Automatic attribute threshold selection for morphological connected attribute filters. (May 2016)

• Record Type: Journal Article
• Authors: Kiwanuka, Fred N.; Wilkinson, Michael H.F.
• Is Part Of: Pattern recognition. Volume 53(2016:May)
• Page Start: 59
• Page End: 72
• Publication Date: 2016-05
• Subjects: Medical image enhancement -- Attribute filters -- Connected operators -- Thresholding -- Segmentation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2015.11.012
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Attribute filters allow enhancement and extraction of features without distorting their borders, and never introduce new image features. In attribute filters, till date setting the attribute-threshold parameters has to be done manually. This research explores novel, simple, fast and automated methods of computing attribute threshold parameters based on image segmentation, thresholding and data clustering techniques in medical image enhancement. A performance analysis of the different methods is carried out using various 3D medical images of different modalities. Though several techniques perform well on these images, the choice of technique appears to depend on the imaging mode. Abstract : Highlights: Attribute filters enhance and extract features without distorting borders. Visual image inspection is labor intensive, can be inaccurate and irreproducible. Automatic shape quantification attempts to agree with human intuition. Methods for automatic computation of attribute thresholds can be simple and fast. The choice of a technique for classification appears to depend on the imaging mode.