Design of a neuro fuzzy model for image compression in wavelet domain
- PDF / 782,449 Bytes
- 15 Pages / 516 x 707.75 pts Page_size
- 14 Downloads / 182 Views
Photonirvachak
J. Indian Soc. Remote Sens. (June 2009) 37:185–199
RESEARCH ARTICLE
Design of a Neuro Fuzzy Model for Image Compression in Wavelet Domain Vipula Singh . Navin Rajpal . K. Srikanta Murthy
Received: 21 January 2008 / Accepted : 11 March 2009
Keywords Image compression . Fuzzy vector quantization . Multi resolution analysis . Wavelet transform . Neural network Abstract Image compression forms the backbone for several applications such as storage of images in a database, picture archiving, TV and facsimile transmission, and video conferencing. Compression of images involves taking advantage of the redundancy in the data present within an image. This work evaluates the performance of an image compression system based on fuzzy vector quantization, wavelet-based sub band decomposition and neural network. The vector quantization is often used when high compression ratios are required. The implementation consists of three steps: first, the image is decomposed into a set of sub bands with different resolutions corresponding to different V. Singh ( )1 . N. Rajpal2 . K. S. Murthy3 GGSIPU, New Delhi – 110 403, India ECE Dept PESIT, Bangalore – 560 085, India 2 GGSIPU, New Delhi – 110 403, India 3 IS Dept PESIT, Bangalore – 560 085, India
frequency bands. Different quantization and coding schemes are used for different sub bands based on their statistical properties. In the second step, wavelet coefficients corresponding to the lowest frequency band are compressed by differential pulse code modulation (DPCM) and the coefficients corresponding to higher frequency bands are compressed using neural network. Finally, the result of the second step was used as input to fuzzy vector quantizer. Image quality was compared objectively using mean squared error and peak signal to noise ratio along with the visual appearance. The simulation results show clear performance improvement with respect to decoded picture quality when compared with other image compression techniques (Liu, 2005; Premaraju, 1996).
1
email: [email protected]
Introduction The interest in digital image compression techniques dates back to a few decades. Here we are concerned
186
with minimizing the number of bits required to represent an image primarily for achieving information transmission and storage efficiency. All image compression algorithms strive to remove statistical redundancy and exploit perceptual irrelevancy while reducing the amount of data as much as possible. Over the last few decades, researches have proposed many competing techniques such as prediction coders, transform coders, vector quantizers, trellis-coded quantizers and fractal image representation. However, due to the nature of each scheme, every algorithm has its own advantages and disadvantages. Among all these schemes, however, the discrete cosine transform used in the JPEG standard has an advantage as it is well understood and is quite mature. On the other hand, vector quantization is a more recently developed technique. VQ performance is directly proportional to
Data Loading...
