This study introduces an innovative methodology for estimating food weight from images using advanced segmentation and volumetric estimation. Applying this methodology to an extended set of rotisserie chicken images, the training process was refined and the Exponential Gaussian Regression model was highlighted for its predictive accuracy. Cross-validation confirmed the reliability of the model, with an average error of only 2.86%. These results demonstrate the effectiveness of the model and suggest its applicability in the food industry to improve management and quality control in food preparation, opening avenues for future research in automation and accuracy in volume and weight estimation in various industrial sectors.