Densely connected AutoEncoders for image compression
| Autor: | Song Zebang, Kamata Sei-ichiro |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
business.industry
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Data_CODINGANDINFORMATIONTHEORY 02 engineering and technology computer.file_format Autoencoder JPEG Digital image Feature (computer vision) Compression (functional analysis) JPEG 2000 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business computer Data compression Image compression |
| Zdroj: | Proceedings of the 2nd International Conference on Image and Graphics Processing. |
| DOI: | 10.1145/3313950.3313965 |
| Popis: | Image compression, which is a type of data compression applied to digital images, has been a fundamental research topic for many decades. Recent image techniques produce very large amounts of data, which may make it prohibitive to storage and communications of image data without the use of compression. However, the traditional compression methods, such as JPEG, may introduce the compression artefact problems. Recently, deep learning has achieved great success in many computer vision tasks and is gradually being used in image compression. To solve the compression atrefact problem, in this paper, we present a lossy image compression architecture, which utilizes the advantages of the existing deep learning methods to achieve a high coding efficiency. We design a densely connected autoencoder structure for lossy image compression. Firstly, we design a densely autoencoder structure to get richer feature information from image which can be helpful for compression. Secondly, we design a U-net like network to decrease the distortion caused by compression. Finally, an improved binarizer is adopted to quantize the output of encoder. In low bit rate image compression, experiments show that our method significantly outperforms JPEG and JPEG2000 and can produce a better visual result with sharp edges, rich textures, and fewer artifacts. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|