Skip to content

classic content-based image retrieval using python (feature vector distance)

License

Notifications You must be signed in to change notification settings

aa1000/ImageRetrievalClassic

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Content-based Image Retrieval

classic content-based image retrieval using python (feature vector distance)

Each feature vector consists of an:

  • RGB Color Histogram
  • Indexed Color Histogram (using the indices of color classes in a global LUT)
  • DCT2 (Discrete Cosine Transform) Low Frequency Range
  • GLCM (Gray-Level Co-occurrence Matrix) Energy And Contrast

Dependencies:

  • OpenCV (CV2)
  • numpy
  • scipy
  • sklearn
  • skimage
  • glob2
  • matplotlib
  • tkinter

Steps:

  • Create a root directory and put the 'CreateDatabase.py', 'RetrieveSimilarImages.py' and 'ImageUtils.py' scripts in it
  • Collect the number of images you want to use as a database and arrange them into a new folder(s) in the root directory
  • Run 'CreateDatabase.py' which will search for all folders in the root directory and create the database of feature vectors for all images present in them (might take a while depending on the size of the database and processing power)
  • Run 'RetrieveSimilarImages.py' which will prompt you to choose an image file to use as the base for search then return the closest matches

About

classic content-based image retrieval using python (feature vector distance)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages