Academia.eduAcademia.edu

Figure 6 – uploaded by Mansour Jamzad

See full PDFdownloadDownload figure
TABLE 5 Comparison between statistical and Deep learning-based methods in terms of Computation Cost TABLE 6 __ Execution time of statistics-based methods for the first image in Gehler-Shi ColorChecker database [30, 69]

Table 5 Comparison between statistical and Deep learning-based methods in terms of Computation Cost TABLE 6 __ Execution time of statistics-based methods for the first image in Gehler-Shi ColorChecker database [30, 69]

Related Figures (11)

FIGURE 1_— Examples of Gamma transformation functions with different values for parameters y [63]
FIGURE 1_— Examples of Gamma transformation functions with different values for parameters y [63]
performance evaluation are presented in Section 5.2. Finally, the experimental results are presented and discussed. ALGORITHM 1 Weighted Colour Constancy
performance evaluation are presented in Section 5.2. Finally, the experimental results are presented and discussed. ALGORITHM 1 Weighted Colour Constancy
FIGURE 3 A visual flow diagram of the proposed method
FIGURE 3 A visual flow diagram of the proposed method
TABLE 1 The recovery angular error of different colour constancy algorithms obtained on 8 NUS databases in terms of mean, median, trimean, best-25% and worst-25% angular errors The average of mean, median, trimean, best-25 % and worst-25% angular errors are tabulated in the last column
TABLE 1 The recovery angular error of different colour constancy algorithms obtained on 8 NUS databases in terms of mean, median, trimean, best-25% and worst-25% angular errors The average of mean, median, trimean, best-25 % and worst-25% angular errors are tabulated in the last column
TABLE 2 The recovery angular error of different colour constancy algorithms evaluated on ColorChecker Gehlet-Shi database [30, 69]
TABLE 2 The recovery angular error of different colour constancy algorithms evaluated on ColorChecker Gehlet-Shi database [30, 69]
[GURE 4 Influence of changing tunable parameters E and d on performance of the proposed algorithm on eight NUS databases. Charts 4c and 4d show the ages and values of standard deviations for errors of the proposed method on NUS-8camera database
[GURE 4 Influence of changing tunable parameters E and d on performance of the proposed algorithm on eight NUS databases. Charts 4c and 4d show the ages and values of standard deviations for errors of the proposed method on NUS-8camera database
TABLE 3 Parameters of all databases for the methods of Tables 1 and 2
TABLE 3 Parameters of all databases for the methods of Tables 1 and 2
TABLE 4 The reproduction angular error of different colour constancy algorithms evaluated on ColorChecker Gehler-Shi database [30, 69]
TABLE 4 The reproduction angular error of different colour constancy algorithms evaluated on ColorChecker Gehler-Shi database [30, 69]
Therefore, the best performance of the proposed algorithm is ir certain ranges or values for both two parameters. In addition these ranges are robust to change of databases or cameras.
Therefore, the best performance of the proposed algorithm is ir certain ranges or values for both two parameters. In addition these ranges are robust to change of databases or cameras.
FIGURE 5 Comparison of the proposed method (WCS), FFCC [49], GI [5], Cheng [6] and Bright Pixel method (BP) [15] to some images of NUS database and linear ColorChecker database. For each image, the camera type is displayed in top left and the recovery angular error for proposed (WCS) and another metho are displayed in bottom left and bottom right corners of each image, respectively
FIGURE 5 Comparison of the proposed method (WCS), FFCC [49], GI [5], Cheng [6] and Bright Pixel method (BP) [15] to some images of NUS database and linear ColorChecker database. For each image, the camera type is displayed in top left and the recovery angular error for proposed (WCS) and another metho are displayed in bottom left and bottom right corners of each image, respectively
Related topics:
Computer ScienceArtificial IntelligenceChemistryComputer VisionColor ConstancyElectrical and Electronic Engineering
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved