Optimal clustering based outlier detection and cluster center initialization algorithm for effective tone mapping
- 66 Downloads
The high dynamic range (HDR) imaging and displaying a wide range of imaging levels in the imaging industry is found in the world using devices with limited dynamic range. Generally, the clustering system plays an important role in tone mapping. Clustering is a combination of similar properties based on their properties. Maximum detection and cluster core initiation is a major problem in the cluster; has been used to remove and identify abnormal data from the database. The data value can be represented by the value data outside the boundary of the sample data. In this paper, we have suggested clustering-based release detection and cluster core initialization protocols for open tone mapping, which uses the modified K-object clustering algorithm in the cluster the data sets. A density-based multi-level data suppression (DBMSDC) algorithm is used the early cluster centers calculated using the DBMSDC algorithm have been found to be very close to the desired cluster centers. Exposure has been detected using a weight based center approach and the change K-material clustering has been removed. Test results show that the proposed methods reach advanced and efficient solutions, while the art tone mapping protocols.
KeywordsClustering Outlier K-means Density based multi scale data condensation Weight based center approach
- 21.Malm H, Oskarsson M, Warrant E et al (2007) Adaptive enhancement and noise reduction in very low light-level video. In: 2007 IEEE 11th international conference on computer vision, Rio de Janeiro, Brazil, pp 1–8. https://doi.org/10.1109/iccv.2007.4409007
- 27.Patel VA, Shah P, Raman S (2018) A generative adversarial network for tone mapping HDR images. In: Computer vision, pattern recognition, image processing, and graphics: 6th National Conference, NCVPRIPG 2017, Mandi, India, pp 220–223Google Scholar
- 30.Shibata T, Tanaka M, Okutomi M (2016) Gradient-domain image reconstruction framework with intensity-range and base-structure constraints. Proc IEEE Conf Comput Vis Pattern Recognit:2745–2753Google Scholar