Analysis of beef quality according to color changes using computer vision and white-box machine learning techniques.

The quality of beef products relies on the presence of a cherry red color, as any deviation toward brownish tones indicates a loss in quality. Existing studies typically analyze individual color channels separately, establishing acceptable ranges. In contrast, our proposed approach involves conducting a multivariate analysis of beef color changes using white-box machine learning techniques. Our proposal encompasses three phases. (1) We employed a Computer Vision System (CVS) to capture the color of beef pieces, implementing a color correction pre-processing step within a specially designed cabin. (2) We examined the differences among three color spaces (RGB, HSV, and CIELab*) (3) We evaluated the performance of three white-box classifiers (decision tree, logistic regression, and multivariate normal distributions) for predicting color in both fresh and non-fresh beef. These models demonstrated high accuracy and enabled a comprehensive understanding of the prediction process. Our results affirm that conducting a multivariate analysis yields superior beef color prediction outcomes compared to the conventional practice of analyzing each channel independently.

Measuring water holding capacity in pork meat images using deep learning.

Water holding capacity (WHC) plays an important role when obtaining a high-quality pork meat. This attribute is usually estimated by pressing the meat and measuring the amount of water expelled by the sample and absorbed by a filter paper. In this work, we used the Deep Learning (DL) architecture named U-Net to estimate water holding capacity (WHC) from filter paper images of pork samples obtained using the press method. We evaluated the ability of the U-Net to segment the different regions of the WHC images and, since the images are much larger than the traditional input size of the U-Net, we also evaluated its performance when we change the input size. Results show that U-Net can be used to segment the external and internal areas of the WHC images with great precision, even though the difference in the appearance of these areas is subtle.

Evaluating the diameter of eyedropper tips using a computer vision system / Avaliação do diâmetro de bicos de conta-gotas de colírios por visão computacional

ABSTRACT Purpose: This study aimed to determine the variation in diameters of outer and inner apertures of eyedropper tips using a computer vision system. Standardizing the size of eye drop nozzles is crucial to reduce the treatment cost of chronic eye diseases and to ensure a continued use of medication. An eyedropper volume of >20 µL (maximum storage of the conjunctival sac) causes medication wastage and increases treatment costs. Methods: We measured the diameters of the outer and inner apertures of eyedropper tips and evaluated variations in diameters using a computerized visual inspection system. Results: The computer visual inspection system identified anomalies in the apertures of eyedropper tips that resulted in diameter variations. Conclusions: The results of the present study show discrepancies in diameters of eyedropper tips, suggesting a variation in eyedropper size and medication wastage.

RESUMO Objetivo: Este estudo teve como objetivo determinar a variação dos diâmetros das aberturas externa e interna dos bicos conta-gotas utilizando sistema de visão computacional. A padronização do tamanho dos colírios conta-gotas é importante para reduzir o custo do tratamento de doenças crônicas e garantir o uso contínuo de medicamentos. O volume da gota maior do que 20 µl (volume de armazenamento máximo do saco conjuntival) gera desperdício da medicação e aumenta o custo do tratamento. Métodos: Medimos os diâmetros das aberturas externa e interna das pontas dos conta-gotas e avaliamos as variações no diâmetro usando um sistema de inspeção visual computadorizado. Resultados: O sistema de inspeção visual por computador identificou anomalias nas aberturas dos bicos dos frascos conta-gotas que resultaram em variações de diâmetro. Conclusões: Os resultados do presente estudo mostram discrepâncias nos diâmetros dos bicos dos frascos dos conta-gotas, sugerindo uma variação no tamanho das gotas e no desperdício de remédios.

Design and Validation of a Low-Cost Telepathology System.

OBJECTIVE: This work sought to evaluate the precision and repeatability of a telepathology prototype based on open software and hardware. MATERIALS AND METHODS: A prototype was designed with application in telepathology and telemicroscopy. Accuracy and prototype precision were evaluated by calculating the mean absolute error and the intraclass and repeatability correlation coefficients for a series of 190 displacements at 10, 25, 50, 75, and 100 µm. RESULTS AND CONCLUSIONS: This work developed a low-cost prototype that is accessible, easily reproducible, implementable, and scalable; based on the use of technology created under principles of open software and hardware. A pathologist reviewed the obtained images and found them to be of diagnostic quality. Its excellent repeatability, coupled with its good accuracy, allows for its application in telemicroscopy and static, dynamic, and whole-slide imaging pathology systems.