GitHub

Reliable DOM Fluorescence Prediction via Solvent Sensitive Machine Learning and Domain Refinement

This repository contains the complete code implementation for the manuscript "Reliable DOM Fluorescence Prediction via Solvent Sensitive Machine Learning and Domain Refinement". The code implements a ...
GitHub

This repository contains scripts for transmittance/reflectance calibration (same formula) using an reference images and for image mosaicing/stitching. It also contains various ...

To run the scripts you need the packages: Numpy, OpenCV, SciPy, Pillow and SpectralPython. The full workflow from radiance images to a mosaiced image is: 1. Make a clean white reference without lines ...
IEEE

Grid-Shift: An Image Preprocessing Approach to Reduce Overfitting in AI Training

Abstract: We present Grid-Shift, a lightweight image pre-processing approach to counteract overfitting when training Convolutional Neural Networks. Grid-Shift solves the problem that tiling large ...
IEEE

Evaluation of Image Preprocessing Algorithms for Foggy Scene Enhancement

Abstract: Fog significantly degrades image quality by reducing contrast, detail, and color fidelity. This degradation negatively impacts computer vision tasks. This work presents a comparative ...