Please use this identifier to cite or link to this item:
Title: Medical tablets identification algorithm
Authors: Ng, Joann Xin Chi
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2019
Abstract: Identifying tablets is very important in the medical world. Many tablets are similar in colour and shape, and it is difficult to identify them through the human eye. Therefore in this paper, an algorithm is developed to aid in the identification of the existing tablets, mainly focusing on using the colour and shape of the unknown tablet. Matric Laboratory (MATLAB) is used to code the algorithm. A database is created based on approximately 200 samples. The algorithm was designed to analyse the colour and the shape of an unknown tablet and match it to the database sample. Points are allocated to each individual database sample that matches the colour and/or shape of the unknown tablet. The algorithm will then identify the top 10 database samples with the highest points. From the top 10 results, the database samples with the highest score will serve as an indication of the unknown tablet. The algorithm is successful to a certain extent in indentifying an unknown tablet based only on the colour and shapes. However, there are different features of the tablets such as wording and size to be considered as well. In this paper, further investigation was also carried out to enhance the algorithm while implementing the wording and size detection methods. Finally some challenging issues are raised for further researches.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
NgXinChiJoann_U1621209H_FYP Final Report.pdf
  Restricted Access
2.84 MBAdobe PDFView/Open

Page view(s) 50

checked on Oct 31, 2020

Download(s) 50

checked on Oct 31, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.