Development of a Low-Cost Portable System for Text-to-Speech Conversion: A Mechanical-Aided Optical Solution for Educational Inclusion

This study presents a low-cost assistive reading system based on a distributed architecture, in which an ESP32-CAM performs image acquisition while an Android application executes the image-processing, optical character recognition, and text-to-speech stages. The processing pipeline includes fixed-threshold binarization, morphological dilation, median filtering, Canny edge detection, and projection-based text segmentation. A key contribution is the mechanical sliding rule-frame, designed to maintain horizontal alignment between the camera and the printed text and to reduce perspective-related errors. The system was evaluated through 36 trials conducted with six participants under Low, Medium, and High Lighting conditions. A repeated-measures analysis showed a statistically significant effect of lighting on the Word Recognition Rate (WRR), with significantly lower performance under Low Lighting than under Medium and High Lighting, while no significant difference was found between Medium and High Lighting. Across all trials, the prototype achieved an overall mean WRR of 76.53%, with a median of 78.75% and a maximum observed WRR of 97.50%. Exploratory participant-level correlations between mean WRR, age, and prior reading experience were not statistically significant and were interpreted cautiously because of the small sample size. These findings provide preliminary evidence of the technical feasibility of combining mechanical alignment with a low-cost portable reading architecture for educational accessibility, while highlighting the need for further validation with larger samples and more diverse operating conditions.