Quantum-Inspired PCA for Image Compression

This demo applies Quantum Principal Component Analysis (QPCA) concepts to images. The uploaded image is converted into a quantum-like state (normalized amplitudes) and analyzed through eigenvalue decomposition.

• Reconstruction: rebuilds the image using all principal components.
• Compression: keeps only the top components capturing ~95% of total variance (energy), reducing information while preserving key features.
• MSE: quantifies the loss between the original and compressed images.
• Overlays: visualize leading eigencomponents that form the compressed basis.

Although executed on a classical backend, the algorithm follows the mathematical structure of QPCA and can be adapted to run on real quantum processing units (QPUs) once large-scale hardware becomes available. Quantum image compression can be easily done using Quantag Studio python SDK.