Pre-Processing Techniques in DL

Description

This project involves implementing various image preprocessing techniques using Python to help users understand and apply these methods, thereby increasing the accuracy of machine learning models. The following preprocessing techniques will be covered:

Image Resize Image Crop Edge Detection (Sobel, Prewitt, Canny) Noise Removal Image Conversion (Grayscale, Binary) Histogram Equalization

Summary of Changes

Image Resize: Implemented functionality to adjust the dimensions of images, standardizing their input size for machine learning models. Image Crop: Added methods to extract specific regions from images, focusing on areas of interest and removing unwanted parts. Edge Detection: Developed techniques for highlighting edges within images using Sobel, Prewitt, and Canny algorithms. Noise Removal: Introduced methods to reduce or eliminate noise from images, enhancing their quality. Image Conversion: Created functions to convert images to grayscale or binary formats, simplifying processing and reducing computational complexity. Histogram Equalization: Implemented functionality to adjust image contrast using histogram equalization, improving the visibility of features.

Fixes #418

Type of change

[x] Added a new machine learning frameworks, libraries or software.
[x] Documentation update

Checklist:

[x] My code follows the style guidelines of this project
[x] I have performed a self-review of my own code
[x] I have commented my code, particularly in hard-to-understand areas
[x] I have made corresponding changes to the documentation
[ ] My changes generate no new warnings

Recode-Hive / machine-learning-repos