Using color histograms and SPA-LDA to classify bacteria

Abstract

In this work, a new approach is proposed to verify the differentiating characteristics of five bacteria (Escherichia coli, Enterococcus faecalis, Streptococcus salivarius, Streptococcus oralis, and Staphylococcus aureus) by using digital images obtained with a simple webcam and variable selection by the Successive Projections Algorithm associated with Linear Discriminant Analysis (SPA-LDA). In this sense, color histograms in the red-green-blue (RGB), hue-saturation-value (HSV), and grayscale channels and their combinations were used as input data, and statistically evaluated by using different multivariate classifiers (Soft Independent Modeling by Class Analogy (SIMCA), Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA), Partial Least Squares Discriminant Analysis (PLS-DA) and Successive Projections Algorithm-Linear Discriminant Analysis (SPA-LDA)). The bacteria strains were cultivated in a nutritive blood agar base layer for 24 h by following the Brazilian Pharmacopoeia, maintaining the status of cell growth and the nature of nutrient solutions under the same conditions. The best result in classification was obtained by using RGB and SPA-LDA, which reached 94 and 100 % of classification accuracy in the training and test sets, respectively. This result is extremely positive from the viewpoint of routine clinical analyses, because it avoids bacterial identification based on phenotypic identification of the causative organism using Gram staining, culture, and biochemical proofs. Therefore, the proposed method presents inherent advantages, promoting a simpler, faster, and low-cost alternative for bacterial identification.

Fruit classification by biogeography‐based optimization and feedforward neural network

“…The colour histogram (CH) was widely harnessed to represent the colour distribution in the chromatic fruit images (De Almeida et al, ). It counted the number of pixels, which had similar colours in a fixed range (Zhang et al, ).…”

Chemometrics‐assisted color histogram‐based analytical systems

“…3 An image capturing device to register the images of the chemical system under consideration. Simple commercial devices include digital cameras, 15,25,30,41,45,52,53,59,60 scanners, 21,28,34,35,39,43,46,[54][55][56][57]61 webcams, 26,29,32,33,[36][37][38]40,42,44,[47][48][49] and smartphones, 17,18,27,31,50,51,58 and the choice of one of them shall be according to its availability in each laboratory or specific need for a given application. However, it is important to note that the portability of systems through the use of smartphones has become a remarkable trend in the literature, mainly in applications involving univariate calibration for colorimetric analysis.…”

A survey for the applications of content-based microscopic image analysis in microorganism classification domains

“…In Almeida et al (2014), five different bacteria are classified using colour features and Successive Projections Algorithm associated with LDA (SPA-LDA) algorithm. 335 images are used in the experiment, where 75% of these images are used for classifier training, and the remaining ones are used for test, finally a 94% and a 100% accuracy are achieved using training and test images, respectively.…”