Enhancing the Tablet Images using Noise Reduction Algorithms by Analyzing Different Color Models
A.B. Dhivya1, M. Sundaresan2

1A.B. Dhivya *, Department of Information Technology, Bharathiar University, Coimbatore, Tamilnadu, India.
2M. Sundaresan, Department of Information Technology, Bharathiar University, Coimbatore, Tamilnadu, India.
Manuscript received on November 25, 2019. | Revised Manuscript received on December 08, 2019. | Manuscript published on December 30, 2019. | PP: 148-155 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3119129219/2019©BEIESP | DOI: 10.35940/ijeat.B3119.129219
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 (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Unidentified tablets are challenges to both patients and healthcare professionals. Using these unknown tablets results in undesirable reaction of drug and also it is foundation to ill health that leads to death even sometimes. Thus, recognition of unidentified tablets is a significant task in medical industry. Identification of tablets is one of the major concerns for public and pharmacists, which can be carried out by means of either text-based or image-based methods. The tablet identification system is focused on removing noise from the tablet images using algorithms like Independent Component Analysis (ICA) and Discrete Wavelet Packet Transmission (DWPT). The three color space models, i.e., RGB (Red-Green-Blue), YCbCr (Y-Luma, CChroma of blue and red components) and HSV (Hue-SaturationValue) are examined for their efficiency on removing noise from tablets. For each color space model, the two denoising algorithms, ICA and DWPT are analyzed and applied. The result is interpreted using metrics like PSNR, FoM, MSSI and Speed. Experimental results proved that denoising with HSV color space model gives maximum efficiency when used with ICA and DWPT-based tablet identification systems.
Keywords: Color Space Model, Tablet Retrieval, Denoising, Wavelet Packets, ICA, DWPT, Reference Image, Consumer Image.