Abstract | ||
---|---|---|
We present an optimization methodology for improving the measurement accuracy of image features for low signal to noise ratio (SNR) images. By superimposing known background noise with high quality images in various proportions, we produce a degraded image set spanning a range of SNRs with reference feature values established from the unmodified high quality images. We then experiment with a variety of image processing spatial filters applied to the degraded images and identify which filter produces an image whose feature values most closely correspond to the reference values. When using the best combination of three filters and six kernel sizes for each feature, the average correlation of feature values between the degraded and high quality images increased from 0.6 (without filtering) to 0.92 (with feature-specific filters), a 53% improvement. Selecting a single filter is more practical than having a separate filter per feature. However, this results in a 1.95% reduction in correlation and a 10% increase in feature residual root mean square error compared to selecting the optimal filter and kernel size per feature. We quantified the tradeoff between a practical solution for all features and feature-specific solution to support decision making. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/CVPRW.2016.176 | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
Field | DocType | Volume |
Kernel (linear algebra),Computer vision,Residual,Background noise,Pattern recognition,Feature (computer vision),Signal-to-noise ratio,Mean squared error,Image processing,Filter (signal processing),Artificial intelligence,Mathematics | Conference | 2016 |
Issue | ISSN | Citations |
1 | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 8 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Majurski | 1 | 18 | 2.96 |
Joe Chalfoun | 2 | 28 | 7.49 |
Steve Lund | 3 | 0 | 0.68 |
Peter Bajcsy | 4 | 138 | 25.50 |
Mary Brady | 5 | 39 | 10.10 |