Can use face to array in feature_extractor.py?

[arpsyapathy]

Hello!

In this super repository python script feature_extractor.py make array from all image with Keras.
I want processing faces off 10 peoples. But i want get array from faces of this people.
Is it possible in this? With dlib?
Thank you advance

[Yusuke Matsui]

You should detect faces first, then extract features from the detected face areas

[arpsyapathy]

@matsui528

In this?

    def extract(self, img):  # img is from PIL.Image.open(path) or keras.preprocessing.image.load_img(path)
        img = img.resize((224, 224))  # VGG must take a 224x224 img as an input
        img = img.convert('RGB')  # Make sure img is color
        x = image.img_to_array(img)  # To np.array. Height x Width x Channel. dtype=float32
        x = np.expand_dims(x, axis=0)  # (H, W, C)->(1, H, W, C), where the first elem is the number of img
        x = preprocess_input(x)  # Subtracting avg values for each pixel

[arpsyapathy]

@matsui528
Can I see these coordinates on the photo? Show image using PIL?

[Yusuke Matsui]

You can crop a face region by some face detector, and put it to the above extract function. You might need to convert the data little bit, or you can re-write the extract function so as to accept your data.