[Review] Park CVPR’17 / DHCF / DHDE: Multi-scale Deep and Hand-crafted Features for Defocus Estimation (Blur Detection)

Deep and Hand-Crafted Features Together for Blur Detection


1. Hand-Crafted Features

1.1. DCT Feature

Hand-Crafted Features: Average DCT, DFT, DST features from sharp (dotted) and blurry (solid) patches.

1.2. Gradient Feature

Hand-Crafted Features: Average gradient feature from sharp (dotted) and blurry (solid) patches.

1.3. SVD Feature

Hand-Crafted Features: Average SVD feature from sharp (dotted) and blurry (solid) patches.
Low-rank matrix approximation of an image

2. Deep Feature Using CNN

CNN for Deep Feature
The average activations with sharp, intermediate and blurry patches.

3. Defocus Feature

3.1. Concatenations of All Features

Classification accuracies. Note that the accuracy of a random guess is 9.09%.

3.2. Neural Network Classifier

3.3. Defocus Map

4. Training

Feature scale encoding scheme

5. Experimental Results

Segmentation accuracies (top) and Precision-Recall comparison (bottom)
(a) Input images. (b) Results of [30]. (c) Results of [31]. (d) Results of [32] (Inverted for visualization). (e) Results of [42]. (f) Proposed defocus maps and (g) corresponding binary masks. (h) Ground truth binary masks.
Defocus maps from each feature



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store