Publications by authors named "Ashwini S Galande"
Article Synopsis
- Lensless digital inline holographic microscopy (LDIHM) uses computational methods for imaging, but existing networks require large and diverse datasets for high-quality hologram reconstruction.
- To address the data scarcity, a hybrid deep framework called HDPhysNet is proposed, combining pre-trained and physics-aware models for improved phase recovery from low-resolution holograms.
- Experimental results indicate that HDPhysNet significantly outperforms both trained and untrained deep networks in reconstruction quality, enhancing structural similarity and phase signal-to-noise ratio for complex biological samples.
Significance: Artificial intelligence (AI) has become a prominent technology in computational imaging over the past decade. The expeditious and label-free characteristics of quantitative phase imaging (QPI) render it a promising contender for AI investigation. Though interferometric methodologies exhibit potential efficacy, their implementation involves complex experimental platforms and computationally intensive reconstruction procedures.
View Article and Find Full Text PDF