Abstract
The study focuses on the use of the HSV (Hue, Saturation, Value) color model for image processing tasks, specifically in recognizing objects such as tomatoes. Unlike the RGB model, where color information is strongly tied to intensity values of red, green, and blue, the HSV model separates color tone, saturation, and brightness. This makes it more effective for analyzing visual signals, as the human visual system is more sensitive to brightness than to chromaticity. The research describes the process of converting RGB signals to the HSV model, which allows brightness to be represented with higher resolution and improves the detection of color-based objects. The HSV coordinates are defined as follows: hue determines the color tone and is expressed in a range of 0°-360°, saturation defines the intensity of the color (0-100%), and value indicates brightness, also within a 0-100% range. By applying this transformation, the study provides a method for more reliable recognition of objects based on their color features under varying illumination conditions. This approach enhances image analysis tasks, offering a practical framework for applications in computer vision, agriculture, and automation, where accurate color recognition is essential.