ms" % (t * 1000.0 / cv.getTickFrequency())
# Get scores and geometry
scores = outs[0]
geometry = outs[1]
[boxes, confidences] = decode(scores, geometry, confThreshold)
# Draw results
drawResult(frame, rW, rH, boxes, confidences, confThreshold, nmsThreshold)
# Put efficiency information
print("[INFO] EAST " + label)
if args.info:
cv.putText(
frame, label, (0, 60), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255)
)
# Calculate processing time
label = "Total process time: %.2f ms" % ((time.time() - start_time) * 1000)
print("[INFO] " + label)
if args.info:
cv.putText(
frame, label, (0, 30), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255)
)
# Display the frame
cv.imshow(kWinName, frame)
# Save results
if args.save and args.input:
saveResult(frame, "text_east")
def main():
# Read and store arguments
confThreshold = args.thr
nmsThreshold = args.nms
inpWidth = args.width
inpHeight = args.height
# Load network
net = cv.dnn.readNet(args.model)
print("[INFO] East model loaded from {}".format(args.model))
# Start RealSense Camera
options = rsOptions()
options.enableColor = True
options.resColor = [1280, 720]
rs = realsense(options)
rs.deviceInitial()
# Create a new named window
kWinName = "Text detection demo with EAST"
outNames = []
outNames.append("feature_fusion/Conv_7/Sigmoid")
outNames.append("feature_fusion/concat_3")
flagCapture = False
try:
while True:
# Save program start time
start_time = time.time()
# Read frame
rs.getFrame()
frame = rs.imageColor
if not frame.any():
cv.waitKey()
break
# Get frame height and width
height_ = frame.shape[0]
width_ = frame.shape[1]
rW = width_ / float(inpWidth)
rH = height_ / float(inpHeight)
# Create a 4D blob from frame.
blob = cv.dnn.blobFromImage(
frame,
1.0,
(inpWidth, inpHeight),
(123.68, 116.78, 103.94),
swapRB=True,
crop=False,
)
# Run the model
net.setInput(blob)
outs = net.forward(outNames)
t, _ = net.getPerfProfile()
label = "Inference time: %.2f ms" % (t * 1000.0 / cv.getTickFrequency())
# Get scores and geometry
scores = outs[0]
geometry = outs[1]
[boxes, confidences] = decode(scores, geometry, confThreshold)
# Draw results
drawResult(frame, rW, rH, boxes, confidences, confThreshold, nmsThreshold)
# Put efficiency information
if args.info:
cv.putText(
frame, label, (0, 60), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255)
)
# Calculate processing time
label = "Total process time: %.2f ms" % ((time.time() - start_time) * 1000)
if args.info:
cv.putText(
frame, label, (0, 30), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255)
)
# Display the frame
cv.imshow(kWinName, frame)
# Process screen capture
if flagCapture:
print("[INFO] Screen captured")
saveResult(frame, "text_rs_east")
flagCapture = False
# Keyboard commands
getKey = cv.waitKey(1) & 0xFF
if getKey is ord("c") or getKey is ord("C"):
flagCapture = True
elif getKey is ord("q") or getKey is ord("Q"):
break
except Exception as e:
print(e)
pass
finally:
# Stop streaming
cv.destroyAllWindows()
rs.pipeline.stop()
def main():
# load learned faces
print("[INFO] loading faces ...")
# check the image source comes from
print("[INFO] faces loaded from {} ...".format(args.pickle))
data = pickle.loads(open(args.pickle, "rb").read())
# Initialize some variables
face_locations = []
process_this_frame = True
flagCapture = False
# Create a new named window
kWinName = "Face recognition demo"
# Start RealSense Camera
options = rsOptions()
options.enableColor = True
options.resColor = [1280, 720]
rs = realsense(options)
rs.deviceInitial()
try:
while True:
# Save program start time
if args.skip is True:
if process_this_frame:
start_time = time.time()
else:
start_time = time.time()
# Read frame
rs.getFrame()
frame = rs.imageColor
if not frame.any():
cv.waitKey()
break
# Resize frame of video to 1/2 size for faster face recognition processing
small_frame = cv.resize(frame, (0, 0),
fx=args.scale,
fy=args.scale)
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_small_frame = small_frame[:, :, ::-1]
if args.skip is True:
# Only process every other frame of video to save time
if process_this_frame:
face_locations, face_names = faceMatch(
rgb_small_frame, data, args.threshold)
process_this_frame = not process_this_frame
else:
face_locations, face_names = faceMatch(rgb_small_frame, data,
args.threshold)
# Display the results
drawRecognition(frame, face_locations, face_names, args.scale)
# Calculate processing time
if args.skip is True:
if not process_this_frame:
label = "Process time: %.2f ms" % (
(time.time() - start_time) * 500)
else:
label = "Process time: %.2f ms" % (
(time.time() - start_time) * 1000)
# Display infomation
if args.info is True:
# if not process_this_frame:
# print("[INFO] " + label)
cv.putText(frame, label, (0, 30), cv.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 255, 255))
# Display the frame
cv.imshow(kWinName, frame)
# Process screen capture
if flagCapture:
print("[INFO] Screen captured")
saveResult(frame, "recognition_rs")
flagCapture = False
# Keyboard commands
getKey = cv.waitKey(1) & 0xFF
if getKey is ord("c") or getKey is ord("C"):
flagCapture = True
elif getKey is ord("q") or getKey is ord("Q"):
break
except Exception as e:
print(e)
pass
finally:
# Stop streaming
cv.destroyAllWindows()
rs.pipeline.stop()
def main():
# load learned faces
print("[INFO] loading faces ...")
# check the image source comes from
print("[INFO] faces loaded from {} ...".format(args.pickle))
data = pickle.loads(open(args.pickle, "rb").read())
# Initialize some variables
face_locations = []
process_this_frame = True
# Create a new named window
kWinName = "Face recognition demo"
# Open a video file or an image file or a camera stream
cap = cv.VideoCapture(args.input if args.input else 0)
while cv.waitKey(1) < 0:
# Save program start time
start_time = time.time()
# Read frame
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
# Resize frame of video to 1/2 size for faster face recognition processing
small_frame = cv.resize(frame, (0, 0), fx=args.scale, fy=args.scale)
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_small_frame = small_frame[:, :, ::-1]
if args.skip:
# Only process every other frame of video to save time
if process_this_frame:
face_locations, face_names = faceMatch(rgb_small_frame, data,
args.threshold)
if args.landmark:
face_landmarks = face_recognition.face_landmarks(
rgb_small_frame, face_locations)
process_this_frame = not process_this_frame
else:
face_locations, face_names = faceMatch(rgb_small_frame, data,
args.threshold)
if args.landmark:
face_landmarks = face_recognition.face_landmarks(
rgb_small_frame, face_locations)
if args.landmark:
drawLandmarks(frame, face_landmarks, args.scale)
# Display the results
drawRecognition(frame, face_locations, face_names, args.scale)
# Calculate processing time
label = "Process time: %.2f ms" % ((time.time() - start_time) * 1000)
print("[INFO] " + label)
if args.info:
cv.putText(frame, label, (0, 30), cv.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 255, 255))
# Display the frame
cv.imshow(kWinName, frame)
# Save results
if args.save and args.input:
saveResult(frame, "recognition")
# Release handle to the webcam
cap.release()
cv.destroyAllWindows()
def main():
# load svm model
print("[INFO] loading SVM model ...")
print("[INFO] SVM model from {} ...".format(args.svm))
clf = pickle.loads(open(args.svm, "rb").read())
# Initialize some variables
face_locations = []
process_this_frame = True
# Create a new named window
kWinName = "Face recognition demo with SVM classifier"
# Open a video file or an image file or a camera stream
cap = cv.VideoCapture(args.input if args.input else 0)
while cv.waitKey(1) < 0:
# Save program start time
start_time = time.time()
# Read frame
hasFrame, frame = cap.read()
if not hasFrame:
cv.waitKey()
break
# Resize frame of video to 1/2 size for faster face recognition processing
small_frame = cv.resize(frame, (0, 0), fx=args.scale, fy=args.scale)
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_small_frame = small_frame[:, :, ::-1]
if args.skip:
# Only process every other frame of video to save time
if process_this_frame:
# Find all the faces and face encodings in the current frame of video
face_locations = face_recognition.face_locations(
rgb_small_frame)
face_encodings = face_recognition.face_encodings(
rgb_small_frame, face_locations)
face_names = []
for face_encoding in face_encodings:
# predict face by SVM
name = clf.predict([face_encoding])
face_names.append(name[0])
process_this_frame = not process_this_frame
else:
face_locations = face_recognition.face_locations(rgb_small_frame)
face_encodings = face_recognition.face_encodings(
rgb_small_frame, face_locations)
face_names = []
for face_encoding in face_encodings:
# predict face by SVM
name = clf.predict([face_encoding])
face_names.append(name[0])
# Display the results
drawRecognition(frame, face_locations, face_names, args.scale)
# Calculate processing time
label = "Process time: %.2f ms" % ((time.time() - start_time) * 1000)
print("[INFO] " + label)
if args.info:
cv.putText(frame, label, (0, 30), cv.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 255, 255))
# Display the frame
cv.imshow(kWinName, frame)
# Save results
if args.save and args.input:
saveResult(frame, "recognition_svm")
# Release handle to the webcam
cap.release()
cv.destroyAllWindows()