SCT-YOLO: A Dual-Stream Defect Detection Network Utilizing Computational Shape, Texture, and Color Features

Steel surface defect detection is a key component of industrial quality control. Existing deep learning methods mostly rely on single-backbone networks to extract high-level semantic features from raw images, yet fail to explicitly analyze low-level visual features. To overcome the limitations of conventional frameworks, this paper proposes SCT-YOLO, a defect detection model based on a dual-stream collaborative architecture that effectively integrates low-level visual features with high-level semantic information for complementary feature representation. The primary scientific novelty of this work lies in the formalization of a multi-dimensional prior feature-guided learning paradigm, which mathematically bridges explicit hand-crafted physical priors with deep latent representations within this dual-stream architecture, differing from conventional black-box deep feature extraction. On the SD-Saliency-900 dataset, the proposed SCT-YOLO achieves an mAP@0.5 of 88.9%, representing a significant 4.6% improvement over the baseline model YOLOv8n, while maintaining an inference speed of 257.2 FPS with only 5.66 M parameters and 15.2 GFLOPs, fully meeting the real-time deployment requirements of industrial production lines. Visualization analysis demonstrates that the method exhibits more stable detection capability for small defects in complex backgrounds. Meanwhile, experiments on the GC10-DET dataset further verify its excellent generalization performance, providing a reliable technical solution for other industrial defect detection scenarios.