IMAGE REPROCESSING FOR ARTIFICIAL INTELLIGENCE ALGORITHMS
Authors/Creators
- 1. Faculty of Artificial Intelligence and Digital Technologies Samarkand State University, Uzbekistan
- 2. 2nd-year Master's Student Faculty of Artificial Intelligence and Digital Technologies Samarkand State University named after Sharof Rashidov, Uzbekistan
- 3. Samarkand State University named after Sharof Rashidov, Uzbekistan
Description
As is known, today modern technologies create various conveniences for humans. Their effects are clearly visible in many areas today. In particular, many convenient devices are being created using data visualization and analysis. Such devices make important decisions using image processing. The most important step in the image processing process is the Image preprocessing process. During the image preprocessing process, various changes are made to the size, color, and quality of the image. The finished image is provided to the appropriate program or artificial intelligence algorithms. The image processing process is a very important stage and has a great impact on the result of the program. A qualitatively processed image increases the accuracy of the program several times.
This research paper provides information about image processing and the work performed in it. At the same time, sample images are taken and subjected to the reprocessing stage. The results obtained are analyzed and conclusions are drawn. These results are presented for use in future research.
Files
1334-1343.pdf
Files
(370.3 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:e2dec6b80e618b9e1bc97c1b558b9afe
|
370.3 kB | Preview Download |
Additional details
References
- Donoho, D. L. Noise reduction using a soft thresholding method // IEEE Journal of Information Theory. – 1995. – Vol. 41. – pp. 613–627.
- Addison, P. S. Wavelet transforms and the ECG: a review // Journal of Physiological Measurement. – 2005. – Vol. 26. – pp. R155–R199.
- Thakor, N. V., Zhu, Y.-S. Application of adaptive filtering in ECG analysis: noise reduction and arrhythmia detection // IEEE Journal of Biomedical Engineering. – 1991. – Vol. 38. – pp. 785–794.
- Kiranyaz, S., Ince, T., Gabbouj, M. Real-time patient-specific ECG classification using 1-dimensional convolutional neural networks // IEEE Journal of Biomedical Engineering. – 2016. – Vol. 63. – pp. 664–675.
- Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., Ng, A. Y. Cardiologist-level detection and classification of arrhythmia in electrocardiograms using deep neural networks // Nature Medicine. – 2019. – Vol. 25. – pp. 65–69.