Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network
When we compress a large amount of data, we face the problem of the time it takes to compress it. Moreover, we cannot predict how effective the compression performance will be. Therefore, we are not able to choose the best algorithm to compress the data to its minimum size. According to the Kolmogor...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/4/504 |
| _version_ | 1797480946451087360 |
|---|---|
| author | Shinichi Yamagiwa Wenjia Yang Koichi Wada |
| author_facet | Shinichi Yamagiwa Wenjia Yang Koichi Wada |
| author_sort | Shinichi Yamagiwa |
| collection | DOAJ |
| description | When we compress a large amount of data, we face the problem of the time it takes to compress it. Moreover, we cannot predict how effective the compression performance will be. Therefore, we are not able to choose the best algorithm to compress the data to its minimum size. According to the Kolmogorov complexity, the compression performances of the algorithms implemented in the available compression programs in the system differ. Thus, it is impossible to deliberately select the best compression program before we try the compression operation. From this background, this paper proposes a method with a principal component analysis (PCA) and a deep neural network (DNN) to predict the entropy of data to be compressed. The method infers an appropriate compression program in the system for each data block of the input data and achieves a good compression ratio without trying to compress the entire amount of data at once. This paper especially focuses on lossless compression for image data, focusing on the image blocks. Through experimental evaluation, this paper shows the reasonable compression performance when the proposed method is applied rather than when a compression program randomly selected is applied to the entire dataset. |
| first_indexed | 2024-03-09T22:07:29Z |
| format | Article |
| id | doaj.art-751d9610c1214282a0e74faf72712178 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T22:07:29Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-751d9610c1214282a0e74faf727121782023-11-23T19:38:18ZengMDPI AGElectronics2079-92922022-02-0111450410.3390/electronics11040504Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural NetworkShinichi Yamagiwa0Wenjia Yang1Koichi Wada2Faculty of Engineering, Information and Systems, University of Tsukuba, 1-1-1 Tennodai, Tsukuba, Ibaraki 305-8573, JapanMaster’s Program in Information and Systems and Computer Science, University of Tsukuba, 1-1-1 Tennodai, Tsukuba, Ibaraki 305-8573, JapanFaculty of Engineering, Information and Systems, University of Tsukuba, 1-1-1 Tennodai, Tsukuba, Ibaraki 305-8573, JapanWhen we compress a large amount of data, we face the problem of the time it takes to compress it. Moreover, we cannot predict how effective the compression performance will be. Therefore, we are not able to choose the best algorithm to compress the data to its minimum size. According to the Kolmogorov complexity, the compression performances of the algorithms implemented in the available compression programs in the system differ. Thus, it is impossible to deliberately select the best compression program before we try the compression operation. From this background, this paper proposes a method with a principal component analysis (PCA) and a deep neural network (DNN) to predict the entropy of data to be compressed. The method infers an appropriate compression program in the system for each data block of the input data and achieves a good compression ratio without trying to compress the entire amount of data at once. This paper especially focuses on lossless compression for image data, focusing on the image blocks. Through experimental evaluation, this paper shows the reasonable compression performance when the proposed method is applied rather than when a compression program randomly selected is applied to the entire dataset.https://www.mdpi.com/2079-9292/11/4/504lossless data compressionKolmogorov complexitydeep neural network |
| spellingShingle | Shinichi Yamagiwa Wenjia Yang Koichi Wada Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network Electronics lossless data compression Kolmogorov complexity deep neural network |
| title | Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network |
| title_full | Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network |
| title_fullStr | Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network |
| title_full_unstemmed | Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network |
| title_short | Adaptive Lossless Image Data Compression Method Inferring Data Entropy by Applying Deep Neural Network |
| title_sort | adaptive lossless image data compression method inferring data entropy by applying deep neural network |
| topic | lossless data compression Kolmogorov complexity deep neural network |
| url | https://www.mdpi.com/2079-9292/11/4/504 |
| work_keys_str_mv | AT shinichiyamagiwa adaptivelosslessimagedatacompressionmethodinferringdataentropybyapplyingdeepneuralnetwork AT wenjiayang adaptivelosslessimagedatacompressionmethodinferringdataentropybyapplyingdeepneuralnetwork AT koichiwada adaptivelosslessimagedatacompressionmethodinferringdataentropybyapplyingdeepneuralnetwork |