Skip to content

Mashiatmm/Content-Based-Image-Retrieval

Repository files navigation

Content-Based-Image-Retrieval

Dataset

CBIR Dataset

Size : 4738 Images of animals

Pipeline

This is a partial implementation of the pipeline of this paper with some modifications and a new dataset.

Pipeline

The images are first trained on the following convolutional AutoEncoder model as the backbone network to extract local features of size 256 * 32 * 32. The loss is minimized by calculating MSE of the decoded output and the original image.

AutoEncoder

The highlights of the pipeline for image retrieval are summarized below.

  • Generalized Mean Pooling : The outputs of the network is passed through a generalized mean pooling (GeM) layer.
  • L2 norm feature selection : 200 out of 256 2D local featurea are selected based on high L2 norm values.
  • Cosine Similarity : The similarity of two images are computed by calculating the cosine similarity between them.

Note : K-means clustering is not implemented here as shown in the pipeline and many steps are also excluded. This is a very simplified and modified pipeline.

Output

Output

This project is done as a part of the Advanced Digital Image Processing Course.

Credits

The codebase is modified from this work here.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published