Reading: DeepSim — Deep Similarity for (Image Quality Assessment)

Using ImageNet Pretrained VGGNet, Outperforms Handcrafted-Feature IQA: MSSIM, FSIM, GMSD & RMSE

Outline

1. IQA Algorithms

Image quality assessment (IQA) algorithms is to precisely and automatically estimate human perceived image quality.

Traditionally, both the features and the mapping function are hand-crafted.
(At that moment, there are not much deep learning approaches.)

DeepSim is FR-IQA using VGGNet.

2. DeepSim: Deep Similarity

VGGNet: Network Architecture

ImageNet pre-trained VGG-16 is used in DeepSim without any further training or fine-tuning.

Flowchart of the Proposed DeepSim Framework

3. Experimental Results

PLCC across all distortions for all databases
Illustration of preprocessed images. (a) Reference image, 512 ×768 pixels; (b) JPEG20 0 0 compressed version of (a), 512 ×768 pixels; (c) Preprocessed version of (a), 224 ×224 pixels; (d) Preprocessed version of (b), 224 ×224 pixels.
Heat maps of the average (left) and weighted average (right) PLCC values across the four databases related to each layer w.r.t different pooling strategies
Weighted average PLCC values, between the quality scores predicted over each layer and MOS/DMOS, across the four databases
Performance of DeepSim w.r.t different pooling strategies
Scatter plots of the quality score, predicted by DeepSim with preprocessing and the average pooling strategy, vs. the MOS/DMOS

--

--

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