Document Type: Original Paper
Ph.D. Student of Computer Engineering, Islamic Azad University, Research and Science Branch, Tehran, Iran
Assistant Professor and Director of Multimedia Research Group, IT Faculty, Iran Telecom Research Center, Tehran, Iran
Associate Professor and Director of IT Faculty, Iran Telecom Research Center, Tehran, Iran
Introduction: Content Based Image Retrieval (CBIR) is a method of image searching and retrieval in a
database. In medical applications, CBIR is a tool used by physicians to compare the previous and current
medical images associated with patients pathological conditions. As the volume of pictorial information
stored in medical image databases is in progress, efficient image indexing and retrieval is increasingly
becoming a necessity.
Materials and Methods: This paper presents a new content based radiographic image retrieval approach
based on histogram of pattern orientations, namely pattern orientation histogram (POH). POH represents
the spatial distribution of five different pattern orientations: vertical, horizontal, diagonal down/left,
diagonal down/right and non-orientation. In this method, a given image is first divided into image-blocks
and the frequency of each type of pattern is determined in each image-block. Then, local pattern
histograms for each of these image-blocks are computed.
Results: The method was compared to two well known texture-based image retrieval methods: Tamura
and Edge Histogram Descriptors (EHD) in MPEG-7 standard. Experimental results based on 10000
IRMA radiography image dataset, demonstrate that POH provides better precision and recall rates
compared to Tamura and EHD. For some images, the recall and precision rates obtained by POH are,
respectively, 48% and 18% better than the best of the two above mentioned methods.
Discussion and Conclusion: Since we exploit the absolute location of the pattern in the image as well as
its global composition, the proposed matching method can retrieve semantically similar medical images.