The scope of this homework is to evaluate qualitatively and quantitatively a face detection method. What you should do: 1. Find (download or capture) 10 images, each containing at least 3 faces "in the wild" (i.e., in unconstrained environments, e.g., outdoors and/or in cluttered surroundings) 2. Use either Viola-Jones method (see HW1) or a Convolutional NN-based method to detect the faces in the 10 images. (Obviously, the ground-truth faces should be more than 30.) 3. Repeat #2 9 more times, increasingly smoothing/blurring the images. 4. Report the confusion matrix = {True Positives, True Negatives, False Positives, False Negatives} for each of the 10 repetitions, with respect to the detections. (If a face is detected, it does not matter how much of the face is left outside the detection or how much of the background is included in the detection.) 5. Plot the corresponding Receiver-Operating Characteristic (ROC) curve.

Need a deep-dive on the concept behind this application? Look no further. Learn more about this topic, computer-science and related others by exploring similar questions and additional content below.