Corpus ID: 8333448

Image Compression Using Neural Networks

  title={Image Compression Using Neural Networks},
  author={Yahya M. Masalmah and Dr. Jorge Ortiz},
In this project, multilayer neural network will be employed to achieve image compression. The network parameters will be adjusted using different learning rules for comparison purposes. Mainly, the input pixels will be used as target values so that assigned mean square error can be obtained, and then the hidden layer output will be the compressed image. It was noticed that selection between learning algorithms is important as a result of big variations among them with respect to convergence… Expand

Figures from this paper

Neural Network based Complex Image Compression using Modified Levenberg-Marquardt method for Learning
The emergence of artificial neural networks in image processing has led to improvements in image compression. In this paper an adaptive method for image compression based on complexity level of theExpand
A Survey on Image Compression Techniques Using Artificial Neural Networks
This Survey paper covers neural network built on image compression method. Image compression performs an important part incommunication application, to reduce the redundancy of pixels from the image,Expand
Full Resolution Image Compression with Deep Neural Networks
The proposed algorithm is effective in accomplishing better errorcorrection and reducing the storage requirements, and shows better quality of the decompressed images along with less computational capacity. Expand
Artificial Neural Network based Image Compression using
Uncompressed multimedia (graphics, audio and video) data requires considerable storage capacity and transmission bandwidth. Despite rapid progress in mass-storage density, processor speeds, andExpand
Fuzzy Neural Network based Image Compression using Levenberg-Marquardt Algorithm
Uncompressed multimedia (graphics, audio and video) data requires considerable storage capacity and transmission bandwidth. Despite rapid progress in mass-storage density, processor speeds, andExpand
Compression of Monochromatic and Multicolored Image with Neural Network
The ANN algorithm investigated is BEP-SOFM, which uses a Backward Error Propagation algorithm to quickly obtain the initial weights, and then these weights are used to speed up the training time required by the Self-Organizing Feature Map algorithm. Expand
Image Compression Technique Based on Fractal Image Compression Using Neural Network – A Review
This paper explores a unique neural network FIC that is capable of increasing neural network speed and image quality simultaneously and demonstrates the quality of this FIC by demonstrating the simulation findings. Expand
Wavelet Networks Approach for Image Compression
Natural gas whose calorific value is to be determined is illuminated with a light beam that is applied by a measurement head and that defines three measurement bands with different wavelength rangesExpand
New Method to Reduce the Size of Codebook in Vector Quantization of Images
The vector quantization method for image compression inherently requires the generation of a codebook which has to be made available for both the encoding and decoding processes. That necessitatesExpand
Supervised fuzzy and Bayesian classification of high dimensional data: a comparative study
Performance results of the three algorithms are presented on simulated and real remote sensing multispectral data, which show improvement in the classification accuracy using the SFCM technique. Expand


Image compression using multilayer neural networks
A modfied feedback error is proposed to reduce further the training time and to enhance the image quality and the performance superiority of multilayer neural networks compared with that of the two-layer one, especially at high compression ratios. Expand
A neural network based image compression system
It is proposed that vector quantization be implemented for image compression based on neural networks. Separate codebooks for edge and background blocks are designed using Kohonen (1984)Expand
Lossy image compression using a modular structured neural network
  • E. Watanabe, K. Mori
  • Computer Science
  • Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584)
  • 2001
From simulation results it is shown that the proposed compression method gives better compression performance compared with the conventional compression method using a single neural network. Expand
Neural networks-based image compression system
  • H. Nait Charif, F. Salam
  • Computer Science
  • Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems (Cat.No.CH37144)
  • 2000
A comparison in performance sample images shows that the new image compression system improves the image quality when 16/spl times/16-subimages with compression ratio of 16:1. Expand
Neural network approaches to image compression
This paper presents a tutor a overview of neural networks as signal processing tools for image compression due to their massively parallel and distributed architecture. Expand
Image compression using auto-associative neural network and embedded zero-tree coding
  • S. Patnaik, R. Pal
  • Mathematics
  • 2001 IEEE Third Workshop on Signal Processing Advances in Wireless Communications (SPAWC'01). Workshop Proceedings (Cat. No.01EX471)
  • 2001
This paper presents an image compression method using auto-associative neural network and embedded zero-tree coding. The role of the neural network (NN) is to decompose the image stage by stage,Expand
Image compression using a stochastic competitive learning algorithm (SCoLA)
  • A. Bouzerdoum
  • Mathematics, Computer Science
  • Proceedings of the Sixth International Symposium on Signal Processing and its Applications (Cat.No.01EX467)
  • 2001
A new stochastic competitive learning algorithm (SCoLA) is introduced and applied to vector quantization for image compression, finding that SCoLA achieves higher peak signal-to-noise ratios (PSNR) than FSCL. Expand
Image compression using Auto-associative neural network and embedded zero-tree coding, "Third IEEE processing workshop advances in wireless
  • 2001