Arya Yudhi Wijaya

Classification of non-proliferative diabetic retinopathy based on hard exudates using soft margin SVM

Diabetic retinopathy is a retinal disease caused by diabetes mellitus. Severity of diabetic retinopathy may lead to blindness. Therefore, early detection of diabetic retinopathy is very important. One of diabetic retinopathy symptoms is the existence of hard exudates. In this study, hard exudates in retinal fundus images are employed to classify the moderate and severe non-proliferative diabetic retinopathy. The hard exudates are segmented using mathematical morphology and the extracted features are classified by using soft margin SVM. The classification model achieves accuracy of 90.54% for 75 training data and 74 testing data of retinal images.

Fractal-based texture and HSV color features for fabric image retrieval

Wide range of products such as clothing, bed linen, curtains, and shoes, use fabrics as main raw material. Fabrics have various types of materials, colors and patterns. Harmony in combining the various types of fabrics will affect the beauty of the resulted product. A system that can be used to retrieve some fabrics similar to a fabrics sample automatically will facilitate the combining process in creating a product. In this study, a fabrics image retrieval system using combination of fractal-based texture feature and HSV color feature is developed. The Canberra Distance is used to measure similarity between features vectors. The experiment which is done using two kinds of fabrics image datasets, i.e. “batik” and “common”, gives average recall 94% and 92%, respectively.

Non-uniform decimation-free directional filter bank using histogram analysis for image enhancement

Directional Filter Banks (DFB) is a method for directional decomposition. It has been used in image enhancement procedure that involved image with many edges. The design of Decimation-Free Directional Filter Bank (DDFB) is made to give a better result for enhancement. However, the design cannot give an adaptive directional decomposition based on input image. In this paper, we proposed a Non-Uniform Decimation-Free Directional Filter Bank (NUDDFB) using Histogram Analysis for Image Enhancement. NUDDFB can build an adaptive directional filter depends on the input image. The result shows that NUDDFB can separate each directional image better than DDFB. The use of this method in image enhancement helps to retain the image from over enhancement.

Image thresholding based on index of fuzziness and fuzzy similarity measure

In this paper, we propose an automatic image thresholding method based on an index of fuzziness and a fuzzy similarity measure. This work aims at overcoming the limitation of the existing method which is semi-supervised. Using an index of fuzziness, two initial regions of gray levels located at the boundaries of the histogram are defined based on the fuzzy region. Then the threshold point is found by using a fuzzy similarity measure. No prior knowledge of the image is required. Experiments on practical images illustrate the effectiveness of the proposed method.

Feature extraction using gray-level co-occurrence matrix of wavelet coefficients and texture matching for batik motif recognition

Batik is one of Indonesian’s traditional cloth. Motif or pattern drawn on a piece of batik fabric has a specific name and philosopy. Although batik cloths are widely used in everyday life, but only few people understand its motif and philosophy. This research is intended to develop a batik motif recognition system which can be used to identify motif of Batik image automatically. First, a batik image is decomposed into sub-images using wavelet transform. Six texture descriptors, i.e. max probability, correlation, contrast, uniformity, homogenity and entropy, are extracted from gray-level co-occurrence matrix of each sub-image. The texture features are then matched to the template features using canberra distance. The experiment is performed on Batik Dataset consisting of 1088 batik images grouped into seven motifs. The best recognition rate, that is 92,1%, is achieved using feature extraction process with 5 level wavelet decomposition and 4 directional gray-level co-occurrence matrix.

Tuna fish classification using decision tree algorithm and image processing method

Fishery has contributed a lot to Indonesian economy development such as domestic industries, micro industries, and export industries. Tuna is one of the fishery product. To produce tuna fish product, an industry must separate tuna based on their type. Nowadays, the separation process is still done manually. As consequence, the process was slow and the error rate was high. This research proposed automatic tuna fish classification using decision tree algorithm and image processing method. Eight features, texture feature and shape feature, were extracted from tuna fish image using image processing method. The texture features are contrast, correlation, energy, homogeneity, inverse difference moment, and entropy. While the shape features are the circular rate of tunas head and the ratio of head area and circular area. These features are then used to create classification model using decision tree. Sixty tunas image from tree types tuna, Bigeye, Yellowfin, and Skipjack, were used in experiment. From experiment, it shows that the average accuracy of the classification is 88%.