Segmentation and features extraction of Malaysian herbs leaves

• Main Authors: Hadi, N.A (Author), Halim, S.A (Author), Kirubhashankar C.K (Author), Mat Lazim, N.S (Author), Nirmala M. (Author)
• Format: Article
• Language: English
• Published: IOP Publishing Ltd 2021
• Subjects: Boundary points; Classification (of information); Extraction; Features extraction; Geometrical features; Image recognition; Image segmentation; Major axis lengths; Medical practice; Minor axis lengths; Sobel operator; Textural feature
• Online Access: View Fulltext in Publisher; View in Scopus

 In modern medical practice, herbs play a very important role as the source of biotechnology. Therefore, providing a database containing information of these herbs is significant to assist the medicinal practitioners and users. Image recognition, a process that includes image segmentation, features extraction and classification, is one of the methods to develop the database for herbs. This paper focuses on image segmentation and features extraction of 125 images with 1616×1080 pixels of Malaysian Herb Leaves including Sirih, Mexican Mint, Rerama, Belalai Gajah and Senduduk. The images were first segmented using Sobel operator to get the boundary points. Then, 7 geometrical features and 7 textural features were extracted for each image including area, perimeter, major axis length, minor axis length, roundness, smoothness and flatness. The experimental results were obtained using MATLAB R2018a. The results show that Sobel can successfully segment the images and calculates the features of the herb leaves. © 2021 Institute of Physics Publishing. All rights reserved.