Abstract
AbstractCurrent mask processing operations rely on interpolation algorithms that do not produce extra pixels, such as nearest neighbor (NN) interpolation, as opposed to algorithms that do produce extra pixels, like bicubic (BIC) or bilinear (BIL) interpolation. In our previous study, the author proposed an alternative approach to NN-based mask processing and evaluated its effects on deep learning training outcomes. In this study, the author evaluated the effects of both BIC-based image and mask processing and BIC-and-NN-based image and mask processing versus NN-based image and mask processing. The evaluation revealed that the BIC-BIC model/network was an 8.9578% (with image size 256 × 256) and a 1.0496% (with image size 384 × 384) increase of the NN-NN network compared to the NN-BIC network which was an 8.3127% (with image size 256 × 256) and a 0.2887% (with image size 384 × 384) increase of the NN-NN network.
Funder
Medical University of Vienna
Publisher
Springer Science and Business Media LLC
Reference15 articles.
1. Rukundo, O.: Effects of image size on Deep Learning. Electronics. 12, 985 (2023)
2. Rukundo, O., Schmidt, S.: Stochastic rounding for image interpolation and scan Conversion. Int. J. Adv. Comput. Sci. Appl. 13, 13–22 (2022)
3. Rukundo, O., Schmidt, S.E., Von Ramm, O.T.: Software implementation of optimized bicubic interpolated scan conversion in echocardiography, arXiv:2005.11269, (2020)
4. Rukundo, O., Schmidt, S.E.: Aliasing artefact index for image interpolation quality assessment, Proc. SPIE 10817, Optoelectronic Imaging and Multimedia Technology V, 108171E, (2018)
5. Parker, J.A., Kenyon, R.V., Troxel, D.E.: Comparison of interpolating methods for image Resampling. in IEEE Trans. Med. Imaging, 2(1), pp. 31–39, March 1983
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献