Glaucoma, a disease characterized by increased intraocular pressure (IOP) in the eyes, is the leading cause of preventable blindness worldwide. Accurate measurement of IOP is essential to early diagnosis of glaucoma in order to begin treatment and prevent long-term vision loss. Currently, non-contact tonometry, known as an “air-puff test”, is the most common diagnostic method despite its inaccessibility, discomfort, high cost, and reliance on an expert to operate. In order to improve upon this method, we designed an accurate and less invasive measurement system utilizing a novel depth-mapping neural network and a microcontroller-driven valve system. We applanated eyes with a variable-intensity air puff while imaging the deformation with a single camera. Our neural network then processed the image data and generated a three-dimensional deformation map. We compared our results to accepted tonometry measurements in order to validate the accuracy of our system as an alternative diagnostic device. With a lower pressure puff and simplified imaging setup, we were able to accurately measure IOP, improving existing diagnostic techniques in optometry.