TY  - JOUR
T1  - Identification of Medical Plants Using Genetic Algorithm and
Recurrent Neural Network
AU - Malarkhodi, S. 
JO  - Asian Journal of Information Technology
VL  - 15
IS  - 23
SP  - 4934
EP  - 4944
PY  - 2016
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2016.4934.4944
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2016.4934.4944
KW  - Medicinal leaves
KW  -feature extraction
KW  -genetic algorithm
KW  -recurrent neural network
KW  -support vector machine
AB  - Medicinal leaves widely used in medicine, cosmetic and pharamastic cosmetic industry. Medicinal
leaves are verge of extinction. Presently identification of the type of medicinal leaves is still done manually and
it will be occur to human error. Leaves are the key components of plants. The leaf extracts of many medicinal
plants can cure various diseases and alternating for allopathic medicinal system now a days. In this method an
extraction of shape, color, morphology and texture features from leaf image. Next step is using Genetic algorithm
to feature selection process. Final step training a Recurrent Neural Network (RNN) classifier and Support Vector
Machine (SVM) to display the leaf name and uses. The results of the flavia database leaf achieved an average
accuracy is 95.53% from the ACO-based approach. Same method used to find medical leaf using Genetic
Algorithm an average accuracy is 91.30%. This research has been implemented using the image processing and
neural network toolbox in MATLAB.
ER  -