Design and evaluation of an intelligent sorting system for bell pepper using deep convolutional neural networks.

Homogeneity of appearance attributes of bell peppers is essential for consumers and food industries. This research aimed to develop an in-line sorting system using a deep convolutional neural network (DCNN) which is considered the state-of-the-art in the field of machine vision-based classifications, for grading bell peppers into five classes. According to export standards, the crop should be graded based on maturity stage and size. For that, the fully connected layer in the ResNet50 architecture of DCNN was replaced with a developed classifier block, including a global average-pooling layer, dense layers, batch normalization, and dropout layer. The developed model was trained and evaluated through the five-fold cross-validation method. The required processing time to classify each sample in the proposed model was estimated as 4 ms which is fast enough for real-time applications. Accordingly, the DCNN model was integrated with a machine vision-based designed sorting machine. Then, the developed system was evaluated in the in-line phase. The performance parameters in the in-line phase include accuracy, precision, sensitivity, specificity, F1-score, and overall accuracies were 98.7%, 97%, 96.9%, 99%, 96.9%, and 96.9%, respectively. The total rate of sorting the bell pepper was also measured as approximately 3000 sample/h with one sorting line. The proposed sorting system demonstrates a very good capability that allows it to be used in industrial applications. PRACTICAL APPLICATION: A developed intelligent model was integrated with a machine vision-based designed sorting machine for bell peppers. The developed system can sort the crop according to export criteria with an accuracy of 96.9%. The proposed sorting system demonstrated a very good capability that allows it to be used in industrial applications.

A critical review on intelligent and active packaging in the food industry: Research and development.

The emergence of many new food products on the market with need of consumers to constantly monitor their quality until consuming, in addition to the necessity for reducing food corruption during preservation time, have led to the development of some modern packaging technologies such as intelligent packaging (IP) and active packaging (AP). The benefits of IP are detecting defects, quality monitoring and tracking the packaged food products to control the storage conditions from the production stage to the consumption stage by using various sensors and indicators such as time-temperature indicators (TTIs), gas indicators, humidity sensors, optical, calorimetric and electrochemical biosensors. While, AP helps to increase the shelf-life of products by using absorbing and diffusion systems for various materials like carbon dioxide, oxygen, and ethanol. However, there are some important issues over these emerging technologies including cost, marketability, consumer acceptance, safety and organoleptic quality of the food and emphatically environmental safety concerns. Therefore, future researches should be conducted to solve these problems and to prompt applications of IP and AP in the food industry. This paper reviews the latest innovations in these advanced packaging technologies and their applications in food industry. The IP systems namely indicators, barcoding techniques, radio frequency identification systems, sensors and biosensor are reviewed and then the latest innovations in AP methods including scavengers, diffusion systems and antimicrobial packaging are reviewed in detail.