Abstract:
Computer vision and computational photography rely on multispectral imaging. Image registration is needed to avoid spectral information distortion from imaging device movement. Multispectral data registration measures are robust but computationally intensive.
SSD and SAD are computationally efficient but perform poorly on multispectral data. We propose a structure consistency boosting (SCB) transform to improve multispectral image structural similarity. SCB allows multispectral image registration using common measures.
Despite band image nonlinearity, inherent edge structures maintain relative saliency locally, which the SCB transform exploits. To build a parametric SCB, a gradient-intensity correlation-based natural image statistical prior is explored.
Experimental results show that the SCB transform outperforms similarity enhancement algorithms and state-of-the-art multispectral registration measures. The statistical prior makes the SCB transform suitable for multimodal data like flash/no-flash images and medical images.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
