|
| 1 | +# Color_Quantization |
| 2 | + |
| 3 | + Program to perform color quantization using four k-means variants: |
| 4 | + 1) Batch K-Means (Forgy, 1965 and Lloyd, 1982) |
| 5 | + 2) Incremental Batch K-Means (Linde et al., 1980) |
| 6 | + 3) Online K-Means (MacQueen, 1967) |
| 7 | + 4) Incremental Online K-Means (Abernathy & Celebi, 2022) |
| 8 | + |
| 9 | + Authors: Amber Abernathy & M. Emre Celebi |
| 10 | + |
| 11 | + Contact email: ecelebi@uca.edu |
| 12 | + |
| 13 | + If you find this program useful, please cite: |
| 14 | + A. D. Abernathy and M. E. Celebi, |
| 15 | + The Incremental Online K-Means Clustering Algorithm |
| 16 | + and Its Application to Color Quantization, |
| 17 | + Expert Systems with Applications, |
| 18 | + in press, https://doi.org/10.1016/j.eswa.2022.117927, 2022. |
| 19 | + |
| 20 | + Compilation: |
| 21 | + g++ -O3 -std=c++11 -o test_km_algs test_km_algs.cpp -lm |
| 22 | + |
| 23 | + or |
| 24 | + |
| 25 | + g++ -Ofast -std=c++11 -o test_km_algs test_km_algs.cpp -lm |
| 26 | + |
| 27 | + Displaying command-line options: |
| 28 | + ./test_km_algs |
| 29 | + |
| 30 | + Notes: |
| 31 | + 1) The program requires C++11 or later due to its use of <chrono> (for |
| 32 | + measuring time). If your compiler does not support C++11, you should |
| 33 | + measure time another way or eliminate time measurement. |
| 34 | + 2) This program does not use any object-oriented features of C++. |
| 35 | + Therefore, it should be straightforward to port it to C or Java. |
| 36 | + |
0 commit comments