Skip to content

Latest commit

 

History

History
48 lines (36 loc) · 1.57 KB

paper.md

File metadata and controls

48 lines (36 loc) · 1.57 KB
title tags authors affiliations date bibliography
ipfml: A Python package for `Image Processing For Machine Learning`
Python
Image Processing
Computer Graphics
Statistics
Global illumination
name orcid affiliation
Jérôme BUISINE
0000-0001-6071-744X
1
name index
Univ. Littoral Côte d’Opale, LISIC Calais, France, F-62100
1
9 June 2020
paper.bib

Summary

Motivation

ipfml Python package have been developed during thesis project in order to regroup all usefull methods for image processing for machine learning problems.

This Python package is subdivised into multiple modules:

  • metrics: Metrics computation for model performance (between predicted and known labels)
  • utils: All utils functions developed (such as normalization of images or data)
  • exceptions: All customized exceptions
  • filters: Image filter module with convolution (additive noise using convolution)
  • iqa: Image quality assessments (full-reference IQA mainly)
  • processing: Image processing module (reduction dimension, transformation, segmentation...)

Application

Acknowledgements

This work is supported by Agence Nationale de la Recherche : project ANR-17-CE38-0009

References