Phase identification in many-body systems by virtual configuration binarization

Artificial intelligence provides an unprecedented perspective for studying phases of matter in condensed-matter systems. Image segmentation is a basic technique computer vision that belongs to branch artificial intelligence. Inspired by the image techniques, this work, we propose scheme named virtual configuration binarization (VCB) unveil quantum and phase transitions many-body By encoding information renormalized states into color binarize through VCB, can be visualized, from which revealed corresponding critical points identified. Our benchmarked on several strongly correlated spin systems, does not depend priori knowledge order parameters phases. This demonstrates potential disclose underlying structure techniques vision.