Automated particle identification through regression analysis of size, shape and colour

J. C. Rodriguez Luna; J. M. Cooper; S. L. Neale

doi:10.1117/12.2211107

6 April 2016 Automated particle identification through regression analysis of size, shape and colour

J. C. Rodriguez Luna, J. M. Cooper, S. L. Neale

Proceedings Volume 9711, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues IX; 97110R (2016) https://doi.org/10.1117/12.2211107
Event: SPIE BiOS, 2016, San Francisco, California, United States

Abstract

Rapid point of care diagnostic tests and tests to provide therapeutic information are now available for a range of specific conditions from the measurement of blood glucose levels for diabetes to card agglutination tests for parasitic infections. Due to a lack of specificity these test are often then backed up by more conventional lab based diagnostic methods for example a card agglutination test may be carried out for a suspected parasitic infection in the field and if positive a blood sample can then be sent to a lab for confirmation. The eventual diagnosis is often achieved by microscopic examination of the sample. In this paper we propose a computerized vision system for aiding in the diagnostic process; this system used a novel particle recognition algorithm to improve specificity and speed during the diagnostic process. We will show the detection and classification of different types of cells in a diluted blood sample using regression analysis of their size, shape and colour. The first step is to define the objects to be tracked by a Gaussian Mixture Model for background subtraction and binary opening and closing for noise suppression. After subtracting the objects of interest from the background the next challenge is to predict if a given object belongs to a certain category or not. This is a classification problem, and the output of the algorithm is a Boolean value (true/false). As such the computer program should be able to "predict" with reasonable level of confidence if a given particle belongs to the kind we are looking for or not. We show the use of a binary logistic regression analysis with three continuous predictors: size, shape and color histogram. The results suggest this variables could be very useful in a logistic regression equation as they proved to have a relatively high predictive value on their own.

Citation Download Citation

J. C. Rodriguez Luna, J. M. Cooper, and S. L. Neale "Automated particle identification through regression analysis of size, shape and colour", Proc. SPIE 9711, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues IX, 97110R (6 April 2016); https://doi.org/10.1117/12.2211107

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available