Deep Learning Based Image Retrieval in the JPEG Compressed Domain

TL;DR

This paper introduces a unified deep learning model that extracts image features directly from JPEG compressed data, enabling faster and efficient content-based image retrieval without full image decoding.

Contribution

The novel approach directly utilizes DCT coefficients from JPEG images for feature extraction, reducing computation and speeding up retrieval compared to pixel-based methods.

Findings

Model achieves similar accuracy to RGB-based methods in retrieval tasks.

Faster training and retrieval speeds demonstrated.

Effective in extracting both global and local features from compressed data.

Abstract

Content-based image retrieval (CBIR) systems on pixel domain use low-level features, such as colour, texture and shape, to retrieve images. In this context, two types of image representations i.e. local and global image features have been studied in the literature. Extracting these features from pixel images and comparing them with images from the database is very time-consuming. Therefore, in recent years, there has been some effort to accomplish image analysis directly in the compressed domain with lesser computations. Furthermore, most of the images in our daily transactions are stored in the JPEG compressed format. Therefore, it would be ideal if we could retrieve features directly from the partially decoded or compressed data and use them for retrieval. Here, we propose a unified model for image retrieval which takes DCT coefficients as input and efficiently extracts global and local features directly in the JPEG compressed domain for accurate image retrieval. The experimental findings indicate that our proposed model performed similarly to the current DELG model which takes RGB features as an input with reference to mean average precision while having a faster training and retrieval speed.