Fundus Photograph Defect Repair Algorithm Based on Portable Camera Empty Shot

Fundus photograph is an important basis for ophthalmologists to diagnose retinal diseases. Due to the limitations of the optical system design for portable fundus cameras, there still exist typical image defects leading to low quality images. There are stray light defects such as atomization area, shadow ring, bright spot, central dark hole and so on. Since the camera empty shot in a dark environment can reflect important device-specific characteristics of typical defects, we propose a novel framework to execute image defects repairing by template compensation based on camera empty shots for portable fundus cameras. First, noise reduction is employed from a camera empty shot image. Then, a defect compensation template based on empty shot is generated. For each fundus image, an adjusted ratio is optimized in different defect areas of the customized compensation template. Finally, this template is applied to compensate and repair the stray light defects in order to improve image quality for the target image captured from the same camera. Experimental results show that our proposed method is effective, and it is able to obtain fundus images in better quality.