An egg image noise model for digital visual counting processing

Contactless counting is a suitable technique for the measurement of fragile commodities, acting as a successful tool for industrial production control. Visual counting processing is one of the most common contactless methods for non-invasive measurements. However, the creation of accurate models for processing images in realistic scenarios is still challenging due to the existence of noise in optical sensors. This paper proposes an egg image noise model for digital visual counting processing that incorporates particular aspects of real images in such acquisition systems. The matching function is defined in hue saturation value (HSV) color space, and a classical nearest neighbor cluster classification is utilized for the counting. Validation experiments are executed with low and high diversity test images, and the performance of the proposed model is compared to existing methods. The matching function results suggest that the introduced egg image noise model is able to represent more accurately complex aspects of egg images in an industrial environment. The comparative results show that the proposed model significantly improves digital visual counting, in terms of egg counting errors, and outperforms in 9% the second best method.