Deep Autoencoder-Based Image Compression using Multi-Layer Perceptrons
| Autor: | G.G.H.M.T.R. Bandara, R. Siyambalapitiya |
|---|---|
| Přispěvatelé: | Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Deep learning Computer Science::Neural and Evolutionary Computation Pattern recognition Image Compression Deep Learning Autoencoder Backpropagation Algorithm Perceptron Autoencoder Backpropagation Computer Science::Computer Vision and Pattern Recognition E3357039620/2020©BEIESP 2231-2307 Artificial intelligence business Multi layer Image compression |
| Zdroj: | International Journal of Soft Computing and Engineering. 9:1-6 |
| ISSN: | 2231-2307 |
| DOI: | 10.35940/ijsce.e3357.039620 |
| Popis: | The Artificial Neural Network is one of the heavily used alternatives for solving complex problems in machine learning and deep learning. In this research, a deep autoencoder-based multi-layer feed-forward neural network has been proposed to achieve image compression. The proposed neural network splits down a large image into small blocks and each block applies the normalization process as the preprocessing technique. Since this is an autoencoder-based neural network, each normalized block of pixels has been initialized as the input and the output of the neural network. The training process of the proposed network has been done for various block sizes and different saving percentages of various kinds of images by using the backpropagation algorithm. The output of the middle-hidden layer will be the compressed representation for each block of the image. The proposed model has been implemented using Python, Keras, and Tensor flow backend. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|