A combined method for histogram equalization of high dynamic range images

M.A. Kazakov

---

Abstract: When working with raw images obtained directly from the equipment matrix, specific problems arise associated with a large dynamic range. The paper proposes a combined histogram correction method that can significantly improve the contrast of such raw images with a large dynamic range. In the combined method, soft clipping of highlights in the histogram is performed using a clustering algorithm based on partitioning the feature space and gamma correction of the clipped area. The clustering algorithm used manages to identify the cutoff point, both in the presence and absence of highlights in the image. The method also produces weak edge accentuation based on Sobel filters. To improve the histogram, the well-known Contrast Limited Adaptive Histogram Equalization method is used. In this case, a combination of transformations with different mesh sizes is used, which allows one to achieve much better results than when selecting one optimal transformation. These algorithms are described in detail and illustrations for comparison are provided.

Keywords: histogram, histogram equalization, x-ray images, image processing, contrast enhancement, clustering

For citation. Kazakov M.A. A combined method for histogram equalization of high dynamic range images. News of the Kabardino-Balkarian Scientific Center of RAS. 2023. No. 6(116). Pp. 160–166. DOI: 10.35330/1991-6639-2023-6-116-160-166

References

1. Vijayalakshmi D., Nath M.K., Acharya O.P. A comprehensive survey on image contrast enhancement techniques in spatial domain. Sensing and Imaging. 2020. Vol. 21. No. 1. P. 40. DOI: 10.1007/s11220-020-00305-3
2. Woods R.E., Gonzalez R.C. Digital Image Processing. England: Pearson, 2021. 1022 с.
3. Jain A.K. Fundamentals of digital image processing. England: Pearson, 1989. 569 с.
4. Naidu S., Quadros A., Natekar A. et al. Enhancement of X-ray images using various Image Processing Approaches. International Conference on Technological Advancements and Innovations. Tashkent, 2021. Pp. 115–120. DOI: 10.1109/ICTAI53825.2021.9673317
5. Ishigami R., Zin T.T., Shinkawa N., Nishii R. Human identifi cation using X-Ray image matching. Proceedings of the International Multi Conference of Engineers and Computer Scientists. Hong Kong. 2017.
6. Rajpurkar P., Irvin J., Zhu K. et al. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. 2017. arXiv URL preprint arXiv:1711.05225.
7. Costa M.V.L., Aguiar E.J. A Deep Learning-based Radiomics Approach for COVID-19 Detection from CXR Images using Ensemble Learning Model. XXXVI International Symposium on Computer-Based Medical Systems. L’Aquila, Italy, 2023. Pp. 517–522. DOI: 10.1109/CBMS58004.2023.00272
8. Radvansky M., Kudelka M., Kriegova E. Process of finding human knee in image based on multiple weighted thresholding and histograms of gradients. XXIV International Carpathian Control Conference. Miskolc-Szilv´asv´arad, Hungary, 2023. Pp. 358–363. DOI: 10.1109/10.1109/ICCC57093.2023.10178913
9. Pizer S.M., Amburn E.P., Austin J.D. Adaptive histogram equalization and its variations. Computer Vision, Graphics, and Image Processing. 1987. Vol. 39. Pp. 355–368. DOI: 10.1016/S0734-189X(87)80186-X
10. Cromartie R., Pizer S.M. Edge-affected context for adaptive contrast enhancement. Proceedings of the XLLTH International Meeting on Information Processing in Medical Imaging: Lecture Notes in Computer Science. Berlin: Springer-Verlag. 1991. Pp. 474–485. DOI: 10.1007/BFb00337
11. Zuiderveld K.J. Contrast limited adaptive histogram equalization. Graphics gems. 1994. Pp. 474–485. DOI: 10.1016/B978-0-12-336156-1.50061-6
12. Kazakov M.A. Clustering Algorithm Based on Feature Space Partitioning. International Russian Automation Conference. 2022. Pp. 399–403. DOI:10.1109/RusAutoCon54946.2022.9896314
13. Sobel I. An Isotropic 3×3 Image Gradient Operator. Presentation at Stanford A.I. Project 2014.

Information about the author

Kazakov Mukhamed Anatolievich, Junior Researcher of the Department of Neuroinformatics and Machine Learning, Institute of Applied Mathematics and Automation – branch of Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences;
360000, Russia, Nalchik, 89 A Shortanov street;
kasakow.muchamed@gmail.com, ORCID: https://orcid.org/0000-0002-5112-5079