R. Aktar, V. H. Huxley, G. Guidoboni, O. V. Glinskii, and K. Palaniappan

IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pgs. 1-5, 2020

global mosaicing, registration, normalize cross correlation, fuse descriptor, mesentery

PlainText, Bibtex, PDF, URL, DOI, Google Scholar

Abstract

Mosaicing or large-scale panoramic image generation is a crucial task in medical imaging especially examining cellular features or microstructures. Earlier we have proposed an algorithm, Deformable Normalized Cross-Correlation (DNCC) [1] to mosaic feature-poor, motion-blurred frog mesentery video sequences. DNCC algorithm generates a single mosaic from each sequence establishing broad structure morphology. Unfortunately, a single mosaic cannot incorporate all information captured from all the sequences together. In another word, we aim to generate a global mosaic combining or fusing all the single mosaics from mesentery sequences. Global mosaic is desirable for comprehensive observation and exploration of the target region in microscopic resolution. Unfortunately, registration of single mosaics to a global mosaic is challenging due to the perspective distortion, scale change and visible seam of single mosaics which are introduced during stitching. Traditional feature-based or correlation-based method does not work well in such cases. To handle these challenges, we propose a new fused descriptor combining the strengths of both feature-based and correlation-based registration methods for fusing/stitching the single mosaics into one global mosaic or panorama.