| Summary: | In the previous era, sickness and diseases were treated using traditional herbs since medical technology had yet to be developed. Due to massive development in medicine, more herbs species are facing the risk of extinction due to not being well conserved. This paper describes the development of a graphical user interface (GUI) for identification of Malaysian Herbs Plant from image data using MATLAB. Besides, the GUI development will contribute to the database development of herbs species that are much needed to systematically stores relevant information. It can provide valuable knowledge for society. It is quite challenging for people including the herbs' expert, to differentiate herbs' plants since there are too many of them and limited knowledge and experiences. Fortunately, this can be overcome by using image processing approaches specifically image segmentation and classification. A set of image data consists of five types of Malaysian herbs plants is used in this study. The types are Rerama, Sirih, Mexican Mint, Belalai Gajah dan Senduduk. Sobel edge detection operator is a segmentation approach that works by computing the gradient of image intensity at each point and measuring the pixel value changes in horizontal and vertical directions by using two convolution masks. The shape and texture features are used in multiclass Support Vector Machine (SVM) model to classify the species of the herbs. Results show that performance of model are 95.56% for accuracy and sensitivity, 98.89% for specificity, 95.78% for precision, and 94.53% for Matthews correlation. The demonstration of image data shows the effectiveness of the developed GUI in classifying the five types of herbs. © Published under licence by IOP Publishing Ltd.
|
|---|