Application of Machine Learning Using Color and Texture Analysis to Recognize Microwave Vacuum Puffed Pork Snacks

The objective of the study was to create artificial neural networks (ANN) capable highly efficient recognition modified and unmodified puffed pork snacks for purposes obtaining an optimal final product. involved meat produced from papain raw (Psoas major) by means microwave-vacuum puffing (MVP) under specified conditions. were then analyzed using various instruments in order determine their basic chemical composition, color texture. As a result MVP process, moisture-to-protein ratio (MPR) reduced 0.11. A darker reduction hardness approx. 25% observed enzymatically products. Multi-layer perceptron (MLPN) developed texture descriptor training sets (machine learning), which is undoubtedly innovative solution this area.