Open Access Open Access  Restricted Access Subscription or Fee Access

A Novel Multi-Wavelet Based Image Filtering Technique for Noise Reduction in Mammographic Medical Images

Swapnil Tamrakar, Abha Choubey


The digital mammographic imagery is often influenced by various types of noises and thus requires application of various filters to denoise the noise level in order to preserve the vital imagery contents. This evidently helps the medical practitioner to improve the image quality of the mammograms and helps them in giving accurate diagnosis. Though there are several works on image denoising algorithm but they aren’t much to pay emphasis over the mammographic images. In terms of application the images of importance are classified into Multispectral Image (used for satellite surveillance), RGB standard colour scheme based Image or other digital versions of the film image i.e., in our case its mammographic image. Here is the point, to every image type there is a different approach for its denoising because there are several factors that count in. In this case of mammographic image denoising, the denoising technique that is to be adopted is based on its affectivity against noises at each resolution level of the microns to enable the micro-classification of the cancerous tissues to that of the bright water dense patches caused by the calcium salts in the mammary glands. Thus, not all methods can be and is effective against the scenario of mammographic image denoising. Also, the mammographic image is influenced by several noise types and no single algorithm can give similar performance range against this noise types. Therefore, in this study we have presented a method to denoise the mammograms with higher accuracy and performance range suited for the denoising applications.


Cite this Article
Swapnil Tamrakar, Abha Choubey, A Novel Multi-Wavelet Based Image Filtering Technique for Noise Reduction in Mammographic Medical Images. Journal of Advanced Database Management & Systems. 2015; 2(1): 12–17p.


Digital mammography, denoising, independent component analysis, wavelet shrinkage

Full Text:



Heinlein P., Drexl J., Schneider W., Integrated Wavelet for Enhancement of Microcalcification in Digital Mammography, IEEE T Med Imag. Mar 2000; 22(3): 402–413p.

Pandey N., Salcic Z., Sivaswamy J., Fuzzy Logic based Microcalcification Detection, Proceedings of the IEEE for Signal Processing Workshop, 2000, 662–671p.

Strickland R. N., Hahn H. L., Wavelet Transforms for Detecting Microcalcifications in Mammograms, IEEE T Med Imag. 1996; 15(2): 218–229p.

Mini M. G., Thomas T., A Neural Network Method for Mammogram Analysis Based on Statistical Features, Proceedings of TENCON. Oct. 2003; 4: 1489–1492p.

Yu S., Guan L., A CAD System for the Automatic Detection of Clustered Microcalcifications in Digitized Mammogram Films, IEEE T Med Imag 2000; 19(2): 115–126p.

Choubey A., Sinha G.R., Choubey S., A Hybrid Filtering Technique in Medical Image Denoising: Blending of Neural Network and Fuzzy Inference, Electronics Computer Technology (ICECT), 2011 3rd International Conference on, 8–10 April 2011; 1: 170–177p. doi: 10.1109/ICECTECH.2011.5941584

Ferreira CBR, Borges DL, Analysis of Mammogram Classification using a Wavelet Transform Decomposition. Pattern Recogn Lett 2003; 24: 973–982p.

Sentelle S., Sentelle C., Sutton MA., Multiresolution-Based Segmentation of Calcifications for the Early Detection of Breast Cancer. Real-Time Imaging 2002; 8: 237–252p.

Nakayama R., Uchiyama Y., Yamamoto K., et al., Computer-aided Diagnosis Scheme using a Filter Bank for Detection of Microcalcification Clusters in Mammograms, IEEE T Biomed Eng. Feb 2006; 53(2): 273–283p.

Paul Bao Lei Zhang, Noise Reduction for Magnetic Resonance Images via Adaptive Multiscale Products Thresholding, IEEE T Med Imag. Sep 2003; 22(9): 1089–1099p

Sameti M., Ward R.K., Morgan-Parkes J., et al. Image Feature Extraction in the Last Screening Mammograms Prior to Detection of Breast Cancer. IEEE J Sel Top Signal Process. Feb 2009; 3(1): 46–52p.

Choubey A, Sinha GR, Rai A., Application of Image Denoising through Comorbid Pixel Regularization Algorithm based on Neuro-Fuzzy Rule. Research & Reviews: Journal of Embedded System & Application, 2014; 2(2).

University of South Florida Digital Mammography, DDSM: Digital Database for Screening Mammography, Available at:


  • There are currently no refbacks.