Mrs Mina Zohoorian Yazdi, Dr. Mohsen Soryani,
Volume 9, Issue 3 (9-2019)
Abstract
Today most accidents are caused by drivers’ fatigue, drowsiness and losing attention on the road ahead. In this paper, a system is introduced, using RGB-D cameras to automatically identify drowsiness and give warning. In this system two important modules have been utilized simultaneously to identify the state of driver’s mouth and eyes for detecting drowsiness. At first, using the depth information, the mouth area and its state are identified. Then using CNN networks, to predict whether the eyes are open or closed, a semi-VGG architecture is used .The results of yawning and eyes states detection are integrated to decide whether an alarm should be issued. The results show an accuracy of about 90% which is encouraging.
Dr Mansour Baghaeian, Mr Ehsan Abbasi,
Volume 16, Issue 1 (3-2026)
Abstract
In metal casting, detecting defects like pores and cracks in X-ray images is crucial for product quality and safety. This study presents an advanced U-Net architecture for semantic segmentation of defects in the GDXray dataset, achieving superior accuracy. By formulating defect detection as an inverse problem reconstructing material density from X-ray projections the method integrates transfer learning, data augmentation, and Convolutional Block Attention Modules (CBAM) to address low contrast-to-noise ratios and limited data. Pretrained on synthetic Radon transform projections, the U-Net, enhanced with CBAM, sharpens focus on defect regions, improving boundary precision by 5%. Data augmentation, including rotations, flips, and noise injection, generates 5,000 synthetic images to overcome data scarcity. Experiments on 2,727 grayscale GDXray images demonstrate a mean Intersection over :union: (mIoU) of 0.85, a 15% improvement over baseline U-Net models, with 97.8% accuracy for pores and 94.5% for cracks. The inverse problem approach reduces false negatives by 12%, excelling in noisy conditions. Compared to methods like Mask R-CNN, this approach advances non-destructive evaluation (NDE) for casting applications, ensuring reliability and safety. Validated on laboratory X-ray data, the model offers a scalable solution for industrial defect detection. Future work will optimize computational efficiency and explore multi-modal data to enhance robustness.
