Selection of Image Texture Analysis and Color Model in the Advanced Image Processing of Thermal Images of Horses following Exercise

Abstract

As the detection of horse state after exercise is constantly developing, a link between blood biomarkers and infrared thermography (IRT) was investigated using advanced image texture analysis. The aim of the study was to determine which combinations of RGB (red–green–blue), YUI (brightness–UV–components), YIQ (brightness–IQ–components), and HSB (hue–saturation–brightness) color models, components, and texture features are related to the blood biomarkers of exercise effect. Twelve Polish warmblood horses underwent standardized exercise tests for six consecutive days. Both thermal images and blood samples were collected before and after each test. All 144 obtained IRT images were analyzed independently for 12 color components in four color models using eight texture-feature approaches, including 88 features. The similarity between blood biomarker levels and texture features was determined using linear regression models. In the horses’ thoracolumbar region, 12 texture features (nine in RGB, one in YIQ, and two in HSB) were related to blood biomarkers. Variance, sum of squares, and sum of variance in the RGB were highly repeatable between image processing protocols. The combination of two approaches of image texture (histogram statistics and gray-level co-occurrence matrix) and two color models (RGB, YIQ), should be considered in the application of digital image processing of equine IRT.

Object-based Classification of Natural Scenes Using Machine Learning Methods

“…HSV is an abbreviation for 'Hue Saturation Value' [49]. It is sometimes referred to as HIS (for intensity) [50] and HSB (for brightness) [51]. An HSV color wheel [52] can take the shape of a cylinder or a cone, but it always has these 3 parts.…”

An Image Processing Techniques Used for Soil Moisture Inspection and Classification

“…We next performed the texture and characteristics analysis, then the undesirable regions (background) of the picture were extracted, and the pixel (surface feature) value was black color (#0000) [15]. It represents the cropping segmentation technique that dramatically decreases the portion of data and filters out ineffective information while keeping the critical element of consistency features in the good parts [13,14].…”

“…Black and white color imaging techniques are executed to decide the residue cover over the soil surface, and wavelength and filters are identified. They claim that imaging methodology proposed success in replacing human investigating fields [4] [12] [14].…”

“…The images were produced using a Charge Coupled Devices (CCD) coloring camera, and the investigation examined exterior textures. Furthermore, nearly earlier studies above indicated that surface image examination to quantify external texture differences from images is possible [9] [14] because the image surface meditates the changes in intensity pixel significances, which may include information about the coloring and electromagnetic range of entities [6] [9]. However, most of the techniques described above were designed to detect images exclusively from the visible range/spectrum (VS), such as RGB.…”

Equine Surface Temperature Before and After Exercise Using Thermographic Images

“…Equines control this increase through sweating, vasodilation, and tachypnea [1]. In this sense, detecting the state of the equine after exercise is essential to maximize athletic performance [7]. One of the main characteristics of equine training is the significant influence of the thermal environment on sports performance, as they are outdoor activities, thus allowing direct exposure to climatic variables [8].…”