DefinePK hosts the largest index of Pakistani journals, research articles, news headlines, and videos. It also offers chapter-level book search.
Title: Design and implementation of an algorithm for plants identification and classification based on physical characteristics of their leaves using computer vision
Authors: Jose Salgado Patron, Diego Sendoya-Losada, Faiber Robayo-Betancourt
Journal: ARPN Journal of Engineering and Applied Sciences
Publisher: Khyber Medical College, Peshawar
Country: Pakistan
Year: 2018
Volume: 13
Issue: 5
Language: English
In this paper, it’s described an algorithm for plants identification based on leaves physical features using image processing techniques and the feed forward neural network specialized on patterns recognition. As fundamental step, the sobel operator is used to highlight the leaves boundaries and veins. After obtaining those features, the new image is transfer to the frequency space through the wavelet transform as basis for the main vector of every sample. Finally, the results are evaluated according to percentage of samples correctly identified. The algorithm is adapted to a visual interface that allows the user to observe the steps of the image processing and get the leaf information.
Loading PDF...
Loading Statistics...