International Journal of Advanced Networking and Applications

Open Access Open Access  Restricted Access Subscription Access

Performance Analysis of Image Coders, ANN, DTCWT


Affiliations
1 REVA University, Yelahanka, Bengaluru, India
 

Data compression plays a very important role in storage and transmission of information. High storage and transmission requirements leads us to develop better digital image compression techniques. The wavelet analysis like Discrete Wavelet Transform (DWT) alone does not actually compress a signal. Therefore there will be need of the coding techniques along with wavelet analysis of an image in order to compress the data. The problems of Discrete Wavelet Transforms can be overcome with the uses of Dual Tree Complex Wavelet Transform (DTCWT). Proposed work uses the encoding techniques like Neural networks can helps to train the data in efficient ways without missing any information and it also helps to handle noisy data or missing data. Continuous training of neural networks helps in produce efficient transmission and also to produce generalized solutions. It also helps in reducing non-linearity. Proposed algorithm has been designed and tested with different quality image and analysis has been carried out in MATLAB.

Keywords

DWT, DTCWT, Neural Networks and RNN.
User
Notifications
Font Size

  • K. Indira devi ; R. shanmugalakshmi: Dual Tree Complex Wavelet Transform Based Image Compression Using Threshoulding. APRN Journal of Engineering and Applied Sciences, Vol. 10,2015,ISSN 1819-6608.

  • QiuSheng Lian; Yan Yan Gao; Lin Li; PengPeng Hao: Image Compressed Sensing based on DTCWT, IEEE,2008.

  • Lahence Mitiche; Amel baba Houda; Hilal Naimi: Medical Image Denoising using DTCWT complex thresholding, IEEE Jordan conference on Applied Electrical Engineering and Computing Technologies, 2011.

  • Li Hui Fang; Miao Guo Feng; Xu Hou Jie: Image Compression using DTCWT, International Conference of Information Science and Management Engineering, 2010.

  • George Toderci; Sean M. O’Malley; Sung Jin Hwang; Damien Vincent: Variable Rate Image Compression with Recurrent Neural Networks, ICLR, 2016.

  • Aaron van den Oord; Nal Kalchbrenner; Koray Kavukcuoglu: Pixel Recurrent Neural Networks , International Confrence on Deep Machine Learning, USA, 2016.

  • Pingo pan; Zhongwn Xu; Yi Yang; Fei Wu: Hierarchical Recurrent Neural Encoder for video representation with application to Captioning, Computer Vision Foundation IEEE, 2013.

  • D. Srinivasulu Reddy; S. Vardarajan; M. N. Giriprasad: 2D DTCWT, Contemporary Engineering SCiences, Vol. 5, 2012,127-136.

  • Liang Lu; Xingxing Zhang; Kyunghyun Cho: A study of Recurrent Neural encoder and decoder for large vocabulary speech recognition, Natural Speech Technology, EPSRC.


Abstract Views: 192

PDF Views: 0




  • Performance Analysis of Image Coders, ANN, DTCWT

Abstract Views: 192  |  PDF Views: 0

Authors

V. T. Manjunatha
REVA University, Yelahanka, Bengaluru, India
M. Vinayaka Murthy
REVA University, Yelahanka, Bengaluru, India

Abstract


Data compression plays a very important role in storage and transmission of information. High storage and transmission requirements leads us to develop better digital image compression techniques. The wavelet analysis like Discrete Wavelet Transform (DWT) alone does not actually compress a signal. Therefore there will be need of the coding techniques along with wavelet analysis of an image in order to compress the data. The problems of Discrete Wavelet Transforms can be overcome with the uses of Dual Tree Complex Wavelet Transform (DTCWT). Proposed work uses the encoding techniques like Neural networks can helps to train the data in efficient ways without missing any information and it also helps to handle noisy data or missing data. Continuous training of neural networks helps in produce efficient transmission and also to produce generalized solutions. It also helps in reducing non-linearity. Proposed algorithm has been designed and tested with different quality image and analysis has been carried out in MATLAB.

Keywords


DWT, DTCWT, Neural Networks and RNN.

References