Brain tumor has been acknowledged as the most dangerous disease through all its circles. Early identification of tumor disease is considered pivotal to identify the spread of brain tumors in administering the appropriate treatment. This study proposes a Convolutional Neural Network method to detect brain tumor on MRI images. The 3264 datasets were undertaken in this study with detailed images of Glioma tumor (926 images), Meningioma tumors (937 images), pituitary tumors (901 images), and other with no-tumors (500 images). The application of CNN method combined with Hyperparameter Tuning is proposed to achieve optimal results in classifying the brain tumor types. Hyperparameter Tuning acts as a navigator to achieve the best parameters in the proposed CNN model. In this study, the model testing was conducted with three different scenarios. The result of brain tumor classification depicts an accuracy of 96% in the third model testing scenario.
In this study, we propose a new method to extract texture features of batik images. The proposed method is called co-occurrence matrices of sub-band images. This method is proposed to overcome the problem in classifying batik images that are acquired randomly from the internet. The problem of those images is the batik images contain various types of noise, such as unbalanced brightness, there are folds on fabrics images, the different size of basic motifs, low contrast, and there is watermark on the images. This method combines the advantages of gray-level co-occurrence matrices (GLCM) and discrete wavelet transform (DWT). First, the original image is decomposed using DWT to provide sub-band images. Second, GLCM is applied to sub-band images to extract the texture features. Those features will become the input for the probabilistic neural network (PNN). The results show that this method is robust enough to classify batik images. The maximum accuracy that can be achieved is 72%.
1 February 2023 in Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Herbal leaves are a type that is often used by people in the health sector. The problem faced is the lack of knowledge about the types of herbal leaves and the difficulty of distinguishing the types of herbal leaves for ordinary people who do not understand plants. If any type of plant is used, it will have a negative impact on health. Automatic classification with the help of technology will reduce the risk of misidentification of herbal leaf types. To make identification, a precise and accurate herbal leaf detection process is needed. This research aims to facilitate the classification model of herbal leaf images with a higher accuracy value than previous research. Therefore, the proposed method in this classification process is one of the Transfer Learning methods, namely Convolutional Neural Network (CNN) with a pretrained VGG16 model. This research uses a dataset of herbal leaves with a total of 10 classes: Belimbing Wuluh, Jambu Biji, Jeruk Nipis, Kemangi, Lidah Buaya, Nangka, Pandan, Pepaya, Seledri and Sirih. The performance of the results of the proposed classification method on the test dataset using Classification Report shows an increase in the results of the previous research accuracy value from 82% to 97%. This research also applies Image Data Generator in the augmentation process which aims to improve the image of herbal leaves, reduce overfitting, and improve accuracy.
1 June 2020 in Bulletin of Electrical Engineering and Informatics
This study is proposed to compare which are the better method to classify Batik image between K-Nearest neighbor and Support Vector Machine using minimum features of GLCM. The proposed steps are started by converting image to grayscale and extracting colour feature using four features of GLCM. The features include Energy, Entropy, Contras, Correlation and 0o, 45o, 90o, and 135o. The classifier features consist of 16 features in total. In the experimental result, there exist comparison of previous works regarding the classification KNN and SVM using multi texton histogram (MTH). The experiments are carried out in the form of calculation of accuracy with data sharing and cross-validation scenario. From the test results, the average accuracy for KNN is 78.3% and 92.3% for SVM in the cross-validation scenario. The scenario for the highest accuracy of data sharing is at 70% for KNN and at 100% for SVM. Thus, it is apparent that the application of the GLCM and SVM method for extracting and classifying batik motifs has been effective and better than previous work.
Batik is one of the traditional heritages of Indonesia, with each motif of batik having a profound cultural and philosophical significance. This article introduces Batik Nitik 960 dataset from Yogyakarta, Indonesia. The dataset was extracted from a piece of fabric with 60 Nitik patterns. The dataset was supplied by the Paguyuban Pecinta Batik Indonesia (PPBI) Sekar Jagad Yogyakarta collection of Winotosasto Batik and the data were extracted from the APIPS Gallery. Each of the 60 categories in the collection contains 16 photographs, for a total of 960 images. The photographs were acquired with a Sony Alpha a6400, illuminated with a Godox SK II 400, and the data were compressed using the jpg file format. Each category contains four motifs rotated by 90, 180, and 270 degrees. Thus, the total number of images per motif is 16. Each class has a specific philosophical significance associated with the motif’s origins. This dataset aims to enable the training and evaluation of machine learning models for classification, retrieval, or generation of a new batik pattern using a generative adversarial network. To our knowledge, this study is the first to present a Batik Nitik dataset equipped with philosophical significance that is freely accessible.
28 January 2016 in IOP Conference Series: Materials Science and Engineering
Image classification plays an important rule for other image domains such as image retrieval, object recognition, image annotation and relevance feedback. In this paper, we describe our work in image classification using Multi Texton Histogram (MTH) and Probabilistic Neural Network (PNN). The result shows that the proposed method reaches 92% accuracy for Batik dataset and 98% for Brodatz dataset. This indicates that the use of MTH and PNN for image classification for Batik dataset and Brodatz dataset are effective.