Skip to content

Latest commit

 

History

History
49 lines (44 loc) · 3.19 KB

README.md

File metadata and controls

49 lines (44 loc) · 3.19 KB
Raw

image_enhancement

Library of NumPy-based Image Processing functions for various types of Image Enhancement, including:

  • Spatial Tone Mapping
  • Local Contrast Enhencement
  • Color Correction (White Balance)
  • Color Saturation Adjustment

Examples:

Example1 Example2 Example3 Example4 Example5 Example6

Functions:

/source/image_enhancement.py contains:

  • get_photometric_mask(): Estimates local brightness distribution (edge-aware blurring).
  • apply_local_contrast_enhancement(): Adjusts strength of local details.
  • apply_spatial_tonemapping(): Adjusts brightness levels in dark and bright regions.
  • transfer_graytone_to_color(): Transfers tones from a tone-mapped grayscale image to a color image.
  • change_color_saturation(): Adjusts the color vibrance of an image.
  • correct_colors(): Removes color casts from images.
  • srgb_to_linear(): Transforms image to the linear color space.
  • linear_to_srgb(): Transforms image to the gamma-corrected color space.
  • enhance_image(): Applies multiple stages of enhancement to an image.

Contents:

├── src                                        [Directory: Source code]
│   ├── image_enhancement.py                   [Main script with all the functions] 
│   ├── example_color_correction.py            [Example of applying color correction]
│   ├── example_enhance_image.py               [Example of combined image enhancement]
│   ├── example_local_contrast_enhancement.py  [Example of applying increasing local details]
│   └── example_medical_image.py               [Example of processing medical images]
└── images                                     [Directory: Sample test images]

Dependences

  • numpy
  • imageio
  • skimage (can be easily bypassed if needed)

Citations

If you use this code in your research please cite the following papers:

  1. Vonikakis, V., Andreadis, I., & Gasteratos, A. (2008). Fast centre-surround contrast modification. IET Image processing 2(1), 19-34.
  2. Vonikakis, V., Winkler, S. (2016). A center-surround framework for spatial image processing. Proc. IS&T Human Vision & Electronic Imaging, (Retinex020), San Francisco, CA, Feb. 14-18.
  3. Vonikakis, V., Arapakis, I. & Andreadis, I. (2011).Combining Gray-World assumption, White-Point correction and power transformation for automatic white balance. International Workshop on Advanced Image Technology (IWAIT), 1569353295.
  4. Vonikakis, V., & Andreadis, I. (2008). Multi-Scale Image Contrast Enhancement. ICARCV 2008. (pp. 385-391).