Image-based Discrimination of Ultrasound-Assisted Frozen Meat Using Inception-v۳

Categorizing images based on ultrasound power levels can be difficult because of thenuanced differences in image quality. Ultrasound technology utilizes high-frequency soundwaves to generate cavitation bubbles within food structures, and the characteristics of thesebubbles can vary depending on the power levels employed. The objective of this research is toinvestigate the possible applications of deep learning algorithms in categorizing sonicated meatsamples according to their quality attributes, including cooking loss, thawing loss, cutting force,color, and texture. The findings could offer significant insights into the utilization of deeplearning algorithms for analyzing meat quality data and their potential in creating intelligentmeat processing systems. Through training a CNN model on a dataset of images categorizedby ultrasound power levels, the model can identify and comprehend patterns and featuresrelated to specific power levels. The model achieves an accuracy rate of ۹۷.۷۵% for identifyingthawed samples and ۹۷.۶۸% for cooked ones. The model's impressive performance inclassifying the images highlights its capacity to accurately distinguish subtle variations in imagequality and clarity.

کلیدواژه ها:

Deep Learning ، Ultrasound ، GoogLeNet ، Inception V۳