In this paper a new image processing technique based on Cellular Neural Networks for improving the automatic classification of fruits (in particular, oranges) is introduced. It allows the digitized orange images to be processed in order to highlight some peculiarities of the fruits. In this way the following classification step is greatly simplified and improved. Moreover, the real-time processing characteristic of CNNs is a very advantageous point over the traditional computing resources commonly used in this kind of processing. The proposed task is accomplished by the choice of suitable templates in a simple CNN model. These templates are described and some examples are reported. PUBLISHER: IEEE, Piscataway, NJ, United States
CNN image processing for the automatic classification of oranges
ARENA, Paolo Pietro;
1994-01-01
Abstract
In this paper a new image processing technique based on Cellular Neural Networks for improving the automatic classification of fruits (in particular, oranges) is introduced. It allows the digitized orange images to be processed in order to highlight some peculiarities of the fruits. In this way the following classification step is greatly simplified and improved. Moreover, the real-time processing characteristic of CNNs is a very advantageous point over the traditional computing resources commonly used in this kind of processing. The proposed task is accomplished by the choice of suitable templates in a simple CNN model. These templates are described and some examples are reported. PUBLISHER: IEEE, Piscataway, NJ, United StatesI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.