The aim of this course is to provide students with a comprehensive and robust foundation in digital image processing and computer vision, specifically tailored to applications in optics, optometry, and ophthalmology.

To achieve this, the course is structured across five core dimensions:

Knowledge and understanding: Students will acquire a fundamental understanding of physical and mathematical models of image formation, including the pin-hole model, spatial/intensity sampling, and the optical or sensor-driven defects inherent to digital cameras. They will grasp the principles underlying image processing, local feature detection, segmentation, and point-based stereometry.

Applying knowledge and understanding: Students will learn to apply point operators, spatial filtering, and denoising algorithms to digital images. Critically, they will apply these computational concepts to calibrate projection models and execute basic triangulation and stereo-matching tasks relevant to optical diagnostics.

Making judgments: Students will develop the capacity to critically evaluate digital image quality, diagnosing whether artifacts are caused by optics or sensors. They will exercise judgment in selecting the appropriate filtering, registration, or segmentation algorithms required to process complex ophthalmic and retinal imagery.

Communication skills: Students will become proficient in communicating technical computer vision concepts, algorithm limitations, and image analysis results clearly to both engineering specialists and fellow eye-care professionals or clinicians.

Learning skills: Students will develop the autonomous learning skills necessary to independently navigate, evaluate, and adopt emerging digital imaging software and advanced computer vision technologies in their future clinical optometric practice or ophthalmic research.