X-Ray Medical Image Classification Based on Multi Classifiers

Advances in the medical imaging technology has lead to a growth in the number of digital images that needs to be classified, stored and retrieved properly. Content Based Image Retrieval (CBIR) systems represent the application of specific computer vision techniques to retrieve images from large databases based on their visual features, such as color, texture and shape. Practically, the use of these visual features only does not offer appropriate measurement performance and accuracy since those features cannot express the high-level semantics of users. Therefore, image classification systems based on machine learning techniques are used as solutions for this problem of CBIR systems. In our previous works, performance of different feature types were investigated by using two techniques of machine learning which are k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM). In this paper, we extend that work by exploring the effect of combining these two classifiers. Our experiments show accuracy improvements based on using ImageCLEF2005 dataset.