Many recent medical developments rely on image analysis, however, it is not convenient nor cost-efficient to use professional image acquisition tools in every clinic or laboratory. Hence, a reliable color calibration is necessary; color calibration refers to adjusting the pixel colors to a standard color space. During a real-life project on neonatal jaundice disease detection, we faced a problem to perform skin color calibration on already taken images of neonatal babies. These images were captured with a smartphone (Samsung Galaxy S7, equipped with a 12 Mega Pixel camera to capture 4032x3024 resolution images) in the presence of a specific calibration pattern. This post-processing image analysis deprived us from calibrating the camera itself. There is currently no comprehensive study on color calibration methods applied to human skin images, particularly when using amateur cameras (e.g. smartphones). We made a comprehensive study and we proposed a novel approach for color calibration, Gaussian process regression (GPR), a machine learning model that adapts to environmental variables. The results show that the GPR achieves equal results to state-of-the-art color calibration techniques, while also creating more general models.

No abstract

In this paper, we present a new generation algorithm with corresponding ranking and unranking algorithms for (k, m)-ary trees in B-order. (k, m)-ary tree is introduced by Du and Liu. A (k, m)-ary tree is a generalization of k-ary tree whose every node of even level of the tree has degree k and odd level of the tree has degree 0 or m. Up to our knowledge no generation, ranking or unranking algorithms are given in the literature for this family of trees. We use Zaks' encoding for representing (k, m)-ary trees, and to generate them in B-order. We also prove that, to generate (k, m)-ary trees in B-order using this encoding, the corresponding codewords should be generated in reverse-lexicographical ordering. The presented generation algorithm has a constant average time and O(n) time complexity in the worst case. Due to the given encoding, both ranking and unranking algorithms are also presented taking O(n) and O(n log n) time complexity, respectively.

No abstract