# Detailed Investigation of Deep Features with Sparse Representation and Dimensionality Reduction in CBIR: A Comparative Study

arXiv: https://arxiv.org/abs/1811.09681 · HTML: https://mlsanity.com/paper/1811.09681/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2018.

## Built on by (most cited first, 3 of 3)

- [Stop Oversampling for Class Imbalance Learning: A Critical Review](https://mlsanity.com/paper/2202.03579/) (2022)
- [Deep learning for identification and face, gender, expression recognition under constraints](https://mlsanity.com/paper/2111.01930/) (2021)
- [Fuzzy Win-Win: A Novel Approach to Quantify Win-Win Using Fuzzy Logic](https://mlsanity.com/paper/2112.07045/) (2021)

## Abstract (arXiv)

Research on content-based image retrieval (CBIR) has been under development for decades, and numerous methods have been competing to extract the most discriminative features for improved representation of the image content. Recently, deep learning methods have gained attention in computer vision, including CBIR. In this paper, we present a comparative investigation of different features, including low-level and high-level features, for CBIR. We compare the performance of CBIR systems using different deep features with state-of-the-art low-level features such as SIFT, SURF, HOG, LBP, and LTP, using different dictionaries and coefficient learning techniques. Furthermore, we conduct comparisons with a set of primitive and popular features that have been used in this field, including colour histograms and Gabor features. We also investigate the discriminative power of deep features using certain similarity measures under different validation approaches. Furthermore, we investigate the effects of the dimensionality reduction of deep features on the performance of CBIR systems using principal component analysis, discrete wavelet transform, and discrete cosine transform. Unprecedentedly, the experimental results demonstrate high (95% and 93%) mean average precisions when using the VGG-16 FC7 deep features of Corel-1000 and Coil-20 datasets with 10-D and 20-D K-SVD, respectively.