Potential of Deep Features for Opinion-Unaware, Distortion-Unaware, No-Reference Image Quality Assessment

Abstract

Image Quality Assessment algorithms predict a quality score for a pristine or distorted input image, such that it correlates with human opinion. Traditional methods required a non-distorted "reference" version of the input image to compare with, in order to predict this score. However, recent "No-reference" methods circumvent this requirement by modelling the distribution of clean image features, thereby making them more suitable for practical use. However, majority of such methods either use hand-crafted features or require training on human opinion scores (supervised learning), which are difficult to obtain and standardise. We explore the possibility of using deep features instead, particularly, the encoded (bottleneck) feature maps of a Convolutional Autoencoder neural network architecture. Also, we do not train the network on subjective scores (unsupervised learning). The primary requirements for an IQA method are monotonic increase in predicted scores with increasing degree of input image distortion, and consistent ranking of images with the same distortion type and content, but different distortion levels. Quantitative experiments using the Pearson, Kendall and Spearman correlation scores on a diverse set of images show that our proposed method meets the above requirements better than the state-of-art method (which uses hand-crafted features) for three types of distortions: blurring, noise and compression artefacts. This demonstrates the potential for future research in this relatively unexplored sub-area within IQA.

No Reference, Opinion Unaware Image Quality Assessment by Anomaly Detection

“…In view of the fact that our proposed algorithm lacks mainly concerning the PLCC, we are interested in improving such metric simultaneously with the others. To better compare our method with respect to the state of the art, we will take into account more recent approaches of no-reference opinion-unaware image quality assessment like the one by Mukherjee et al [ 44 ]. Finally, to better prove the capability of the proposed method to discriminate good quality images with respect to bad quality ones, a possible alternative to the AUC and AUPR could be to take into account frameworks to stress image quality assessment methods [ 45 ].…”

Implementation of an Award-Winning Invasive Fish Recognition and Separation System

“…The image quality can be used for providing feedback to form a closed-loop system to control the LED illumination and the release of flocculant blocks. A quite powerful image quality assessment method without human input, hand-crafted features, or reference images was reported [13]. In our case, images shown in Figure 3 could be used as references, so a less sophisticated image quality assessment method could be employed for this purpose.…”

Unpaired Underwater Image Enhancement Based on CycleGAN

“…Deep learning-based methods can exploit an end-to-end automatic training mechanism to enhance underwater images, which learns the intrinsic underwater features from a set of underwater images. In [14], they replaced the handcrafted features with the nonparametric deep features for the image representation. Other researchers [15,16] introduced the convolutional neural network (CNN) into underwater image enhancement applications.…”