SEM Image
Scanning electron microscopy (SEM) images provide high-resolution visual data of material surfaces, crucial for analyzing microstructures and defects across diverse fields like semiconductor manufacturing and materials science. Current research heavily utilizes deep learning, employing architectures like U-Net, Mask R-CNN, and generative models (e.g., diffusion models) to automate tasks such as defect detection, segmentation, and classification in SEM images, often addressing challenges like class imbalance and noise. These advancements significantly improve efficiency and accuracy in material characterization, enabling faster analysis and more precise quantitative measurements for applications ranging from quality control in advanced electronics to fundamental materials research.
Papers
Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis
Sakhinana Sagar Srinivas, Chidaksh Ravuru, Geethan Sannidhi, Venkataramana Runkana
Multi-Modal Instruction-Tuning Small-Scale Language-and-Vision Assistant for Semiconductor Electron Micrograph Analysis
Sakhinana Sagar Srinivas, Geethan Sannidhi, Venkataramana Runkana