Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design
The performance of signal processing systems based on vector quantization depends on codebook design. In the image compression scenario, the quality of the reconstructed images depends on the codebooks used. In this paper, alternatives are proposed for accelerating families of fuzzy K-means algorith...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/11/1963 |
| _version_ | 1811187240336883712 |
|---|---|
| author | Edson Mata Silvio Bandeira Paulo de Mattos Neto Waslon Lopes Francisco Madeiro |
| author_facet | Edson Mata Silvio Bandeira Paulo de Mattos Neto Waslon Lopes Francisco Madeiro |
| author_sort | Edson Mata |
| collection | DOAJ |
| description | The performance of signal processing systems based on vector quantization depends on codebook design. In the image compression scenario, the quality of the reconstructed images depends on the codebooks used. In this paper, alternatives are proposed for accelerating families of fuzzy K-means algorithms for codebook design. The acceleration is obtained by reducing the number of iterations of the algorithms and applying efficient nearest neighbor search techniques. Simulation results concerning image vector quantization have shown that the acceleration obtained so far does not decrease the quality of the reconstructed images. Codebook design time savings up to about 40% are obtained by the accelerated versions with respect to the original versions of the algorithms. |
| first_indexed | 2024-04-11T13:59:55Z |
| format | Article |
| id | doaj.art-0c8dd994ab214ea0a3cf26e9b91027ee |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:59:55Z |
| publishDate | 2016-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0c8dd994ab214ea0a3cf26e9b91027ee2022-12-22T04:20:09ZengMDPI AGSensors1424-82202016-11-011611196310.3390/s16111963s16111963Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook DesignEdson Mata0Silvio Bandeira1Paulo de Mattos Neto2Waslon Lopes3Francisco Madeiro4Center of Science and Technology, Catholic University of Pernambuco (UNICAP), Recife 50050-900, BrazilCenter of Science and Technology, Catholic University of Pernambuco (UNICAP), Recife 50050-900, BrazilCentro de Informática, Universidade Federal de Pernambuco (UFPE), Recife 50740-560, BrazilDepartment of Electrical Engineering, Center of Alternative and Renewable Energy, Federal University of Paraíba (UFPB), João Pessoa 58038-130, BrazilCenter of Science and Technology, Catholic University of Pernambuco (UNICAP), Recife 50050-900, BrazilThe performance of signal processing systems based on vector quantization depends on codebook design. In the image compression scenario, the quality of the reconstructed images depends on the codebooks used. In this paper, alternatives are proposed for accelerating families of fuzzy K-means algorithms for codebook design. The acceleration is obtained by reducing the number of iterations of the algorithms and applying efficient nearest neighbor search techniques. Simulation results concerning image vector quantization have shown that the acceleration obtained so far does not decrease the quality of the reconstructed images. Codebook design time savings up to about 40% are obtained by the accelerated versions with respect to the original versions of the algorithms.http://www.mdpi.com/1424-8220/16/11/1963fuzzy K-meansvector quantizationcomputational complexity |
| spellingShingle | Edson Mata Silvio Bandeira Paulo de Mattos Neto Waslon Lopes Francisco Madeiro Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design Sensors fuzzy K-means vector quantization computational complexity |
| title | Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design |
| title_full | Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design |
| title_fullStr | Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design |
| title_full_unstemmed | Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design |
| title_short | Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design |
| title_sort | accelerating families of fuzzy k means algorithms for vector quantization codebook design |
| topic | fuzzy K-means vector quantization computational complexity |
| url | http://www.mdpi.com/1424-8220/16/11/1963 |
| work_keys_str_mv | AT edsonmata acceleratingfamiliesoffuzzykmeansalgorithmsforvectorquantizationcodebookdesign AT silviobandeira acceleratingfamiliesoffuzzykmeansalgorithmsforvectorquantizationcodebookdesign AT paulodemattosneto acceleratingfamiliesoffuzzykmeansalgorithmsforvectorquantizationcodebookdesign AT waslonlopes acceleratingfamiliesoffuzzykmeansalgorithmsforvectorquantizationcodebookdesign AT franciscomadeiro acceleratingfamiliesoffuzzykmeansalgorithmsforvectorquantizationcodebookdesign |