Classifying stem cell differentiation images by information distance
ECML PKDD'12 Proceedings of the 2012 European conference on Machine Learning and Knowledge Discovery in Databases - Volume Part I
Supervised texture classification using a novel compression-based similarity measure
ICCVG'12 Proceedings of the 2012 international conference on Computer Vision and Graphics
Acoustic detection of elephant presence in noisy environments
Proceedings of the 2nd ACM international workshop on Multimedia analysis for ecological data
Hi-index | 0.00 |
The analysis of texture is an important subroutine in application areas as diverse as biology, medicine, robotics, and forensic science. While the last three decades have seen extensive research in algorithms to measure texture similarity, almost all existing methods require the careful setting of many parameters. There are many problems associated with a lot of parameters, the most obvious of which is that with many parameters to fit, it is very difficult to avoid overfitting. In this work, we propose to extend recent advances in Kolmogorov complexity‐based similarity measures to texture matching problems. These Kolmogorov‐based methods have been shown to be very useful in intrinsically discrete domains such as DNA, protein sequences, MIDI music, and natural languages; however, they are not well defined for real‐valued data. To address this, we introduce a very simple idea, the Campana‐Keogh (CK) video compression‐based method for texture measures. These measures utilize video compressors to approximate the Kolmogorov complexity. Using the parameter‐free CK method, we novely utilize lossy compression to create an efficient and robust parameter‐lite texture similarity measure: the CK‐1 distance measure. We demonstrate the utility of our measure with extensive empirical evaluations on real‐world case studies drawn from nematology, arachnology, entomology, medicine, forensics, texture analysis benchmarks, and many other domains. Copyright © 2010 Wiley Periodicals, Inc. Statistical Analysis and Data Mining 3: 381‐398, 2010 © 2010 Wiley Periodicals, Inc.