Image compression with discriminative dictionaries
| Autor: | Michael Gabb, Roland Schweiger, Markus Thom, Christian Feller, Albrecht Rothermel, Raimar Wagner |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Computer science
business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Top-hat transform Pattern recognition Data_CODINGANDINFORMATIONTHEORY computer.file_format Convolutional neural network JPEG Wavelet Computer Science::Computer Vision and Pattern Recognition Computer Science::Multimedia JPEG 2000 Discrete cosine transform Computer vision Artificial intelligence business computer Image compression Data compression |
| Zdroj: | ICCE-Berlin |
| DOI: | 10.1109/icce-berlin.2013.6698022 |
| Popis: | Common image compression algorithms like JPEG or JPEG2000 transform the individual pixel values into a domain that favors a compact representation. In contrast to the fixed DCT or Wavelet domains, recent efforts were made on image coding with learned overcomplete dictionaries. In this work, we investigate the question whether dictionaries based on classification features are usable for image compression. We show that, despite their original purpose is to extract discriminative features within a Convolutional Neural Network, these features are capable of reaching competitive compression results when combined with a sparsity promoting coding scheme. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|