Segmentation and face detection
Previously, you learned how to make processes more computationally efficient with unsupervised superpixel segmentation. In this exercise, you'll do just that!
Using the slic() function for segmentation, pre-process the image before passing it to the face detector.
profile_image.The Cascade class, the slic() function from segmentation module, and the show_detected_face() function for visualization have already been imported. The detector is already initialized and ready to use as detector.
This exercise is part of the course
Image Processing in Python
Exercise instructions
- Apply superpixel segmentation and obtain the segments a.k.a. labels using
slic(). - Obtain the segmented image using
label2rgb(), passing thesegmentsandprofile_image. - Detect the faces, using the detector with multi scale method.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Obtain the segmentation with default 100 regions
segments = ____
# Obtain segmented image using label2rgb
segmented_image = ____(____, ____, kind='avg')
# Detect the faces with multi scale method
detected = detector.____(img=____,
scale_factor=1.2,
step_ratio=1,
min_size=(10, 10), max_size=(1000, 1000))
# Show the detected faces
show_detected_face(segmented_image, detected)