mirror of
https://github.com/serengil/deepface.git
synced 2025-06-07 03:55:21 +00:00
detector mechanism
This commit is contained in:
Sefik Ilkin Serengil
parent
1e8733035d
commit
b898f97b38
1
.gitignore
vendored
1
.gitignore
vendored
@ -14,6 +14,7 @@ deepface/commons/__pycache__/*
|
||||
deepface/basemodels/__pycache__/*
|
||||
deepface/extendedmodels/__pycache__/*
|
||||
deepface/subsidiarymodels/__pycache__/*
|
||||
deepface/detectors/__pycache__/*
|
||||
tests/dataset/*.pkl
|
||||
.DS_Store
|
||||
deepface/.DS_Store
|
||||
|
||||
@ -774,7 +774,7 @@ def stream(db_path = '', model_name ='VGG-Face', distance_metric = 'cosine', ena
|
||||
realtime.analysis(db_path, model_name, distance_metric, enable_face_analysis
|
||||
, source = source, time_threshold = time_threshold, frame_threshold = frame_threshold)
|
||||
|
||||
def detectFace(img_path, detector_backend = 'mtcnn'):
|
||||
def detectFace(img_path, detector_backend = 'mtcnn', enforce_detection = True):
|
||||
|
||||
"""
|
||||
This function applies pre-processing stages of a face recognition pipeline including detection and alignment
|
||||
@ -790,7 +790,8 @@ def detectFace(img_path, detector_backend = 'mtcnn'):
|
||||
|
||||
functions.initialize_detector(detector_backend = detector_backend)
|
||||
|
||||
img = functions.preprocess_face(img = img_path, detector_backend = detector_backend)[0] #preprocess_face returns (1, 224, 224, 3)
|
||||
img = functions.preprocess_face(img = img_path, detector_backend = detector_backend
|
||||
, enforce_detection = enforce_detection)[0] #preprocess_face returns (1, 224, 224, 3)
|
||||
return img[:, :, ::-1] #bgr to rgb
|
||||
|
||||
#---------------------------
|
||||
|
||||
@ -2,18 +2,10 @@ import os
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import cv2
|
||||
from pathlib import Path
|
||||
import gdown
|
||||
import hashlib
|
||||
import math
|
||||
from PIL import Image
|
||||
import copy
|
||||
import base64
|
||||
import multiprocessing
|
||||
import subprocess
|
||||
import bz2
|
||||
from deepface.commons import distance
|
||||
from mtcnn import MTCNN #0.1.0
|
||||
from pathlib import Path
|
||||
|
||||
from deepface.detectors import FaceDetector
|
||||
|
||||
import tensorflow as tf
|
||||
tf_version = int(tf.__version__.split(".")[0])
|
||||
@ -52,92 +44,7 @@ def initialize_input(img1_path, img2_path = None):
|
||||
def initialize_detector(detector_backend):
|
||||
|
||||
global face_detector
|
||||
|
||||
home = str(Path.home())
|
||||
|
||||
#eye detector is common for opencv and ssd
|
||||
if detector_backend == 'opencv' or detector_backend == 'ssd':
|
||||
opencv_path = get_opencv_path()
|
||||
eye_detector_path = opencv_path+"haarcascade_eye.xml"
|
||||
|
||||
if os.path.isfile(eye_detector_path) != True:
|
||||
raise ValueError("Confirm that opencv is installed on your environment! Expected path ",eye_detector_path," violated.")
|
||||
|
||||
global eye_detector
|
||||
eye_detector = cv2.CascadeClassifier(eye_detector_path)
|
||||
|
||||
#------------------------------
|
||||
#face detectors
|
||||
if detector_backend == 'opencv':
|
||||
opencv_path = get_opencv_path()
|
||||
face_detector_path = opencv_path+"haarcascade_frontalface_default.xml"
|
||||
|
||||
if os.path.isfile(face_detector_path) != True:
|
||||
raise ValueError("Confirm that opencv is installed on your environment! Expected path ",face_detector_path," violated.")
|
||||
|
||||
face_detector = cv2.CascadeClassifier(face_detector_path)
|
||||
|
||||
elif detector_backend == 'ssd':
|
||||
|
||||
#check required ssd model exists in the home/.deepface/weights folder
|
||||
|
||||
#model structure
|
||||
if os.path.isfile(home+'/.deepface/weights/deploy.prototxt') != True:
|
||||
|
||||
print("deploy.prototxt will be downloaded...")
|
||||
|
||||
url = "https://github.com/opencv/opencv/raw/3.4.0/samples/dnn/face_detector/deploy.prototxt"
|
||||
|
||||
output = home+'/.deepface/weights/deploy.prototxt'
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
#pre-trained weights
|
||||
if os.path.isfile(home+'/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel') != True:
|
||||
|
||||
print("res10_300x300_ssd_iter_140000.caffemodel will be downloaded...")
|
||||
|
||||
url = "https://github.com/opencv/opencv_3rdparty/raw/dnn_samples_face_detector_20170830/res10_300x300_ssd_iter_140000.caffemodel"
|
||||
|
||||
output = home+'/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel'
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
face_detector = cv2.dnn.readNetFromCaffe(
|
||||
home+"/.deepface/weights/deploy.prototxt",
|
||||
home+"/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel"
|
||||
)
|
||||
|
||||
elif detector_backend == 'dlib':
|
||||
import dlib #this is not a must library within deepface. that's why, I didn't put this import to a global level. version: 19.20.0
|
||||
|
||||
global sp
|
||||
|
||||
face_detector = dlib.get_frontal_face_detector()
|
||||
|
||||
#check required file exists in the home/.deepface/weights folder
|
||||
if os.path.isfile(home+'/.deepface/weights/shape_predictor_5_face_landmarks.dat') != True:
|
||||
|
||||
print("shape_predictor_5_face_landmarks.dat.bz2 is going to be downloaded")
|
||||
|
||||
url = "http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2"
|
||||
output = home+'/.deepface/weights/'+url.split("/")[-1]
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
zipfile = bz2.BZ2File(output)
|
||||
data = zipfile.read()
|
||||
newfilepath = output[:-4] #discard .bz2 extension
|
||||
open(newfilepath, 'wb').write(data)
|
||||
|
||||
sp = dlib.shape_predictor(home+"/.deepface/weights/shape_predictor_5_face_landmarks.dat")
|
||||
|
||||
elif detector_backend == 'mtcnn':
|
||||
face_detector = MTCNN()
|
||||
|
||||
elif detector_backend == 'retinaface':
|
||||
from retinaface import RetinaFace
|
||||
face_detector = RetinaFace.build_model()
|
||||
face_detector = FaceDetector.build_model(detector_backend)
|
||||
|
||||
def initializeFolder():
|
||||
|
||||
@ -157,16 +64,6 @@ def loadBase64Img(uri):
|
||||
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
|
||||
return img
|
||||
|
||||
def get_opencv_path():
|
||||
opencv_home = cv2.__file__
|
||||
folders = opencv_home.split(os.path.sep)[0:-1]
|
||||
|
||||
path = folders[0]
|
||||
for folder in folders[1:]:
|
||||
path = path + "/" + folder
|
||||
|
||||
return path+"/data/"
|
||||
|
||||
def load_image(img):
|
||||
|
||||
exact_image = False
|
||||
@ -192,280 +89,25 @@ def load_image(img):
|
||||
|
||||
def detect_face(img, detector_backend = 'opencv', grayscale = False, enforce_detection = True):
|
||||
|
||||
home = str(Path.home())
|
||||
|
||||
img_region = [0, 0, img.shape[0], img.shape[1]]
|
||||
|
||||
#if functions.preproces_face is called directly, then face_detector global variable might not been initialized.
|
||||
if not "face_detector" in globals():
|
||||
initialize_detector(detector_backend = detector_backend)
|
||||
|
||||
if detector_backend == 'opencv':
|
||||
|
||||
faces = []
|
||||
|
||||
try:
|
||||
faces = face_detector.detectMultiScale(img, 1.3, 5)
|
||||
except:
|
||||
pass
|
||||
|
||||
if len(faces) > 0:
|
||||
x,y,w,h = faces[0] #focus on the 1st face found in the image
|
||||
detected_face = img[int(y):int(y+h), int(x):int(x+w)]
|
||||
return detected_face, [x, y, w, h]
|
||||
|
||||
else: #if no face detected
|
||||
|
||||
if enforce_detection != True:
|
||||
return img, img_region
|
||||
|
||||
else:
|
||||
raise ValueError("Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.")
|
||||
|
||||
elif detector_backend == 'ssd':
|
||||
|
||||
ssd_labels = ["img_id", "is_face", "confidence", "left", "top", "right", "bottom"]
|
||||
|
||||
target_size = (300, 300)
|
||||
|
||||
base_img = img.copy() #we will restore base_img to img later
|
||||
|
||||
original_size = img.shape
|
||||
|
||||
img = cv2.resize(img, target_size)
|
||||
|
||||
aspect_ratio_x = (original_size[1] / target_size[1])
|
||||
aspect_ratio_y = (original_size[0] / target_size[0])
|
||||
|
||||
imageBlob = cv2.dnn.blobFromImage(image = img)
|
||||
|
||||
face_detector.setInput(imageBlob)
|
||||
detections = face_detector.forward()
|
||||
|
||||
detections_df = pd.DataFrame(detections[0][0], columns = ssd_labels)
|
||||
|
||||
detections_df = detections_df[detections_df['is_face'] == 1] #0: background, 1: face
|
||||
detections_df = detections_df[detections_df['confidence'] >= 0.90]
|
||||
|
||||
detections_df['left'] = (detections_df['left'] * 300).astype(int)
|
||||
detections_df['bottom'] = (detections_df['bottom'] * 300).astype(int)
|
||||
detections_df['right'] = (detections_df['right'] * 300).astype(int)
|
||||
detections_df['top'] = (detections_df['top'] * 300).astype(int)
|
||||
|
||||
if detections_df.shape[0] > 0:
|
||||
|
||||
#TODO: sort detections_df
|
||||
|
||||
#get the first face in the image
|
||||
instance = detections_df.iloc[0]
|
||||
|
||||
left = instance["left"]
|
||||
right = instance["right"]
|
||||
bottom = instance["bottom"]
|
||||
top = instance["top"]
|
||||
|
||||
detected_face = base_img[int(top*aspect_ratio_y):int(bottom*aspect_ratio_y), int(left*aspect_ratio_x):int(right*aspect_ratio_x)]
|
||||
|
||||
return detected_face, [int(left*aspect_ratio_x), int(top*aspect_ratio_y), int(right*aspect_ratio_x) - int(left*aspect_ratio_x), int(bottom*aspect_ratio_y) - int(top*aspect_ratio_y)]
|
||||
|
||||
else: #if no face detected
|
||||
|
||||
if enforce_detection != True:
|
||||
img = base_img.copy()
|
||||
return img, img_region
|
||||
|
||||
else:
|
||||
raise ValueError("Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.")
|
||||
|
||||
elif detector_backend == 'dlib':
|
||||
|
||||
detections = face_detector(img, 1)
|
||||
|
||||
if len(detections) > 0:
|
||||
|
||||
for idx, d in enumerate(detections):
|
||||
left = d.left(); right = d.right()
|
||||
top = d.top(); bottom = d.bottom()
|
||||
|
||||
detected_face = img[top:bottom, left:right]
|
||||
|
||||
return detected_face, [left, top, right - left, bottom - top]
|
||||
|
||||
else: #if no face detected
|
||||
|
||||
if enforce_detection != True:
|
||||
return img, img_region
|
||||
|
||||
else:
|
||||
raise ValueError("Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.")
|
||||
|
||||
elif detector_backend == 'mtcnn':
|
||||
|
||||
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) #mtcnn expects RGB but OpenCV read BGR
|
||||
detections = face_detector.detect_faces(img_rgb)
|
||||
|
||||
if len(detections) > 0:
|
||||
detection = detections[0]
|
||||
x, y, w, h = detection["box"]
|
||||
detected_face = img[int(y):int(y+h), int(x):int(x+w)]
|
||||
return detected_face, [x, y, w, h]
|
||||
|
||||
else: #if no face detected
|
||||
if not enforce_detection:
|
||||
return img, img_region
|
||||
|
||||
else:
|
||||
raise ValueError("Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.")
|
||||
|
||||
elif detector_backend == 'retinaface':
|
||||
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) #retinaface expects RGB but OpenCV read BGR
|
||||
|
||||
from retinaface import RetinaFace
|
||||
faces = RetinaFace.extract_faces(img_rgb, align = True)
|
||||
|
||||
if len(faces) > 0:
|
||||
face = faces[0]
|
||||
return face, img_region
|
||||
|
||||
else: #if no face detected
|
||||
if not enforce_detection:
|
||||
return img, img_region
|
||||
else:
|
||||
raise ValueError("Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.")
|
||||
|
||||
detected_face, img_region = FaceDetector.detect_face(face_detector, detector_backend, img)
|
||||
|
||||
if (isinstance(detected_face, np.ndarray)):
|
||||
return detected_face, img_region
|
||||
else:
|
||||
detectors = ['opencv', 'ssd', 'dlib', 'mtcnn']
|
||||
raise ValueError("Valid backends are ", detectors," but you passed ", detector_backend)
|
||||
|
||||
def alignment_procedure(img, left_eye, right_eye):
|
||||
|
||||
#this function aligns given face in img based on left and right eye coordinates
|
||||
|
||||
left_eye_x, left_eye_y = left_eye
|
||||
right_eye_x, right_eye_y = right_eye
|
||||
|
||||
#-----------------------
|
||||
#find rotation direction
|
||||
|
||||
if left_eye_y > right_eye_y:
|
||||
point_3rd = (right_eye_x, left_eye_y)
|
||||
direction = -1 #rotate same direction to clock
|
||||
else:
|
||||
point_3rd = (left_eye_x, right_eye_y)
|
||||
direction = 1 #rotate inverse direction of clock
|
||||
|
||||
#-----------------------
|
||||
#find length of triangle edges
|
||||
|
||||
a = distance.findEuclideanDistance(np.array(left_eye), np.array(point_3rd))
|
||||
b = distance.findEuclideanDistance(np.array(right_eye), np.array(point_3rd))
|
||||
c = distance.findEuclideanDistance(np.array(right_eye), np.array(left_eye))
|
||||
|
||||
#-----------------------
|
||||
|
||||
#apply cosine rule
|
||||
|
||||
if b != 0 and c != 0: #this multiplication causes division by zero in cos_a calculation
|
||||
|
||||
cos_a = (b*b + c*c - a*a)/(2*b*c)
|
||||
angle = np.arccos(cos_a) #angle in radian
|
||||
angle = (angle * 180) / math.pi #radian to degree
|
||||
|
||||
#-----------------------
|
||||
#rotate base image
|
||||
|
||||
if direction == -1:
|
||||
angle = 90 - angle
|
||||
|
||||
img = Image.fromarray(img)
|
||||
img = np.array(img.rotate(direction * angle))
|
||||
|
||||
#-----------------------
|
||||
|
||||
return img #return img anyway
|
||||
|
||||
def align_face(img, detector_backend = 'opencv'):
|
||||
|
||||
home = str(Path.home())
|
||||
|
||||
if (detector_backend == 'opencv') or (detector_backend == 'ssd'):
|
||||
|
||||
detected_face_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #eye detector expects gray scale image
|
||||
|
||||
eyes = eye_detector.detectMultiScale(detected_face_gray)
|
||||
|
||||
if len(eyes) >= 2:
|
||||
|
||||
#find the largest 2 eye
|
||||
|
||||
base_eyes = eyes[:, 2]
|
||||
|
||||
items = []
|
||||
for i in range(0, len(base_eyes)):
|
||||
item = (base_eyes[i], i)
|
||||
items.append(item)
|
||||
|
||||
df = pd.DataFrame(items, columns = ["length", "idx"]).sort_values(by=['length'], ascending=False)
|
||||
|
||||
eyes = eyes[df.idx.values[0:2]] #eyes variable stores the largest 2 eye
|
||||
|
||||
#-----------------------
|
||||
#decide left and right eye
|
||||
|
||||
eye_1 = eyes[0]; eye_2 = eyes[1]
|
||||
|
||||
if eye_1[0] < eye_2[0]:
|
||||
left_eye = eye_1; right_eye = eye_2
|
||||
if detected_face == None:
|
||||
if enforce_detection != True:
|
||||
return img, img_region
|
||||
else:
|
||||
left_eye = eye_2; right_eye = eye_1
|
||||
|
||||
#-----------------------
|
||||
#find center of eyes
|
||||
|
||||
left_eye = (int(left_eye[0] + (left_eye[2] / 2)), int(left_eye[1] + (left_eye[3] / 2)))
|
||||
right_eye = (int(right_eye[0] + (right_eye[2]/2)), int(right_eye[1] + (right_eye[3]/2)))
|
||||
|
||||
img = alignment_procedure(img, left_eye, right_eye)
|
||||
|
||||
return img #return img anyway
|
||||
|
||||
elif detector_backend == 'dlib':
|
||||
|
||||
import dlib #this is not a must dependency in deepface
|
||||
|
||||
detections = face_detector(img, 1)
|
||||
|
||||
if len(detections) > 0:
|
||||
detected_face = detections[0]
|
||||
img_shape = sp(img, detected_face)
|
||||
img = dlib.get_face_chip(img, img_shape, size = img.shape[0])
|
||||
|
||||
return img #return img anyway
|
||||
|
||||
elif detector_backend == 'mtcnn':
|
||||
|
||||
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) #mtcnn expects RGB but OpenCV read BGR
|
||||
detections = face_detector.detect_faces(img_rgb)
|
||||
|
||||
if len(detections) > 0:
|
||||
detection = detections[0]
|
||||
|
||||
keypoints = detection["keypoints"]
|
||||
left_eye = keypoints["left_eye"]
|
||||
right_eye = keypoints["right_eye"]
|
||||
|
||||
img = alignment_procedure(img, left_eye, right_eye)
|
||||
|
||||
return img #return img anyway
|
||||
elif detector_backend == 'retinaface':
|
||||
#we used extract_faces function of retinaface. it applies alignment anyway.
|
||||
return img #return img anyway
|
||||
raise ValueError("Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.")
|
||||
|
||||
def preprocess_face(img, target_size=(224, 224), grayscale = False, enforce_detection = True, detector_backend = 'opencv', return_region = False):
|
||||
|
||||
#img_path = copy.copy(img)
|
||||
|
||||
#img might be path, base64 or numpy array. Convert it to numpy whatever it is.
|
||||
img = load_image(img)
|
||||
base_img = img.copy()
|
||||
@ -474,10 +116,7 @@ def preprocess_face(img, target_size=(224, 224), grayscale = False, enforce_dete
|
||||
|
||||
#--------------------------
|
||||
|
||||
if img.shape[0] > 0 and img.shape[1] > 0:
|
||||
img = align_face(img = img, detector_backend = detector_backend)
|
||||
else:
|
||||
|
||||
if img.shape[0] == 0 or img.shape[1] == 0:
|
||||
if enforce_detection == True:
|
||||
raise ValueError("Detected face shape is ", img.shape,". Consider to set enforce_detection argument to False.")
|
||||
else: #restore base image
|
||||
|
||||
55
deepface/detectors/DlibWrapper.py
Normal file
55
deepface/detectors/DlibWrapper.py
Normal file
@ -0,0 +1,55 @@
|
||||
from pathlib import Path
|
||||
import gdown
|
||||
import bz2
|
||||
import os
|
||||
|
||||
def build_model():
|
||||
|
||||
home = str(Path.home())
|
||||
|
||||
import dlib #this requirement is not a must that's why imported here
|
||||
|
||||
#check required file exists in the home/.deepface/weights folder
|
||||
if os.path.isfile(home+'/.deepface/weights/shape_predictor_5_face_landmarks.dat') != True:
|
||||
|
||||
print("shape_predictor_5_face_landmarks.dat.bz2 is going to be downloaded")
|
||||
|
||||
url = "http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2"
|
||||
output = home+'/.deepface/weights/'+url.split("/")[-1]
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
zipfile = bz2.BZ2File(output)
|
||||
data = zipfile.read()
|
||||
newfilepath = output[:-4] #discard .bz2 extension
|
||||
open(newfilepath, 'wb').write(data)
|
||||
|
||||
face_detector = dlib.get_frontal_face_detector()
|
||||
return face_detector
|
||||
|
||||
def detect_face(face_detector, img):
|
||||
|
||||
import dlib #this requirement is not a must that's why imported here
|
||||
|
||||
home = str(Path.home())
|
||||
|
||||
sp = dlib.shape_predictor(home+"/.deepface/weights/shape_predictor_5_face_landmarks.dat")
|
||||
|
||||
detected_face = None
|
||||
img_region = [0, 0, img.shape[0], img.shape[1]]
|
||||
|
||||
detections = face_detector(img, 1)
|
||||
|
||||
if len(detections) > 0:
|
||||
|
||||
for idx, d in enumerate(detections):
|
||||
left = d.left(); right = d.right()
|
||||
top = d.top(); bottom = d.bottom()
|
||||
detected_face = img[top:bottom, left:right]
|
||||
img_region = [left, top, right - left, bottom - top]
|
||||
break #get the first one
|
||||
|
||||
img_shape = sp(img, detections[0])
|
||||
detected_face = dlib.get_face_chip(img, img_shape, size = detected_face.shape[0])
|
||||
|
||||
return detected_face, img_region
|
||||
96
deepface/detectors/FaceDetector.py
Normal file
96
deepface/detectors/FaceDetector.py
Normal file
@ -0,0 +1,96 @@
|
||||
from deepface.detectors import OpenCvWrapper, SsdWrapper, DlibWrapper, MtcnnWrapper, RetinaFaceWrapper
|
||||
from PIL import Image
|
||||
import math
|
||||
import numpy as np
|
||||
from deepface.commons import distance
|
||||
|
||||
def build_model(detector_backend):
|
||||
|
||||
if detector_backend == 'opencv':
|
||||
face_detector = OpenCvWrapper.build_model()
|
||||
|
||||
elif detector_backend == 'ssd':
|
||||
face_detector = SsdWrapper.build_model()
|
||||
|
||||
elif detector_backend == 'dlib':
|
||||
face_detector = DlibWrapper.build_model()
|
||||
|
||||
elif detector_backend == 'mtcnn':
|
||||
face_detector = MtcnnWrapper.build_model()
|
||||
|
||||
elif detector_backend == 'retinaface':
|
||||
face_detector = RetinaFaceWrapper.build_model()
|
||||
|
||||
else:
|
||||
raise ValueError("invalid detector_backend passed - " + detector_backend)
|
||||
|
||||
return face_detector
|
||||
|
||||
def detect_face(face_detector, detector_backend, img):
|
||||
|
||||
if detector_backend == 'opencv':
|
||||
face, region = OpenCvWrapper.detect_face(face_detector, img)
|
||||
|
||||
elif detector_backend == 'ssd':
|
||||
face, region = SsdWrapper.detect_face(face_detector, img)
|
||||
|
||||
elif detector_backend == 'dlib':
|
||||
face, region = DlibWrapper.detect_face(face_detector, img)
|
||||
|
||||
elif detector_backend == 'mtcnn':
|
||||
face, region = MtcnnWrapper.detect_face(face_detector, img)
|
||||
|
||||
elif detector_backend == 'retinaface':
|
||||
face, region = RetinaFaceWrapper.detect_face(face_detector, img)
|
||||
|
||||
else:
|
||||
raise ValueError("invalid detector_backend passed - " + detector_backend)
|
||||
|
||||
return face, region
|
||||
|
||||
def alignment_procedure(img, left_eye, right_eye):
|
||||
|
||||
#this function aligns given face in img based on left and right eye coordinates
|
||||
|
||||
left_eye_x, left_eye_y = left_eye
|
||||
right_eye_x, right_eye_y = right_eye
|
||||
|
||||
#-----------------------
|
||||
#find rotation direction
|
||||
|
||||
if left_eye_y > right_eye_y:
|
||||
point_3rd = (right_eye_x, left_eye_y)
|
||||
direction = -1 #rotate same direction to clock
|
||||
else:
|
||||
point_3rd = (left_eye_x, right_eye_y)
|
||||
direction = 1 #rotate inverse direction of clock
|
||||
|
||||
#-----------------------
|
||||
#find length of triangle edges
|
||||
|
||||
a = distance.findEuclideanDistance(np.array(left_eye), np.array(point_3rd))
|
||||
b = distance.findEuclideanDistance(np.array(right_eye), np.array(point_3rd))
|
||||
c = distance.findEuclideanDistance(np.array(right_eye), np.array(left_eye))
|
||||
|
||||
#-----------------------
|
||||
|
||||
#apply cosine rule
|
||||
|
||||
if b != 0 and c != 0: #this multiplication causes division by zero in cos_a calculation
|
||||
|
||||
cos_a = (b*b + c*c - a*a)/(2*b*c)
|
||||
angle = np.arccos(cos_a) #angle in radian
|
||||
angle = (angle * 180) / math.pi #radian to degree
|
||||
|
||||
#-----------------------
|
||||
#rotate base image
|
||||
|
||||
if direction == -1:
|
||||
angle = 90 - angle
|
||||
|
||||
img = Image.fromarray(img)
|
||||
img = np.array(img.rotate(direction * angle))
|
||||
|
||||
#-----------------------
|
||||
|
||||
return img #return img anyway
|
||||
29
deepface/detectors/MtcnnWrapper.py
Normal file
29
deepface/detectors/MtcnnWrapper.py
Normal file
@ -0,0 +1,29 @@
|
||||
from mtcnn import MTCNN
|
||||
import cv2
|
||||
from deepface.detectors import FaceDetector
|
||||
|
||||
def build_model():
|
||||
face_detector = MTCNN()
|
||||
return face_detector
|
||||
|
||||
def detect_face(face_detector, img):
|
||||
|
||||
detected_face = None
|
||||
img_region = [0, 0, img.shape[0], img.shape[1]]
|
||||
|
||||
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) #mtcnn expects RGB but OpenCV read BGR
|
||||
detections = face_detector.detect_faces(img_rgb)
|
||||
|
||||
if len(detections) > 0:
|
||||
detection = detections[0]
|
||||
x, y, w, h = detection["box"]
|
||||
detected_face = img[int(y):int(y+h), int(x):int(x+w)]
|
||||
img_region = [x, y, w, h]
|
||||
|
||||
keypoints = detection["keypoints"]
|
||||
left_eye = keypoints["left_eye"]
|
||||
right_eye = keypoints["right_eye"]
|
||||
|
||||
detected_face = FaceDetector.alignment_procedure(detected_face, left_eye, right_eye)
|
||||
|
||||
return detected_face, img_region
|
||||
97
deepface/detectors/OpenCvWrapper.py
Normal file
97
deepface/detectors/OpenCvWrapper.py
Normal file
@ -0,0 +1,97 @@
|
||||
import cv2
|
||||
import os
|
||||
import pandas as pd
|
||||
from deepface.detectors import FaceDetector
|
||||
|
||||
def build_model(model_name = 'haarcascade'):
|
||||
opencv_path = get_opencv_path()
|
||||
|
||||
if model_name == 'haarcascade':
|
||||
|
||||
face_detector_path = opencv_path+"haarcascade_frontalface_default.xml"
|
||||
|
||||
if os.path.isfile(face_detector_path) != True:
|
||||
raise ValueError("Confirm that opencv is installed on your environment! Expected path ",face_detector_path," violated.")
|
||||
|
||||
|
||||
face_detector = cv2.CascadeClassifier(face_detector_path)
|
||||
return face_detector
|
||||
elif model_name == 'haarcascade_eye':
|
||||
eye_detector_path = opencv_path+"haarcascade_eye.xml"
|
||||
|
||||
if os.path.isfile(eye_detector_path) != True:
|
||||
raise ValueError("Confirm that opencv is installed on your environment! Expected path ",eye_detector_path," violated.")
|
||||
|
||||
eye_detector = cv2.CascadeClassifier(eye_detector_path)
|
||||
return eye_detector
|
||||
|
||||
|
||||
def detect_face(face_detector, img):
|
||||
|
||||
detected_face = None
|
||||
img_region = [0, 0, img.shape[0], img.shape[1]]
|
||||
|
||||
faces = []
|
||||
try:
|
||||
faces = face_detector.detectMultiScale(img, 1.3, 5)
|
||||
except:
|
||||
pass
|
||||
|
||||
if len(faces) > 0:
|
||||
x,y,w,h = faces[0] #focus on the 1st face found in the image
|
||||
detected_face = img[int(y):int(y+h), int(x):int(x+w)]
|
||||
|
||||
detected_face = align_face(detected_face)
|
||||
img_region = [x, y, w, h]
|
||||
|
||||
return detected_face, img_region
|
||||
|
||||
def align_face(img):
|
||||
|
||||
eye_detector = build_model(model_name = 'haarcascade_eye')
|
||||
|
||||
detected_face_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #eye detector expects gray scale image
|
||||
|
||||
eyes = eye_detector.detectMultiScale(detected_face_gray)
|
||||
|
||||
if len(eyes) >= 2:
|
||||
|
||||
#find the largest 2 eye
|
||||
|
||||
base_eyes = eyes[:, 2]
|
||||
|
||||
items = []
|
||||
for i in range(0, len(base_eyes)):
|
||||
item = (base_eyes[i], i)
|
||||
items.append(item)
|
||||
|
||||
df = pd.DataFrame(items, columns = ["length", "idx"]).sort_values(by=['length'], ascending=False)
|
||||
|
||||
eyes = eyes[df.idx.values[0:2]] #eyes variable stores the largest 2 eye
|
||||
|
||||
#-----------------------
|
||||
#decide left and right eye
|
||||
|
||||
eye_1 = eyes[0]; eye_2 = eyes[1]
|
||||
|
||||
if eye_1[0] < eye_2[0]:
|
||||
left_eye = eye_1; right_eye = eye_2
|
||||
else:
|
||||
left_eye = eye_2; right_eye = eye_1
|
||||
|
||||
#-----------------------
|
||||
#find center of eyes
|
||||
left_eye = (int(left_eye[0] + (left_eye[2] / 2)), int(left_eye[1] + (left_eye[3] / 2)))
|
||||
right_eye = (int(right_eye[0] + (right_eye[2]/2)), int(right_eye[1] + (right_eye[3]/2)))
|
||||
img = FaceDetector.alignment_procedure(img, left_eye, right_eye)
|
||||
return img #return img anyway
|
||||
|
||||
def get_opencv_path():
|
||||
opencv_home = cv2.__file__
|
||||
folders = opencv_home.split(os.path.sep)[0:-1]
|
||||
|
||||
path = folders[0]
|
||||
for folder in folders[1:]:
|
||||
path = path + "/" + folder
|
||||
|
||||
return path+"/data/"
|
||||
20
deepface/detectors/RetinaFaceWrapper.py
Normal file
20
deepface/detectors/RetinaFaceWrapper.py
Normal file
@ -0,0 +1,20 @@
|
||||
from retinaface import RetinaFace
|
||||
import cv2
|
||||
|
||||
def build_model():
|
||||
face_detector = RetinaFace.build_model()
|
||||
return face_detector
|
||||
|
||||
def detect_face(face_detector, img):
|
||||
|
||||
face = None
|
||||
img_region = [0, 0, img.shape[0], img.shape[1]]
|
||||
|
||||
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) #retinaface expects RGB but OpenCV read BGR
|
||||
|
||||
faces = RetinaFace.extract_faces(img_rgb, align = True)
|
||||
|
||||
if len(faces) > 0:
|
||||
face = faces[0][:, :, ::-1]
|
||||
|
||||
return face, img_region
|
||||
92
deepface/detectors/SsdWrapper.py
Normal file
92
deepface/detectors/SsdWrapper.py
Normal file
@ -0,0 +1,92 @@
|
||||
import gdown
|
||||
from pathlib import Path
|
||||
import os
|
||||
import cv2
|
||||
import pandas as pd
|
||||
|
||||
from deepface.detectors import OpenCvWrapper
|
||||
|
||||
def build_model():
|
||||
|
||||
home = str(Path.home())
|
||||
|
||||
#model structure
|
||||
if os.path.isfile(home+'/.deepface/weights/deploy.prototxt') != True:
|
||||
|
||||
print("deploy.prototxt will be downloaded...")
|
||||
|
||||
url = "https://github.com/opencv/opencv/raw/3.4.0/samples/dnn/face_detector/deploy.prototxt"
|
||||
|
||||
output = home+'/.deepface/weights/deploy.prototxt'
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
#pre-trained weights
|
||||
if os.path.isfile(home+'/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel') != True:
|
||||
|
||||
print("res10_300x300_ssd_iter_140000.caffemodel will be downloaded...")
|
||||
|
||||
url = "https://github.com/opencv/opencv_3rdparty/raw/dnn_samples_face_detector_20170830/res10_300x300_ssd_iter_140000.caffemodel"
|
||||
|
||||
output = home+'/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel'
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
face_detector = cv2.dnn.readNetFromCaffe(
|
||||
home+"/.deepface/weights/deploy.prototxt",
|
||||
home+"/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel"
|
||||
)
|
||||
|
||||
return face_detector
|
||||
|
||||
def detect_face(face_detector, img):
|
||||
|
||||
detected_face = None
|
||||
img_region = [0, 0, img.shape[0], img.shape[1]]
|
||||
|
||||
ssd_labels = ["img_id", "is_face", "confidence", "left", "top", "right", "bottom"]
|
||||
|
||||
target_size = (300, 300)
|
||||
|
||||
base_img = img.copy() #we will restore base_img to img later
|
||||
|
||||
original_size = img.shape
|
||||
|
||||
img = cv2.resize(img, target_size)
|
||||
|
||||
aspect_ratio_x = (original_size[1] / target_size[1])
|
||||
aspect_ratio_y = (original_size[0] / target_size[0])
|
||||
|
||||
imageBlob = cv2.dnn.blobFromImage(image = img)
|
||||
|
||||
face_detector.setInput(imageBlob)
|
||||
detections = face_detector.forward()
|
||||
|
||||
detections_df = pd.DataFrame(detections[0][0], columns = ssd_labels)
|
||||
|
||||
detections_df = detections_df[detections_df['is_face'] == 1] #0: background, 1: face
|
||||
detections_df = detections_df[detections_df['confidence'] >= 0.90]
|
||||
|
||||
detections_df['left'] = (detections_df['left'] * 300).astype(int)
|
||||
detections_df['bottom'] = (detections_df['bottom'] * 300).astype(int)
|
||||
detections_df['right'] = (detections_df['right'] * 300).astype(int)
|
||||
detections_df['top'] = (detections_df['top'] * 300).astype(int)
|
||||
|
||||
if detections_df.shape[0] > 0:
|
||||
|
||||
#TODO: sort detections_df
|
||||
|
||||
#get the first face in the image
|
||||
instance = detections_df.iloc[0]
|
||||
|
||||
left = instance["left"]
|
||||
right = instance["right"]
|
||||
bottom = instance["bottom"]
|
||||
top = instance["top"]
|
||||
|
||||
detected_face = base_img[int(top*aspect_ratio_y):int(bottom*aspect_ratio_y), int(left*aspect_ratio_x):int(right*aspect_ratio_x)]
|
||||
img_region = [int(left*aspect_ratio_x), int(top*aspect_ratio_y), int(right*aspect_ratio_x) - int(left*aspect_ratio_x), int(bottom*aspect_ratio_y) - int(top*aspect_ratio_y)]
|
||||
|
||||
detected_face = OpenCvWrapper.align_face(detected_face)
|
||||
|
||||
return detected_face, img_region
|
||||
@ -166,7 +166,8 @@ dataset = [
|
||||
['dataset/img6.jpg', 'dataset/img9.jpg', False],
|
||||
]
|
||||
|
||||
models = ['VGG-Face', 'Facenet', 'OpenFace', 'DeepFace', 'DeepID', 'Dlib', 'ArcFace']
|
||||
#models = ['VGG-Face', 'Facenet', 'OpenFace', 'DeepFace', 'DeepID', 'Dlib', 'ArcFace']
|
||||
models = ['VGG-Face', 'Facenet', 'Dlib', 'ArcFace'] #those are robust models
|
||||
metrics = ['cosine', 'euclidean', 'euclidean_l2']
|
||||
|
||||
passed_tests = 0; test_cases = 0
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user