Sharp or Blur: a Fast No-reference Quality Metric for Realistic Photos

There is an increasing demand on identifying the sharp and the blur photos from a burst of series or a mass of collection. Subjective assessment on image blurriness takes account of not only pixel variation but also the region of interest and the scene type. It makes measuring image sharpness in line with visual perception very challenging. In this paper, we devise a noreference image sharpness metric, which combines a set of gradient-based features adept in estimating Gaussian blur, out-of-focus blur and motion blur respectively. We propose a datasetadaptive logistic regression to build the metric upon multiple datasets, where over half of the samples are realistic blurry photos. Cross validation confirms that our metric outperforms thestate-of-the-art methods on the datasets with a total of 1577 images. Moreover, our metric is very fast, suitable for parallelization, and has the potential of running on mobile or embedded devices.