Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN
Indonesia is a tropical country with a diverse range of plants that ancient people used for traditional medicines. However, the similarity in shape of the leaves became an obstacle to distinguishing them. Therefore, technological advancements are expected to help identify the herbal leaves to use th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Fakultas Ilmu Komputer UMI
2023-08-01
|
| Series: | Ilkom Jurnal Ilmiah |
| Subjects: | |
| Online Access: | https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1759 |
| _version_ | 1827317752166088704 |
|---|---|
| author | Purnawansyah Purnawansyah Aji Prasetya Wibawa Triyanna Widyaningtyas Haviluddin Haviluddin Cholisah Erman Hasihi Ming Foey Teng Herdianti Darwis |
| author_facet | Purnawansyah Purnawansyah Aji Prasetya Wibawa Triyanna Widyaningtyas Haviluddin Haviluddin Cholisah Erman Hasihi Ming Foey Teng Herdianti Darwis |
| author_sort | Purnawansyah Purnawansyah |
| collection | DOAJ |
| description | Indonesia is a tropical country with a diverse range of plants that ancient people used for traditional medicines. However, the similarity in shape of the leaves became an obstacle to distinguishing them. Therefore, technological advancements are expected to help identify the herbal leaves to use them right on target according to their efficacy. In this research, image classification of katuk (Sauropus Androgynus) and kelor (Moringa Oleifera) leaves is applied using 3 different algorithms i.e hybrid of Gray Level Co-Occurrence Matrix (GLCM) feature extraction and Support Vector Machine (SVM) implementing 4 kernels namely linear, RBF, polynomial, and sigmoid; hybrid of GLCM and Convolutional Neural Network (CNN); and pure CNN. A dataset of 480 images has been collected with 2 different scenarios, including bright and dark intensities. Based on the result, a hybrid of GLCM and SVM showed the highest accuracy of 96% in the dark intensity test using a linear kernel, while sigmoid obtained the lowest accuracy of 35%. On the other hand, it has been discovered that CNN obtained the highest performance in the bright intensity test with an accuracy of 98%. While in the dark intensity test, a hybrid of GLCM and CNN is superior, obtaining 96% accuracy. In conclusion, CNN is more powerful for image classification with bright intensity. For dark intensity images, both the hybrid of GLCM+SVM (linear) and the hybrid of GLCM+CNN are fairly recommended. |
| first_indexed | 2024-04-24T23:45:11Z |
| format | Article |
| id | doaj.art-11615ca821ec490b8eb7b8376dbb2d05 |
| institution | Directory Open Access Journal |
| issn | 2087-1716 2548-7779 |
| language | English |
| last_indexed | 2024-04-24T23:45:11Z |
| publishDate | 2023-08-01 |
| publisher | Fakultas Ilmu Komputer UMI |
| record_format | Article |
| series | Ilkom Jurnal Ilmiah |
| spelling | doaj.art-11615ca821ec490b8eb7b8376dbb2d052024-03-15T07:10:06ZengFakultas Ilmu Komputer UMIIlkom Jurnal Ilmiah2087-17162548-77792023-08-0115238238910.33096/ilkom.v15i2.1759.382-389551Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNNPurnawansyah Purnawansyah0Aji Prasetya Wibawa1Triyanna Widyaningtyas2Haviluddin Haviluddin3Cholisah Erman Hasihi4Ming Foey Teng5Herdianti Darwis6Univeritas Negeri Malang, Univeristas Muslim IndonesiaUniveritas Negeri MalangUniveritas Negeri MalangUniversitas MulawarmanUniversitas Muslim IndonesiaAmerican University of SharjahUniversitas Muslim IndonesiaIndonesia is a tropical country with a diverse range of plants that ancient people used for traditional medicines. However, the similarity in shape of the leaves became an obstacle to distinguishing them. Therefore, technological advancements are expected to help identify the herbal leaves to use them right on target according to their efficacy. In this research, image classification of katuk (Sauropus Androgynus) and kelor (Moringa Oleifera) leaves is applied using 3 different algorithms i.e hybrid of Gray Level Co-Occurrence Matrix (GLCM) feature extraction and Support Vector Machine (SVM) implementing 4 kernels namely linear, RBF, polynomial, and sigmoid; hybrid of GLCM and Convolutional Neural Network (CNN); and pure CNN. A dataset of 480 images has been collected with 2 different scenarios, including bright and dark intensities. Based on the result, a hybrid of GLCM and SVM showed the highest accuracy of 96% in the dark intensity test using a linear kernel, while sigmoid obtained the lowest accuracy of 35%. On the other hand, it has been discovered that CNN obtained the highest performance in the bright intensity test with an accuracy of 98%. While in the dark intensity test, a hybrid of GLCM and CNN is superior, obtaining 96% accuracy. In conclusion, CNN is more powerful for image classification with bright intensity. For dark intensity images, both the hybrid of GLCM+SVM (linear) and the hybrid of GLCM+CNN are fairly recommended.https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1759convolutional neural networkglcm-cnnglcm-svmherbal leaves classificationsvm kernels |
| spellingShingle | Purnawansyah Purnawansyah Aji Prasetya Wibawa Triyanna Widyaningtyas Haviluddin Haviluddin Cholisah Erman Hasihi Ming Foey Teng Herdianti Darwis Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN Ilkom Jurnal Ilmiah convolutional neural network glcm-cnn glcm-svm herbal leaves classification svm kernels |
| title | Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN |
| title_full | Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN |
| title_fullStr | Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN |
| title_full_unstemmed | Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN |
| title_short | Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN |
| title_sort | comparative study of herbal leaves classification using hybrid of glcm svm and glcm cnn |
| topic | convolutional neural network glcm-cnn glcm-svm herbal leaves classification svm kernels |
| url | https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1759 |
| work_keys_str_mv | AT purnawansyahpurnawansyah comparativestudyofherballeavesclassificationusinghybridofglcmsvmandglcmcnn AT ajiprasetyawibawa comparativestudyofherballeavesclassificationusinghybridofglcmsvmandglcmcnn AT triyannawidyaningtyas comparativestudyofherballeavesclassificationusinghybridofglcmsvmandglcmcnn AT haviluddinhaviluddin comparativestudyofherballeavesclassificationusinghybridofglcmsvmandglcmcnn AT cholisahermanhasihi comparativestudyofherballeavesclassificationusinghybridofglcmsvmandglcmcnn AT mingfoeyteng comparativestudyofherballeavesclassificationusinghybridofglcmsvmandglcmcnn AT herdiantidarwis comparativestudyofherballeavesclassificationusinghybridofglcmsvmandglcmcnn |