Returns an array of bounding boxes of human faces in a image :param img: An image (as a numpy array) :param number_of_times_to_upsample: How many times to upsample the image looking for faces. Higher numbers find smaller faces. :param model: Which face detection model to use. "hog"
(img, number_of_times_to_upsample=1, model="hog")
| 87 | |
| 88 | |
| 89 | def _raw_face_locations(img, number_of_times_to_upsample=1, model="hog"): |
| 90 | """ |
| 91 | Returns an array of bounding boxes of human faces in a image |
| 92 | |
| 93 | :param img: An image (as a numpy array) |
| 94 | :param number_of_times_to_upsample: How many times to upsample the image looking for faces. Higher numbers find smaller faces. |
| 95 | :param model: Which face detection model to use. "hog" is less accurate but faster on CPUs. "cnn" is a more accurate |
| 96 | deep-learning model which is GPU/CUDA accelerated (if available). The default is "hog". |
| 97 | :return: A list of dlib 'rect' objects of found face locations |
| 98 | """ |
| 99 | if model == "cnn": |
| 100 | return cnn_face_detector(img, number_of_times_to_upsample) |
| 101 | else: |
| 102 | return face_detector(img, number_of_times_to_upsample) |
| 103 | |
| 104 | |
| 105 | def face_locations(img, number_of_times_to_upsample=1, model="hog"): |
no outgoing calls
no test coverage detected