상세정보
학술지
Similarity Measurement for Breast Medical Image Retrieval System with Hybrid Object Based Approach
Cited 1 time in 
Download 0 time
Share 
Download 0 time
Share
- 발행일
- 201308
- 출처
- Information : An International Interdisciplinary Journal, v.16 no.8(B), pp.6269-6278
- ISSN
- 1343-4500
- 출판사
- International Information Institute
- 협약과제
- 13PR2600, 전자파 이용 조기진단 고정밀 MT 시스템 개발, 전순익
- 초록
- In this paper, we propose a new binary pixel matching method to measure the similarity of two objects based on the overlapped areas in a data warehouse. In the proposed approach, suspicious tumor objects are extracted as binary images that consist of background and foreground, which are compared based on counting overlapped pixels. Prior to measuring the exact similarity between two objects, a pre-processing stage is performed by calculating the difference in the shape index, performing rotation normalization, and estimating accurate similarity when the difference in the shape index is less than 50%. The results demonstrate that the proposed approach can significantly improve both the accuracy of similarity measurement and the performance of computational speed, when compared with traditional content based image retrieval method approaches that measure the similarity based on contours. © 2013 International Information Institute.
- KSP 제안 키워드
- Based Approach, Computational Speed, Data WareHouse, Medical Image Retrieval, Pixel matching, Pre-processing, Rotation normalization, Shape index, Similarity Measurement, binary image, content based image retrieval method