Abstract: Convolutional Neural Network (NN) has gained a lot of attention of the researchers due to its high accuracy in classification and feature learning. In this paper, we evaluated the performance of CNN used as feature for image retrieval with the gold standard feature, aka SIFT. Experiments are conducted on famous Oxford 5k data-set. The mAP of SIFT and CNN is 0.6279 and 0.5284, respectively. The performance of CNN is also compared with bag of visual word (BoVW) model. CNN achieves better accuracy than BoVW.

Varsha Devi Sachdeva, Junaid Baber, Maheen Bakhtyar, Ihsan Ullah, Waheed Noor and Abdul Basit. “Performance Evaluation of SIFT and Convolutional Neural Network for Image Retrieval”. International Journal of Advanced Computer Science and Applications (IJACSA) 8.12 (2017). http://dx.doi.org/10.14569/IJACSA.2017.081268

@article{Sachdeva2017,
title = {Performance Evaluation of SIFT and Convolutional Neural Network for Image Retrieval},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2017.081268},
url = {http://dx.doi.org/10.14569/IJACSA.2017.081268},
year = {2017},
publisher = {The Science and Information Organization},
volume = {8},
number = {12},
author = {Varsha Devi Sachdeva and Junaid Baber and Maheen Bakhtyar and Ihsan Ullah and Waheed Noor and Abdul Basit}
}