15 December 2022 in PeerJ Computer Science
Curcuma longa(turmeric) andCurcuma zanthorrhiza(temulawak) are members of theZingiberaceaefamily that contain curcuminoids, essential oils, starch, protein, fat, cellulose, and minerals. The nutritional content proportion of turmeric is different from temulawak which implies differences in economic value. However, only a few people who understand herbal plants, can identify the difference between them. This study aims to build a model that can distinguish between the two species ofZingiberaceaebased on the image captured from a mobile phone camera. A collection of images consisting of both types of rhizomes are used to build a model through a learning process using transfer learning, specifically pre-trained VGG-19 and Inception V3 with ImageNet weight. Experimental results show that the accuracy rates of the models to classify the rhizomes are 92.43% and 94.29%, consecutively. These achievements are quite promising to be used in various practical use.
7 July 2020 in IJAIT (International Journal of Applied Information Technology)
The World Health Organization (WHO) estimates that over five percent of the world's population are hearing-impaired. One of the communication problems that often arise between deaf or speech impaired with normal people is the low level of knowledge and understanding of the deaf or speech impaired's normal sign language in their daily communication. To overcome this problem, we build a sign language recognition system, especially for the Indonesian language. The sign language system for Bahasa Indonesia, called Bisindo, is unique from the others. Our work utilizes two image processing algorithms for the pre-processing, namely the grayscale conversion and the histogram equalization. Subsequently, the principal component analysis (PCA) is employed for dimensional reduction and feature extraction. Finally, the support vector machine (SVM) is applied as the classifier. Results indicate that the use of the histogram equalization significantly enhances the accuracy of the recognition. Comprehensive experiments by applying different random seeds for testing data confirm that our method achieves 76.8% accuracy. Accordingly, a more robust method is still open to enhance the accuracy in sign language recognition.