A neural networks approach to image data compression

Soliman, Hamdy; Omari, Mohammed

doi:10.1016/j.asoc.2004.12.006

Cited by 28 publications

(9 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such variants of ART have also been widely adopted in different engineering applications [27][28][29]. This algorithm selects the first input pattern as the prototype of the first kernel.…”

Section: Clusteringmentioning

confidence: 99%

An incremental adaptive neural network model for online noisy data regression and its application to compartment fire studies

Lee

2011

Applied Soft Computing

View full text Add to dashboard Cite

“…Such variants of ART have also been widely adopted in different engineering applications [27][28][29]. This algorithm selects the first input pattern as the prototype of the first kernel.…”

Section: Clusteringmentioning

confidence: 99%

An incremental adaptive neural network model for online noisy data regression and its application to compartment fire studies

Lee

2011

Applied Soft Computing

View full text Add to dashboard Cite

“…The Apadtive Vector Quantization theory (AVQ) is one of the most recent techniques used in the domain of image compression [7]. In the AVQ image compression-based approach, the input image is divided into equal size sections (subimages), where each section of n 2 pixels is considered as a vector in the encoding space N nxn .…”

Section: A Avqmentioning

confidence: 99%

“…Soliman and Omari [7] proposed a new classification method (Direct Classification) based on Kohonen and ART (Adaptive Resonance Theory) neural nets. In the local codebook approach, each image will have its own codebook, even when the codebooks of same domain images overlap.…”

Section: Direct Classificationmentioning

confidence: 99%

Image compression based on genetic algorithm optimization

Omari

Yaichi

2015

2015 2nd World Symposium on Web Applications and Networking (WSWAN)

Self Cite

View full text Add to dashboard Cite

Image compression has attracted a lot of research since the beginning of Internet era and telecommunication. Enhancing image compression quality and ratio was achieved through several approaches such as neural networks and discrete transforms. However, other heuristic and bio-inspired methods such as genetic algorithms are still under experimentation. In this paper, we introduced a new image compression mechanism based on exploiting the relationship between fractional numbers and their corresponding quotient representation. Each sub-image is mapped to a fractional number based on the RGB representation, and then reduced to an efficient quotient. The appeal of using genetic algorithms is explained by the massive search to find a close fraction that is reduced to short quotient. Our method showed a considerable compression ratio when the least significant bits of each byte are altered, hence, the image quality is preserved while achieving high compression ratio.Index Terms-Fractal image, lossy compression, rational numbers, genetic algorithms.

show abstract

“…Moreover, different image compression techniques were combined with neural network classifier for various applications [15]. A neural network model called direct classification was also suggested; this is a hybrid between a subset of the self-organising Kohonen model and the adaptive resonance theory model to compress the image data [16]. Periodic Vector Quantization algorithm based image compression was suggested previously based on competitive neural networks quantizer and neural networks predictor [17].…”

Section: Introductionmentioning

confidence: 99%

Medical radiographs compression using neural networks and Haar wavelet

Khashman

Dimililer

2009

Ieee Eurocon 2009

View full text Add to dashboard Cite

Efficient storage and transmission of medicalimages in telemedicine is of utmost importance however, this efficiency can be hindered due to storage capacity and constraints on bandwidth. Thus, a medical image may require compression before transmission or storage. Ideal image compression systems must yield high quality compressed images with high compression ratio; this can be achieved using wavelet transform based compression, however, the choice of an optimum compression ratio is difficult as it varies depending on the content of the image. In this paper, a neural network is trained to relate radiograph image contents to their optimum image compression ratio. Once trained, the neural network chooses the ideal Haar wavelet compression ratio of the x-ray images upon their presentation to the network. Experimental results suggest that our proposed system, can be efficiently used to compress radiographs while maintaining high image quality.

show abstract

A neural networks approach to image data compression

Cited by 28 publications

References 2 publications

An incremental adaptive neural network model for online noisy data regression and its application to compartment fire studies

An incremental adaptive neural network model for online noisy data regression and its application to compartment fire studies

Image compression based on genetic algorithm optimization

Medical radiographs compression using neural networks and Haar wavelet

Contact Info

Product

Resources

About