Noise Removal and Enhancement of Digital Mammographic Images for Visual Screening
Muhammad Hameed Siddiqi

Muhammad Hameed Siddiqi*, Department of Computer Science, Jouf University, Sakaka, Aljouf, Kingdom of Saudi Arabia.

Manuscript received on February 10, 2020. | Revised Manuscript received on February 20, 2020. | Manuscript published on March 30, 2020. | PP: 1772-1779 | Volume-8 Issue-6, March 2020. | Retrieval Number: F7978038620/2020©BEIESP | DOI: 10.35940/ijrte.F7978.038620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Cancer is one of the most dangerous diseases that if not diagnosed at early stages can lead to death. Cancer is of different types and breast cancer is a known form of it that is prevailing around the world. It is found in almost 11% of the world women population in their life time. The early detection of this type of cancer is essential not only to reduce the life fatalities but also for the human race. Due to some drawbacks and negative impacts, it remains a fascinating concern to recover the pictorial eminence of mammograms at the initial stage by a robust method to examine the cancer in the breast. In this study, we have presented a method of noise destruction and image enrichment by utilizing wavelet transform. The proposed method consisted of three steps. Also, the preprocessing was employed to improve the local divergence in condensed areas in which the improvement parameter delivers the anticipated aspect enrichment. In the proposed method, the effect of artifacts has been solved that is one of the critical issues now a day, which produces during the analyzing of the mammographic image. The proposed algorithm gave best results as compared to the existing works for which less user adjustment parameters are required.
Keywords: Mammographic Image, Noise Removal, Wavelet Transform, Decomposition.
Scope of the Article: Visual Analytics.