![]() ![]() This compression allows transmission of image at very low bandwidths and minimizes the space requirement for storage of this data. Image compression is the process of effectively coding digital images to reduce the number of bits required to represent an image. Usually the amount of data associated with visual information is so large that its storage requires enormous memory and its transmission requires high bandwidths. IntroductionÄigital image compression plays an extremely important role in the transmission and storage of digital image data. The evaluation of objective and subjective quality of reconstructed images also proves that our DNN achieves better generalization as most of the images are never seen by the network before. Experiments performed on standard real world images show that using ReLUs instead of logistic sigmoid units speeds up the training of the DNN by converging markedly faster. The introduction of the ReLUs establishes an efficient gradient propagation, induces sparsity in the proposed network, and is efficient in terms of computations making these networks suitable for real time compression systems. The use of ReLUs which map more plausibly to biological neurons, makes the training of our DNN significantly faster, shortens the encoding/decoding time, and improves its generalization ability. We aim for a DNN for image compression purpose that has better generalization property and reduced training time and support real time operation. We tend to exploit the DNNs capabilities to find a reasonable estimate of the underlying compression/decompression relationships. A compression technique for still digital images is proposed with deep neural networks (DNNs) employing rectified linear units (ReLUs).
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |