Open Access Open Access  Restricted Access Subscription or Fee Access

Multispectral Image Denoising using Bi-Directional Recurrent Neural Network with DPCA Algorithm

Ankush Rai


In practices, a Multispectral Images (MSI) image is always prone to corruption by various sources of noises while procuring the images. In this paper we implemented Decomposable Pixel Component Analysis (DPCA) algorithm with recurrent neural network (RNN) which effectively denoised the MSI images. The RNN enables shrinkage of non-reusable data points during DPCA execution and aid it to effectively transform spatial coordinate in a logical manner and reduces the time of execution of the program. The effectiveness of the proposed approach has demonstrated a high performance on the denoising of MSI images.


Cite this Article:
Rai A. Multispectral Image Denoising Using Bi-Directional Recurrent Neural Network with DPCA Algorithm. Journal of Image Processing & Pattern Recognition Progress. 2015; 2(1): 25–30p.


MSI denoising, recurrent neural network, hybrid methodology

Full Text:



Dabov K, Foi A, Katkovnik V, et al. Image denoising by sparse 3D transform-domain collaborative filtering. IEEE Trans. Image Process. 2007; 16: 2080–95p.

Lansel S. DenoiseLab,

Katkovnik V, Foi A, Egiazarian K, et al. From local kernelto nonlocal multiple-model image denoising. International Journal of Computer Vision. 2010; 86: 1–32 p.

Vansteenkiste E, Van der Weken D, Philips W, et al. Perceived image quality measurement of state-of-the-art noise reduction schemes. Lecture Notes in Computer Science ACIVS, Antwerp, Belgium. 2006; 4179: 114–24p.

Dabov K, Foi A, Katkovnik V, et al. Color image denoising via sparse 3D collaborative filtering with grouping constraint in luminance-chrominance space. Proc. IEEE Int. Conf. Image Process. 2007; 1: 313–16p.

Saghri JA, Tescher AG. Near-lossless bandwidth compression for radiometric data. Optical Engineering. 1991; 30: 934–39p.

Epstein B, Hingorani R, Shapiro J, et al. Multispectral klt-wavelet data compression for landsat thematic mapper images. Data Compression Conference. 1992; 200–08p.

Tretter D, Bouman C. Optimal transforms for multispectral and multilayer image coding Image Processing. IEEE Transactions.1995; 4: 296–308p.

Cagnazzo M, Poggi G, Verdoliva L. Region-based transform coding of multispectral images, IEEE Trans. Image Process. 2007;16: 2916–26p.

Foi A, Trimeche M, Katkovnik V, et al. Practical poissonian-gaussian noise modeling and fitting for single-imageraw-data. IEEE Trans. Image Process. 2008; 17:1737–54p.

Foi A. Clipped noisy images: Heteroskedastic modeling and practical denoising. Signal Processing. 2009; 89: 2609–29 p.

Hordley S., Finalyson G., Morovic P. A multi-spectral image database and its application to image rendering across illumination. Image and Graphics 2004. Proceedings. Third International Conference. Dec. 2004, 394–97p.

Finlayson G, Hordley S, Morovic P. Using the Spectra Cubeto build a multispectral image database. Proc. Second European Conference on Color in Graphics, Imaging and Vision, CGIV 2004, Aachen, Germany, April 2004, 268–74 p.

Mahoney M. Text Compression as a Test for Artificial Intelligence. In: AAAI/IAAI. 1999; 486-502.

Bengio Y, Ducharme R, Vincent P. Aneural probabilistic language model. Journal of Machine Learning Research. 2003; 3: 1137–55p.

Goodman Joshua T. A bit of progress in language modeling, extended version. Technical report MSR-TR-2001-72. 2001.

Schwenk H, Gauvain JL. Training Neural NetworkLanguage Models On Very Large Corpora. Proc. Joint ConferenceHLT/EMNLP. October 2005.

Ankush Rai A Novel Decomposable Pixel Component Analysis Algorithm for Automating Multispectral Satellite Image Denoising. Research & Reviews: A Journal of Embedded System & Applications. 2014; 2(3).


  • There are currently no refbacks.

This site has been shifted to