ASALTAG : Automatic Image Annotation Through Salient Object Detection and Improved k-Nearest Neighbor Feature Matching

Abstract

Image databases are becoming very large nowadays, and there is an increasing need for automatic image annotation, for assiting on finding the desired specific image. In this paper, we present a new approach of automatic image annotation using salient object detection and improved k-Nearest Neigbor classifier named ASALTAG. ASALTAG is consist of three major part, the segmentation using Minimum Barirer Salienct Region Segmentation, feature extraction using Block Truncation Algorithm, Gray Level Co-occurrence Matrix and Hu’ Moments, the last part is classification using improved k-Nearest Neigbor. As the result we get maximum accuracy of 79.56% with k=5, better than earlier research. It is because the saliency object detection we do before the feature extraction proccess give us more focused object in image to annotate. Normalization of the feature vector and the distance measure that we use in ASALTAG also improve the kNN classifier accuracy for labeling image.

Expert System for Early Diagnosis of Heart Disease Using the Random Forest Method

“…In the branch produced one of the branches is pure, while the other branches will continue to be processed until there are no significant changes, at that time the process will be stopped. [ The ROC curve is a way to compare a plot of true positive level with a false positive level, this is seen from the area under the curve the greater the area under the curve the more accurate the test is performed [10], [11]. C-statistic or c-index is a measure of goodness of fit for binary results in the logistic regression model, in clinical studies cstatistics give the probability of patients randomly experiencing certain diseases or conditions with higher scores compared to patients who did not experience the event [12].…”