Evaluating OCR performance for assistive technology: effects of walking speed, camera placement, and camera type

Optical character recognition (OCR), a process that converts printed or handwritten text into machine-readable form, is widely used in assistive technology for people with blindness and low vision. Yet most evaluations rely on static datasets that do not reflect the challenges of mobile use. This study evaluated how OCR performance changes under static and walking conditions relevant to real-world navigation.

Static tests varied distance from 1-7 metres and viewing angle from 0°-75°. Dynamic tests examined the impact of motion by varying walking speed from 0.8 m/s to 1.8 m/s and compared head-mounted, shoulder-mounted, and handheld positions. We evaluated a smartphone and smart glasses, including the phone's main and ultra-wide cameras, across four OCR engines: Google Vision, PaddleOCR 3.0, EasyOCR, and Tesseract. Dynamic tests used PaddleOCR 3.0. Accuracy was computed at the character level using the Levenshtein ratio against manually defined ground truth.

Recognition accuracy declined with increased walking speed and wider viewing angles. Google Vision achieved the highest overall accuracy, with PaddleOCR close behind as the strongest open-source alternative. Across devices, the phone's main camera achieved the highest accuracy, and a shoulder-mounted placement yielded the highest average among body positions; however, differences among shoulder, head, and hand were not statistically significant.

OCR performance depends on the recognition engine, camera hardware, field of view, device placement, and user motion. OCR systems for navigation should be evaluated under dynamic, mobility-relevant conditions rather than static images alone and designed to balance coverage, recognition accuracy, and practical deployment.