Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Generating Adaptive and Robust Filter Sets using an Unsupervised Learning Framework

Abstract: 

In this paper, we introduce an adaptive unsupervised learning framework, which utilizes natural images to train filter sets. The ap- plicability of these filter sets is demonstrated by evaluating their per- formance in two contrasting applications - image quality assessment and texture retrieval. While assessing image quality, the filters need to capture perceptual differences based on dissimilarities between a reference image and its distorted version. In texture retrieval, the filters need to assess similarity between texture images to retrieve closest matching textures. Based on experiments, we show that the filter responses span a set in which a monotonicity-based metric can measure both the perceptual dissimilarity of natural images and the similarity of texture images. In addition, we corrupt the images in the test set and demonstrate that the proposed method leads to robust and reliable retrieval performance compared to existing methods.

up
0 users have voted:

Paper Details

Authors:
Mohit Prabhushankar, Dogancan Temel, and Ghassan Alregib
Submitted On:
11 September 2017 - 6:47pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Ghassan AlRegib
Paper Code:
ICIP1701
Document Year:
2017
Cite

Document Files

ICIP2017Poster_UnsupervisedFramework_MohitCan.pdf

(17 downloads)

Subscribe

[1] Mohit Prabhushankar, Dogancan Temel, and Ghassan Alregib, "Generating Adaptive and Robust Filter Sets using an Unsupervised Learning Framework", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1920. Accessed: Nov. 24, 2017.
@article{1920-17,
url = {http://sigport.org/1920},
author = {Mohit Prabhushankar; Dogancan Temel; and Ghassan Alregib },
publisher = {IEEE SigPort},
title = {Generating Adaptive and Robust Filter Sets using an Unsupervised Learning Framework},
year = {2017} }
TY - EJOUR
T1 - Generating Adaptive and Robust Filter Sets using an Unsupervised Learning Framework
AU - Mohit Prabhushankar; Dogancan Temel; and Ghassan Alregib
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1920
ER -
Mohit Prabhushankar, Dogancan Temel, and Ghassan Alregib. (2017). Generating Adaptive and Robust Filter Sets using an Unsupervised Learning Framework. IEEE SigPort. http://sigport.org/1920
Mohit Prabhushankar, Dogancan Temel, and Ghassan Alregib, 2017. Generating Adaptive and Robust Filter Sets using an Unsupervised Learning Framework. Available at: http://sigport.org/1920.
Mohit Prabhushankar, Dogancan Temel, and Ghassan Alregib. (2017). "Generating Adaptive and Robust Filter Sets using an Unsupervised Learning Framework." Web.
1. Mohit Prabhushankar, Dogancan Temel, and Ghassan Alregib. Generating Adaptive and Robust Filter Sets using an Unsupervised Learning Framework [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1920