Skip to content

This program that will find and remove all similar-looking images in a folder. The input of the program is a path to a folder with images, the result program will remove all non-essential for data collection images - duplicated or almost duplicated images that have only minor differences from the original that may be considered as non-essential.

Notifications You must be signed in to change notification settings

drushtig/imaging_interview

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Image Comparison Project

This project contains a set of scripts for finding and moving similar images from a source folder to a destination folder.

Requirements

Python 3.7+ OpenCV PyYAML imaging_interview

Data Format

  1. The images are in PNG format.
  2. Each image file is named following the pattern: c%camera_id%-%timestamp%.png.
  3. The timestamp is in either of two formats.

Installation

  1. Install the necessary packages by running pip install -r requirements.txt.
  2. Update the source_folder and destination_folder variables in config.yaml with the paths to your source and destination folders.
  3. Run python main.py to start the image processing script.

General Working

This script will process all images in the source folder, compare each image with the next one, and move similar images to the destination folder. The similarity of images is determined by a threshold value. If the score of the comparison is less than the threshold, the images are considered similar.

Contact Information

For more questions, feel free to reach out to [email protected].

Additional information

This project uses the Black code formatter to ensure consistent and readable code style. To format your code with Black, run:

black main.py utilities.py

  

About

This program that will find and remove all similar-looking images in a folder. The input of the program is a path to a folder with images, the result program will remove all non-essential for data collection images - duplicated or almost duplicated images that have only minor differences from the original that may be considered as non-essential.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages