我们从Python开源项目中，提取了以下23个代码示例，用于说明如何使用dlib.shape_predictor()。
def __init__(self, num_jitters=10, dnn=False, det_threshold=0.0, upsample=0): import_dlib() ppath = os.path.join(os.environ['HOME'], '.tdesc') if not dnn: self.detector = dlib.get_frontal_face_detector() else: detpath = os.path.join(ppath, 'models/dlib/mmod_human_face_detector.dat') self.detector = dlib.face_detection_model_v1(detpath) shapepath = os.path.join(ppath, 'models/dlib/shape_predictor_68_face_landmarks.dat') self.sp = dlib.shape_predictor(shapepath) facepath = os.path.join(ppath, 'models/dlib/dlib_face_recognition_resnet_model_v1.dat') self.facerec = dlib.face_recognition_model_v1(facepath) self.num_jitters = num_jitters self.dnn = dnn self.det_threshold = det_threshold self.upsample = upsample print >> sys.stderr, 'DlibFaceWorker: ready (dnn=%d | num_jitters=%d)' % (int(dnn), int(num_jitters))
def __init__(self, facePredictor): """ Instantiate an 'AlignDlib' object. :param facePredictor: The path to dlib's facial landmark detector :type facePredictor: str :param OPENCV_Detector: The path to opencv's HaarCasscade :type OPENCV_Detector: str :param HOG_Detector: The path to dlib's HGO face detection model :type HOG_Detector: str """ assert facePredictor is not None self.OPENCV_Detector = cv2.CascadeClassifier("/home/pi/opencv-3.1.0/data/haarcascades/haarcascade_frontalface_default.xml") self.HOG_Detector = dlib.get_frontal_face_detector() self.predictor = dlib.shape_predictor(facePredictor)
def get_facial_landmarks(img): # No need to upsample rects = face_detector(img, 0) if len(rects) == 0: print "No faces" return None rect = rects[0] shape = shape_predictor(img, rect) return np.matrix([[pt.x, pt.y] for pt in shape.parts()]), rect
def __init__(self, facePredictor): """ Instantiate an 'AlignDlib' object. :param facePredictor: The path to dlib's :type facePredictor: str """ assert facePredictor is not None #pylint: disable=no-member self.detector = dlib.get_frontal_face_detector() self.predictor = dlib.shape_predictor(facePredictor)
def load_trained_models(): """ Helper function to load DLIB's models. """ if not os.path.isfile("data/dlib_data/shape_predictor_68_face_landmarks.dat"): return global FACE_DETECTOR_MODEL, LANDMARKS_PREDICTOR FACE_DETECTOR_MODEL = dlib.get_frontal_face_detector() LANDMARKS_PREDICTOR = dlib.shape_predictor("data/dlib_data/shape_predictor_68_face_landmarks.dat")
def load_trained_models(): if not os.path.isfile("data/dlib_data/shape_predictor_68_face_landmarks.dat"): return global FACE_DETECTOR_MODEL, LANDMARKS_PREDICTOR FACE_DETECTOR_MODEL = dlib.get_frontal_face_detector() LANDMARKS_PREDICTOR = dlib.shape_predictor("data/dlib_data/shape_predictor_68_face_landmarks.dat")
def __init__(self,heads_list=[],predictor_path="./data/shape_predictor_68_face_landmarks.dat"): ''' head_list: ????????????????????????????????????????? ????????????????????????? predictor_path: dlib????? ''' #?????? self.PREDICTOR_PATH = predictor_path self.FACE_POINTS = list(range(17, 68)) self.MOUTH_POINTS = list(range(48, 61)) self.RIGHT_BROW_POINTS = list(range(17, 22)) self.LEFT_BROW_POINTS = list(range(22, 27)) self.RIGHT_EYE_POINTS = list(range(36, 42)) self.LEFT_EYE_POINTS = list(range(42, 48)) self.NOSE_POINTS = list(range(27, 35)) self.JAW_POINTS = list(range(0, 17)) # ???????? self.ALIGN_POINTS = (self.LEFT_BROW_POINTS + self.RIGHT_EYE_POINTS + self.LEFT_EYE_POINTS + self.RIGHT_BROW_POINTS + self.NOSE_POINTS + self.MOUTH_POINTS) # ??????????????????????????????????????????? self.OVERLAY_POINTS = [self.LEFT_EYE_POINTS + self.RIGHT_EYE_POINTS + self.LEFT_BROW_POINTS + self.RIGHT_BROW_POINTS, self.NOSE_POINTS + self.MOUTH_POINTS] # ?????? self.COLOUR_CORRECT_BLUR_FRAC = 0.6 #?????????????dlib self.detector = dlib.get_frontal_face_detector() self.predictor = dlib.shape_predictor(self.PREDICTOR_PATH) #???? self.heads={} if heads_list: self.load_heads(heads_list)
def __init__(self, facePredictor = None): """Initialize the dlib-based alignment.""" self.detector = dlib.get_frontal_face_detector() if facePredictor != None: self.predictor = dlib.shape_predictor(facePredictor) else: self.predictor = None
def debug_face_landmark(file, output=False, output_name='output'): detector = dlib.get_frontal_face_detector() predictor = dlib.shape_predictor(dat_face_landmark) image = cv2.imread(file) image = imutils.resize(image, width=500) gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) img_size = gray.shape faces = detector(gray, 1) for (i, itr_face) in enumerate(faces): shape = predictor(gray, itr_face) shape = shape_to_np(shape) # convert dlib's rectangle to a OpenCV-style bounding box # [i.e., (x, y, w, h)], then draw the face bounding box (x, y, w, h) = rect_to_bb(itr_face, img_size, file) #print "landmark: ({:d}, {:d}) ({:d}, {:d})".format(x, y, w, h) cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2) # show the face number cv2.putText(image, "Face #{}".format(i + 1), (x - 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2) # loop over the (x, y)-coordinates for the facial landmarks # and draw them on the image for (x, y) in shape: cv2.circle(image, (x, y), 1, (0, 0, 255), -1) # show the output image with the face detections + facial landmarks cv2.imshow(file, image) cv2.waitKey(0) if output: cv2.imwrite("../" + str(output_name + 1) + '.jpg', image) cv2.destroyAllWindows()
def __init__(self,option_type,path): self.face_cascade = cv2.CascadeClassifier("cascade/haarcascade_frontalface_default.xml") self.eye_cascade = cv2.CascadeClassifier("cascade/haarcascade_eye.xml") self.smile_cascade = cv2.CascadeClassifier("cascade/haarcascade_smile.xml") self.shape_predictor = "cascade/shape_predictor_68_face_landmarks.dat" self.facedetect = False self.functioncall = option_type self.sourcepath = path self.image_path = None self.video_path = None self.webcam_path = None self.main_function()
def dlib_function(self,image): detector = dlib.get_frontal_face_detector() predictor = dlib.shape_predictor(self.shape_predictor) image = imutils.resize(image, width=500) gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) rects = detector(image, 1) for (i, rect) in enumerate(rects): shape = predictor(gray, rect) shape = face_utils.shape_to_np(shape) for (x, y) in shape: cv2.circle(image, (x, y), 1, (0, 0, 255), -1) return image
def __init__(self, predictor_path): self.detector = dlib.get_frontal_face_detector() self.predictor = dlib.shape_predictor(str(predictor_path))
def __init__(self): self.PREDICTOR_PATH = "../shape_predictor_68_face_landmarks.dat" self.MOUTH_POINTS = [list(range(48, 61))] self.detector = dlib.get_frontal_face_detector() self.predictor = dlib.shape_predictor(self.PREDICTOR_PATH)
def __init__(self): self.PREDICTOR_PATH = "shape_predictor_68_face_landmarks.dat" MOUTH_POINTS = list(range(48, 61)) self.OVERLAY_POINTS = [MOUTH_POINTS] self.detector = dlib.get_frontal_face_detector() self.predictor = dlib.shape_predictor(self.PREDICTOR_PATH)
def encode(detector, shape_predictor, model, image, win=None): """Encodes faces from a single image into a 128 dim descriptor. Args: detector: dlib face detector object shape_predictor: dlib shape predictor object model: dlib convnet model image: image as numpy array win: dlib window object for vizualization if VIZ flag == 1 Returns: list of descriptors (np array) for each face detected in image """ # dlib comments: # Ask the detector to find the bounding boxes of each face. The 1 in the # second argument indicates that we should upsample the image 1 time. This # will make everything bigger and allow us to detect more faces. dets = detector(img, 1) print("Number of faces detected: {}".format(len(dets))) descriptors = [] for k, d in enumerate(dets): print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format( k, d.left(), d.top(), d.right(), d.bottom())) # Get the landmarks/parts for the face in box d. shape = sp(img, d) # Draw the face landmarks on the screen so we can see what face is currently being processed. if win is not None: win.clear_overlay() win.set_image(img) win.add_overlay(d) win.add_overlay(shape) dlib.hit_enter_to_continue() # Compute the 128D vector that describes the face in img identified by shape face_descriptor = facerec.compute_face_descriptor(img, shape) descriptors.append(np.asarray(list(face_descriptor))) return descriptors
def __init__(self, dlib_predictor_path, face_template_path): self.predictor = dlib.shape_predictor(dlib_predictor_path) self.face_template = np.load(face_template_path)
def face_extraction(path): path_str = path[:-1] if path.endswith('/') else path output_dir = path_str + '_faces' if not os.path.isdir(output_dir): os.makedirs(output_dir) detector = dlib.get_frontal_face_detector() predictor = dlib.shape_predictor(dat_face_landmark) face_cascade = cv2.CascadeClassifier(xml_face_classifier) undetectLst = list() numfile = get_dataInfo(path_str) not_detected = 0 itr = 0 for itr_file in os.listdir(path_str): if itr_file.endswith('.jpg'): file = "{:s}/{:s}".format(path_str, itr_file) image = cv2.imread(file) image = imutils.resize(image, width=500) bFace, faces = facial_landmark_detection(image, detector, predictor, file) if not bFace: bFace, faces = face_detect_classifier(image, face_cascade) if not bFace: print file undetectLst.append(file) not_detected += 1 image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) cv2.imwrite("{:s}/{:s}".format(output_dir, itr_file), image) continue x, y, w, h = faces crop_img = image[y:y + h, x:x + w] crop_img = cv2.cvtColor(crop_img, cv2.COLOR_BGR2GRAY) cv2.imwrite("{:s}/{:s}".format(output_dir, itr_file), crop_img) itr += 1 else: continue total = itr + not_detected print "{:s}: {:4d} of {:4d} file missed detected, detect rate {:2.2f}%"\ .format(path_str, not_detected, total, 100.0 * itr / total) return undetectLst, total
def main_func(): img_path='snap.jpg' # THE PATH OF THE IMAGE TO BE ANALYZED font=cv2.FONT_HERSHEY_DUPLEX emotions = ["anger", "happy", "sadness"] #Emotion list clahe=cv2.createCLAHE(clipLimit=2.0,tileGridSize=(8,8)) # Histogram equalization object face_det=dlib.get_frontal_face_detector() land_pred=dlib.shape_predictor("data/DlibPredictor/shape_predictor_68_face_landmarks.dat") SUPPORT_VECTOR_MACHINE_clf2 = joblib.load('data/Trained_ML_Models/SVM_emo_model_7.pkl') # Loading the SVM model trained earlier in the path mentioned above. pred_data=[] pred_labels=[] a=crop_face(img_path) img=cv2.imread(a) gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) clahe_gray=clahe.apply(gray) landmarks_vec = get_landmarks(clahe_gray,face_det,land_pred) #print(len(landmarks_vec)) #print(landmarks_vec) if landmarks_vec == "error": pass else: pred_data.append(landmarks_vec) np_test_data = np.array(pred_data) a=SUPPORT_VECTOR_MACHINE_clf2.predict(pred_data) #cv2.putText(img,'DETECTED FACIAL EXPRESSION : ',(8,30),font,0.7,(0,0,255),2,cv2.LINE_AA) #l=len('Facial Expression Detected : ') #cv2.putText(img,emotions[a[0]].upper(),(150,60),font,1,(255,0,0),2,cv2.LINE_AA) #cv2.imshow('test_image',img) #print(emotions[a[0]]) cv2.waitKey(0) cv2.destroyAllWindows() return emotions[a[0]]
