Manhattan distance-based histogram of oriented gradients for content-based medical image retrieval

Abstract

ABSTRACT Content-based medical image retrieval (CBMIR) is the emerging research area in the field of medical image retrieval and analysis. The proposed CBMIR system includes two phases: feature extraction and feature matching. In the current decades, the feature matching approaches are developed well, but still the feature extraction algorithms are facing difficulties such as poor result in illuminance, lighting variations, etc. For addressing these concerns, Manhattan-distance based histogram of oriented gradients (M-HOG) was proposed in this research paper by assuming the different contributions of the training and testing samples from (Dicom medical image dataset for computed tomography (CT) and magnetic resonance imaging (MRI) images). At first, the medical images were enhanced by using Gaussian filter. The respective pre-processed medical image features were extracted by applying M-HOG. Using a Euclidean distance measure, the similarity between the testing and training medical images was calculated and matched. In the experimental section, the proposed system improved the retrieval accuracy in CBMIR system up to 5–15% related to the existing methodologies.