{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

DK1212_C013 - 13 Image Analysis The procedures described in...

Info icon This preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
593 13 Image Analysis The procedures described in this chapter differ from the previous ones substantially: they provide, as their results, a description of the input image rather than a processed image as such. We shall begin with the analytic methods that are determining local properties of the image or spatially limited relations between these local proper- ties, as used in characterizing textures. Subsequently, segmentation approaches will be presented that allow dividing the image area into meaningful parts as required by a particular purpose of imaging. Finally, as a part of this chapter, we shall introduce the strongly nonlinear morphological operators that belong to both image pro- cessing and analysis; however, they may significantly contribute to image examination and recognition (e.g., by thinning, connecting or disconnecting objects, or providing their structural description) and are thus usually considered analytic methods. Of the literature cited in the references to Part III, the most relevant sources to this chapter are [5], [80], [13], [70], [72], [25], [79], [59], [17], as well as [26], [6], [7], where numerous additional references are cited. Though some of the involved methods are quite sophisticated as to the conceptual and computational means concerned, this type © 2006 by Taylor & Francis Group, LLC
Image of page 1

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
594 Jan of examination is often denoted as the low-level analysis to distin- guish it from a higher-level evaluation of shapes, spatial relations among objects, and automatic scene recognition. It would be perhaps useful to subdivide the low-level analysis into the lowest-level eval- uation of local properties and textures, and the mid-level analysis enabling segmentation based on the local features, and elementary size and volume measurements. In the field of medical imaging, the low- and mid-level analyses are prevailing so far. The higher ana- lysis tasks are still reserved mainly for the medical staff evaluating the images; probably, they will remain so into the foreseeable future, not only because of the technical difficulty of the analytic tasks, but also due to ethical and legislative issues. The reader interested in principles of the automation of the higher-level procedures, e.g., three-dimensional scene recognition, which may find use, e.g., in interventional radiology, should refer to the literature on computer vision, e.g., [17], [72]. 13.1 LOCAL FEATURE ANALYSIS Local features are the simplest description of image properties. They may concern each single pixel individually (e.g., the pixel intensity or color, possibly also vector pixel values in fused images), but more important is the analysis of local properties based on some neigh- borhood pertaining to a particular pixel, to which the parameter obtained by the analysis is then attributed. The magnitude of local gradient, determined for each image pixel that is based on intensi- ties of the neighboring pixels, may serve as an example. As far as such a feature or parameter can be basically determined (derived from the original image) for every pixel on the image grid, a new image, denoted as the
Image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern