Unsupervised feature learning framework for no-reference image quality assessment

Abstract

In this paper, we present an efficient general-purpose objective no-reference (NR) image quality assessment (IQA) framework based on unsupervised feature learning. The goal is to build a computational model to automatically predict human perceived image quality without a reference image and without knowing the distortion present in the image. Previous approaches for this problem typically rely on hand-crafted features which are carefully designed based on prior knowledge.In contrast, we use raw-image-patches extracted from a set of unlabeled images to learn a dictionary in an unsupervised manner. We use soft-assignment coding with max pooling to obtain effective image representations for quality estimation. The proposed algorithm is very computationally appealing, using raw image patches as local descriptors and using soft-assignment for encoding. Furthermore, unlike previous methods, our unsupervised feature learning strategy enables our method to adapt to different domains. CORNIA (Codebook Representation for No-Reference Image Assessment) is tested on LIVE database and shown to perform statistically better than the full-reference quality measure, structural similarity index (SSIM) and is shown to be comparable to state-of-the-art general purpose NR-IQA algorithms.

No-reference synthetic image quality assessment using scene statistics

“…In contrary, COdebook Representation for No-Reference Image Assessment (CORNIA) [22] uses supervised learning technique to learn a dictionary for different distortions from the raw image patches instead of using a fixed set of features.…”

“…In the paper, on the ESPL Synthetic Image Database, we have evaluated the performance of 11 distortion agnostic NR-IQA algorithms (DESIQUE [4], GM-LOG [17], BRISQUE [3], CORNIA [22], BLIINDS-II [2], CurveletQA [20], DIIVINE [1], BIQI [18], GRNN [19], NIQE [16] and Anisotropy [21]), 5 NR-IQA algorithms (LPCM [23], CPBDM [24], FISH [25], S 3 [26] and JNBM [27]) for blurred and one NR-IQA algorithm (JPEG-NR [28]) for JPEG compressed images. The performances of full-reference IQA (FR-IQA) algorithms like Peak Signal-to-noise Ratio (PSNR) and Multi-scale Structural Similarity Index (MS-SSIM) have also been provided for reference.…”

Image quality assessment using deep convolutional networks

“…Similar to Ref. 40, to examine the transfer performance, we also train the models with the dataset LIVE and test their performance on the dataset TID2008 41 using the common four distortion categories (JP2K, JPEG, Gaussian Noise, and Gaussian Blur) both LIVE and TID2008 contain.…”

“…40). Instead of using a nonlinear mapping to transform the quality measure into a certain range, 40 the models which have been trained on the LIVE dataset are tested directly on the TID2008 dataset. The models which are trained on the LIVE dataset have a discrete image quality labels.…”

A deep learning approach to document image quality assessment

“…The first generalpurpose method seen in the literature is the feature learning method introduced by Ye et al [7], which is an extension of the CORNIA system [8]. This method is based on unsupervised feature learning which can automatically learn discriminant features for different types of document degradations.…”