Chronic wounds pose significant clinical and economic challenges globally, requiring accurate assessment for effective management. Traditional wound measurement methods suffer from subjectivity and inefficiency, while existing AI solutions often lack integration of scale markers crucial for size estimation. This study presents an automated wound segmentation system using YOLOv11 Nano, a unified architecture combining detection and segmentation with integrated scale marker analysis. Leveraging transfer learning on 2760 external images and fine-tuning with the IFMBE Challenge dataset (451 annotated images), our model achieved performance with a wound Dice score of 0.8728 and marker Dice score of 0.9475. The lightweight design demonstrated real time inference at 100 FPS (10 ms/image) on an NVIDIA RTX 3090 GPU – 15 × faster than U-Net architectures. By unifying detection and segmentation in a single efficient framework, this approach enables clinical grade wound measurements critical for personal device users seeking precise, efficient solutions that bridge gaps in automated assessment systems.