Local and Global Descriptors in CT Images for Efficient Pattern Classification

Local and global features have recently attracted growing attention in the field of image processing and pattern recognition. The features from local binary pattern (LBP) for instance, usually lack global spatial information while global descriptors would provide very little local information. This paper develops two descriptors to tackle the existing problems in local and global features by providing more information to describe different textural structures in computed tomography (CT) images. The proposed global and local descriptors can provide more accurate classification results by using hybrid concatenation approach. The experimental procedures are validated for different scales of Emphysema images during the classification process in order to determine the appropriate image size that could yield the maximum classification accuracy. The experimental results show that the descriptors developed from the combined features considerably improve the performance of the classifiers. The results also indicate that the global descriptor outperforms the earlier approaches and demonstrate the discriminating power and robustness of the combined features for accurate classification of CT images.