Efficient Method of Detecting Globally Blurry or Sharp Images

Abstract

In this paper we present a simple and efficient method for detecting the blurriness in the pictures. Recently, many digital cameras are equipped with auto-focusing functions to help the users take well-focused pictures. However, digital images can be degraded by limited contrast, inappropriate exposure, imperfection of auto-focusing or motion compensating devices, limited knowledge of amateur photographers, and so on. In order to detect blurry images for deleting them or making them go through an enhancement process automatically, a reliable measure of image degradation is needed. This paper presents a blurriness/sharpness detection algorithm based on the prediction-error variance, and demonstrates its feasibility by using extensive experiments. This method is fast, easy to implement and accurate. Regardless of the detection accuracy, the proposed method in this paper is not demanding on computation time.