An efficient image retrieval framework using fused information feature

Abstract The tremendous growth in the number of digital images has provoked the need for improvement in search and retrieval of images from a large database. The biggest challenge faced in this process is retrieval of the required images from a large database with maximum precision and minimum retrieval time. Selecting appropriate features plays a significant role in improving the performance of image retrieval systems. In this paper, Fused Information Feature-based Image Retrieval System (FIF-IRS) is proposed, consisting of 8-Directional Gray Level Co-occurrence Matrix (8D-GLCM) and HSV Color Moments (HSVCM) features. The performance of the image retrieval system is evaluated by the metrics Precision, Error Rate, and Retrieval Time. The proposed image retrieval system is tested on benchmark image databases- Corel-1K, Corel-5K, and Corel-10K. The experimental results obtained prove that there is a significant improvement while applying the proposed method when compared to existing state-of-the-art techniques with attained precision of 83.3%, 66.9%, and 56.4% on the three databases respectively.

[1]  Jianzhong Wang,et al.  A novel image retrieval method based on hybrid information descriptors , 2014, J. Vis. Commun. Image Represent..

[2]  Q. M. Jonathan Wu,et al.  Modified color motif co-occurrence matrix for image indexing and retrieval , 2013, Comput. Electr. Eng..

[3]  Anil Balaji Gonde,et al.  Modified curvelet transform with vocabulary tree for content based image retrieval , 2013, Digit. Signal Process..

[4]  Adrian G. Bors,et al.  Image retrieval based on query by saliency content , 2015, Digit. Signal Process..

[5]  Vipin Tyagi,et al.  An efficient technique for retrieval of color images in large databases , 2015, Comput. Electr. Eng..

[6]  Miguel Arevalillo-Herráez,et al.  Combining feature extraction and expansion to improve classification based similarity learning , 2017, Pattern Recognit. Lett..

[7]  I. Jeena Jacob,et al.  Local Oppugnant Color Texture Pattern for image retrieval system , 2014, Pattern Recognit. Lett..

[8]  Min Huang,et al.  Content-based image retrieval technology using multi-feature fusion , 2015 .

[9]  Rajneesh Talwar,et al.  A fast and effective image retrieval scheme using color-, texture-, and shape-based histograms , 2016, Multimedia Tools and Applications.

[10]  Jing-Yu Yang,et al.  Content-based image retrieval using computational visual attention model , 2015, Pattern Recognit..

[11]  Muhammad Imran,et al.  Content Based Image Retrieval Using Color Layout Descriptor and Generic Fourier Descriptor , 2015 .

[12]  Muhammad Sharif,et al.  Intelligent Image Retrieval Techniques: A Survey , 2014 .

[13]  Mznah Al-Rodhaan,et al.  Content-based image retrieval using PSO and k-means clustering algorithm , 2015, Arabian Journal of Geosciences.

[14]  Husniza Husni,et al.  A weighted dominant color descriptor for content-based image retrieval , 2013, J. Vis. Commun. Image Represent..

[15]  Subrahmanyam Murala,et al.  Local extrema co-occurrence pattern for color and texture image retrieval , 2015, Neurocomputing.

[16]  Subrahmanyam Murala,et al.  Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval , 2012, IEEE Transactions on Image Processing.

[17]  Mahrokh G. Shayesteh,et al.  Framework for image retrieval using machine learning and statistical similarity matching techniques , 2013, IET Image Process..

[18]  T. Sree Sharmila,et al.  An efficient framework for image retrieval using color, texture and edge features , 2017, Comput. Electr. Eng..

[19]  M. D. Ingole,et al.  Content based image retrieval using hybrid features and various distance metric , 2018, Journal of Electrical Systems and Information Technology.

[20]  Meng Zhao,et al.  A novel image retrieval method based on multi-trend structure descriptor , 2016, J. Vis. Commun. Image Represent..

[21]  Jing-Yu Yang,et al.  Content-based image retrieval using color difference histogram , 2013, Pattern Recognit..

[22]  Aman Pal,et al.  Fusion framework for effective color image retrieval , 2014, J. Vis. Commun. Image Represent..