Performance Evaluation of SIFT and Convolutional Neural Network for Image Retrieval
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 12
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.
Authors and Affiliations
Varsha Devi Sachdeva, Junaid Baber, Maheen Bakhtyar, Ihsan Ullah, Waheed Noor, Abdul Basit
Keywords
Related Articles
- EP ID EP259908
- DOI 10.14569/IJACSA.2017.081268
- Views 78
- Downloads 0
Optimization and Evaluation of Hybrid PV/WT/BM System in Different Initial Costs and LPSP Conditions
A modelling and optimization study was performed to manage energy demand of a faculty in Karabuk University campus area working with a hybrid energy production system by using genetic algorithm (GA). Hybrid system consis...
Cross Language Information Retrieval Model for Discovering WSDL Documents Using Arabic Language Query
Web service discovery is the process of finding a suitable Web service for a given user’s query through analyzing the web service‘s WSDL content and finding the best match for the user’s query. The service query should b...
Performance Analysis of Proposed Congestion Avoiding Protocol for IEEE 802.11s
The wireless technology is one of the core compo-nents of mobile applications with mobility support at low deploy-ment costs. Among these, Wireless Mesh Network (WMN) is one of the technologies that supports mobile users...
(AMDC) Algorithm for wireless sensor networks in the marine environment
Data compression is known today as one of the most important enabling technologies that form the foundation of the majority of data applications and networks as we know them, including wireless sensor networks and the po...
Evaluation of Different Hypervisors Performance in the Private Cloud with SIGAR Framework
To make cloud computing model Practical and to have essential characters like rapid elasticity, resource pooling, on demand access and measured service, two prominent technologies are required. One is internet and second...