A Vegetable Category Recognition System Using Deep Neural Network

In recent years, Ambient Intelligence (AmI) has attracted increased attention within the advanced technology industry in an effort to modernize and develop a more intelligent and reliable information system. Technologies to detect a specific object in images are expected to further expand to wide range of applications, such as car detection functions for intelligent transport system and other systems. Computer vision and pattern recognition are emerging fast and will continue to grow together with local feature detection methods. In this paper, we used the Deep Neural Network (DNN) for object category recognition by extracting and learning the object. We applied deep learning to vegetable object recognition, and explored the Convolutional Neural Network (CNN). From the evaluation results, we found that for vegetable recognition learning process with CNN, 3 million iterations were suitable. The results of learning rate was 99.14% and recognition rate was 97.58%, respectively.