Blur Detection for Historical Document Images

FamilySearch captures millions of digital images annually using digital cameras at sites throughout the world. The top image quality problem encountered during this image capture process is blurriness due to an out of focus camera and/or motion during capture. Several automatic measurements of digital image blur exist, but have been found to not be very accurate at correctly classifying blurry images of historical documents. A new blur detection scheme is presented in this paper that leverages the characteristics of historical documents to more effectively classify blurry images. The proposed technique attempts a best fit of edge data to the logistic function, resulting in a growth rate parameter that can be used as a measurement of image blur. Experimental results demonstrate the effectiveness of the proposed measurement at accurately detecting image blur.