Perceptual Quality Assessment of Smartphone Photography

As smartphones become people’s primary cameras to take photos, the quality of their cameras and the associated computational photography modules has become a de facto standard in evaluating and ranking smartphones in the consumer market. We conduct so far the most comprehensive study of perceptual quality assessment of smartphone photography. We introduce the Smartphone Photography Attribute and Quality (SPAQ) database, consisting of 11,125 pictures taken by 66 smartphones, where each image is attached with so far the richest annotations. Specifically, we collect a series of human opinions for each image, including image quality, image attributes (brightness, colorfulness, contrast, noisiness, and sharpness), and scene category labels (animal, cityscape, human, indoor scene, landscape, night scene, plant, still life, and others) in a well-controlled laboratory environment. The exchangeable image file format (EXIF) data for all images are also recorded to aid deeper analysis. We also make the first attempts using the database to train blind image quality assessment (BIQA) models constructed by baseline and multi-task deep neural networks. The results provide useful insights on how EXIF data, image attributes and high-level semantics interact with image quality, how next-generation BIQA models can be designed, and how better computational photography systems can be optimized on mobile devices. The database along with the proposed BIQA models are available at https://github.com/h4nwei/SPAQ.

1. Introduction

Perceptual image quality assessment (IQA) aims to quantify human perception of image quality. IQA methods can be broadly classified into two categories: subjective and objective IQA [35]. Although time-consuming and expensive, subjective IQA offers the most reliable way of evaluating image quality through psychophysical experiments [30]. Objective IQA, on the other hand, attempts to create computational models that are capable of automatically predicting subjective image quality [3]. In the past decades, there have been a significant number of studies on both directions [1], [12], [17], most of which focus on synthetic distortions, with the assumption that the original undistorted images exist and can be used as reference [37].