HiRes: A Hierarchical Cascaded Method for Resistor Value Identification
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed HiRes, a step-by-step method that can find and read resistor values from normal photos despite tricky conditions like different lighting and angles. Their system uses a mix of object detection, image segmentation, and smart decoding techniques to understand the resistor's colored bands. Tests showed HiRes works better than older methods and even some advanced language-vision models, accurately identifying resistors in real-world images. Their approach is also easier to interpret and more efficient. The authors have shared their code and data for others to use and build upon.
resistor identificationobject detectionsemantic segmentationYOLOv8UNet++EfficientNetE24 resistor seriesmean Average Precision (mAP)mean Intersection over Union (mIoU)resistor color code
Authors
Rama Y. AlHamidi, Aseel A. Mohamed, Mustafa A. Eltayeb, Osama Hasoneh, Mohammad Shaqfeh
Abstract
Accurate identification of resistor values from unconstrained images remains a challenging computer vision task due to variations in lighting, orientation, scale, and background complexity. This paper presents HiRes, a hierarchical cascaded pipeline for end-to-end resistor value identification directly from full-frame images. The approach combines object detection (YOLOv8n), semantic segmentation (UNet++ with EfficientNet-B2), and structured geometric decoding via projection along the resistor axis. To improve robustness, we incorporate geometric filtering, gap-preserving band separation, and validation against the E24 resistor series. Experiments across diverse real-world images show that HiRes achieves a detection mAP50 of 0.9906, a segmentation mIoU of 0.8444, and an end-to-end identification accuracy of 85.8% (95% CI: 78.0-91.9%), outperforming the publicly available classical baseline, CVResist, which fails to generalize beyond controlled conditions. In addition, our architecture outperforms state-of-the-art MLLMs on our challenging test set, offering a lower cost, high efficiency, and an interpretable alternative method. These results demonstrate the effectiveness of integrating learned visual representations with structured reasoning for robust resistor interpretation. Code and dataset are available at https://github.com/HiRes491/HiRes.