Implementation of an image based focusing algorithm for non-mydriatic retinal imaging

Retinal photography is important for the assessment of eye diseases. The task of fine focusing the image is demanding and lack of focus is often the cause of suboptimal photographs. The advent of digital cameras has provided the opportunity to automate the focusing process. In this work, we propose an auto-focus system for non-mydriatic retinal imaging. The core of the system is based on a robust image-based focus measure. The measure is basically a quantification of image anisotropy computed by means of the normalized discrete cosine transform. Additionally, we optimize the autofocusing method by evaluating different focus search strategies. Encouraging experimental results reveal that the method is able to identify the best focus reliably with optimal speed.