Open Access Open Access  Restricted Access Subscription or Fee Access

Image Processing for Leaf Recognition Using Neural Network Algorithm

Hashem Bagheronezhad, Faramarz Sadeghi

Abstract



Plants are one of the most important and most usable of resources for people in the different fields, so it is important to distinguish between plant species and it called as detection system. So far, this task was carried out by expert botanists which this task is onerous and time-consuming which in addition to, this task has the memory loss and the human error, thus the researchers tried to fix this flaws using artificial intelligence algorithms. For this purpose, we present a method for identifying the leaf and plant species, which includes pre-processing, feature extraction, training, and classification. In this paper, we combine the useful features of all three feature categories (leaf shape, leaf texture, leaf color) and provide a system for identifying a large number of plant species. At the end, the feature vectors will be formed and then we classify them using the feed-forward back-propagation multi-layer perceptron artificial neural network algorithm and compare the results with similar methods in this field. The results are evidence of the proper performance of this system for a large number of species in different conditions, such as pests, seasons changes and lighting.

Keywords


leaf recognition, artificial neural network, image processing, feature extraction.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.