Image Visual Similarity Based on High Level Features of Convolutional Neural Networks
Keywords:
Image retrieval, Convolutional neural networks, Distance metricsAbstract
Nowadays, the task of similar content retrieval is one of the central topics of interest in academic and industrial worlds. There are numerous techniques that are both dealing good with structured data and unstructured such as texts, respectively. However, in this paper we present a technique for retrieval of similar image content. We embed images to N dimensional feature space using convolutional neural networks and perform the nearest neighbor search afterwards. At the end, several distance metrics and their influence on the outcome are discussed. We are rather interested in the proportion of related content than in the additional ranking. Thus, the evaluation of results is based on precision and recall. We have selected 6 major categories from ImageNet dataset to assess the performance.
References
R. Datta, J. Li and J. Z. Wang, “Content-based image retrieval - approaches and trends of the new age", The Pennsylvania State University, University Park, PA 16802, 2005.
D. G. Lowe, “Distinctive image features from scale-invariant keypoints", International Journal of Computer Vision, vol. 60, no. 2, pp. 91-11 0, 2004.
R. Funayama, H. Yanagihara, L. Van Gool, T. Tuytelaars and H. Bay, “Robust Interest Point Detector and Descriptor", US Patent office, no. 81 65 401, 2009.
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li and L. Fei-Fei, "ImageNet: A Large-Scale Hierarchical Image Database", IEEE Computer Vision and Pattern Recognition, 2009.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich, “Going Deeper with Convolutions", arXiv, no. 1409.4842, 2014.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
