Rotation Invariant Deep CBIR

TL;DR

This paper presents a novel deep learning approach for rotation-invariant content-based image retrieval, combining orientation angle detection with feature extraction to improve accuracy and enable real-time retrieval from large datasets.

Contribution

Introduces a deep learning method that integrates orientation detection with feature extraction to achieve rotation invariance in CBIR systems.

Findings

Effective rotation-invariant retrieval demonstrated on large datasets

Real-time performance achieved in the proposed system

Outperforms traditional hand-engineered rotation-invariant features

Abstract

Introduction of Convolutional Neural Networks has improved results on almost every image-based problem and Content-Based Image Retrieval is not an exception. But the CNN features, being rotation invariant, creates problems to build a rotation-invariant CBIR system. Though rotation-invariant features can be hand-engineered, the retrieval accuracy is very low because by hand engineering only low-level features can be created, unlike deep learning models that create high-level features along with low-level features. This paper shows a novel method to build a rotational invariant CBIR system by introducing a deep learning orientation angle detection model along with the CBIR feature extraction model. This paper also highlights that this rotation invariant deep CBIR can retrieve images from a large dataset in real-time.