<![CDATA[The implementation of computer vision in educational assistance verification systems is frequently hindered by high storage requirements and heavy server bandwidth consumption. Despite this, empirical research mapping the tolerance threshold of image degradation against object detection reliability in this domain remains limited. This study aims to evaluate the impact of JPEG compression and resolution reduction on the performance of the YOLOv11 model in identifying residential physical components, specifically roofs, walls, and floors. We conducted evaluations using various JPEG quality scenarios and image resolution adjustments. The experimental results demonstrate that YOLOv11 exhibits high robustness to compression. At a 75% quality level, file size was reduced by up to 70.6% while maintaining stable performance, achieving a precision of 0.7605, recall of 0.6651, mAP50 of 0.7341, and an inference time of 8.80 milliseconds. Regarding the resolution experiments, a 480-pixel dimension provided the most optimal outcome, yielding a precision of 0.7309, recall of 0.6711, mAP50 of 0.7333, and an inference time of 3.60 milliseconds. Conversely, extreme resolution reduction triggered a significant drop in accuracy. These findings confirm that the YOLOv11 architecture is more tolerant of compression quality than it is of resolution scaling. We recommend a 75% JPEG compression or a 480-pixel resolution as a standard operational baseline for efficient and accurate residential verification.]]>
Copyrights © 2026
