Fast hybrid fractal image compression using an image feature and neural network

Zhou, Yiming; Zhang, Chao; Zhang, Zengke

doi:10.1016/j.chaos.2006.09.053

Cited by 17 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quality of reconstructed image was evaluated by PSNR defined as follows, and all the experiments were run on a PC with Intel 1.8 GHz processor, Windows XP operating system and VC++ 6.0 language. 2 10 2 2 , , 1 1 (8) where N is the size of the images, , In addition, according to the proposed improved method in Cha.3, it is obvious that the residuals could reveal the edge and texture information in the image; therefore, it may play a better role than the fast algorithm addressed in [5]- [7] (VFC algorithm), the comparison of PSNR performance is shown in Fig. 7 …”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Satellite image compression based on fractal theory

2009

View full text Add to dashboard Cite

Fractal image coding algorithm is a promising technique to improve the storage efficiency for satellite applications, and it can obtain good reconstructed quality with very high compression ratio in contrast with other image compression methods. In this paper, a fractal coding algorithm for satellite image compression is proposed. The framework of this algorithm is simple, so that it can be designed for hardware and applied on satellite conveniently. In addition, some improved methods are also introduced in this paper.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Since the VFC algorithm has not consider the edge and texture information of images much, RFC algorithm is proposed to improve the reconstructed image's quality while the coding process is speeded up greatly [8].…”

Section: Residual-based Fractal Coding (Rfc)mentioning

confidence: 99%

Satellite image compression based on fractal theory

2009

View full text Add to dashboard Cite

show abstract

“…Fast hybrid fractal image compression using an image feature and neural network [14] uses a special neural network to modify the mapping scheme for the sub-blocks in which pixel values fluctuate greatly.…”

Section: Literature Reviewmentioning

confidence: 99%

Fractal based Image Compression Techniques

Kadam¹,

Rathod²

2017

IJCA

View full text Add to dashboard Cite

Fractal image compression offers high compression ratios and quality image reconstruction. It uses various techniques as the fractal with DCT, wavelet, neural network, genetic algorithms, quantum acceleration etc. Additionally, because fractals are infinitely magnifiable, fractal compression is resolution independent and so a single compressed image can be used efficiently for display in any image resolution including resolution higher than the resolution of the original image. Breaking an image into pieces and identifying selfsimilar ones is the main principle of the approach. In this paper, the different issues in fractal image compression as partitioning, larger encoding time, compression ratio, quality of the reconstructed image, decoding time, SSIM(Structured Similarity Index) are discussed and highlighted. The various areas for improvement as larger encoding time and PSNR are also suggested. The various parameters for evaluating the performance of these techniques as PSNR, compression ratio, encoding time, and decoding time are also suggested. Comparison of Fractal techniques for color image, texture and satellite image is done using different parameters as compression time, compression ratio and PSNR. The hybrid method which combines Fractal quad tree with wavelet and Huffman coding is implemented and compared different parameters as compression ratio and the compression time of the proposed method with the existing methods.

show abstract

“…Wu et al [12] uses a two stage genetic algorithm in order to exploit spatial correlation for fractal coding. Yi-Ming Zhou et al [15] proposed a hybrid fractal image compression method based on an image feature and a special neural network (FNFC). Zhou claims that his method is a two-part approach.…”

Section: Fractal Acceleration Techniquesmentioning

confidence: 99%