S.E. Umbaugh, R.H. Moss and W.V. Stoecker, Automatic Color Segmentation of Images with application to detection of Variegated Coloring in Skin Tumors, IEEE Engineering in Medicine and Biology 8(4) (1989), 43--52.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....is a difficult problem in dermatoscopic images because the transition between the lesion(s) and the surrounding skin is smooth and difficult to see accurately, even for a trained dermatologist. In the literature, most of the proposed techniques work with macroscopic, i.e. clinical, images [25 28]. In this kind of image, the contrast between a pigmented lesion and the surrounding s kin is higher and simple methods such as histogram thresholding can be sufficient to detect the lesion. In the case of dermatoscopic images, more sophisticated techniques must be developed to achieve this ....

Umbaugh SE, Moss RH, Stoecker WV. Automatic color segmentation of images with application to detection of variegated coloring in skin tumors. IEEE Engng Med Biol 1989;8(4):43 -- 52.

.... each other out leading to a final colouration lying back on the surface of normal skin colouration This result casts doubt on the eVectiveness of using purely colour information in the diagnosis of malignant melanoma and may oVer itself as an explanation for the moderate success achieved by Umbaugh et al. 1989] when they attempted to classify lesion types by an investigation of colouration. However, this is not to dismiss the usefulness of colour information when combined with other extracted lesion features such as that demonstrated by Dhawan and Sicsu [1992] when they combined colour with a texture ....

Umbaugh, S. E., Moss, R. H., and Stoecker, W. V. [1989]. Automatic color segmentation of images with application to detection of variegated coloring in skin tumors. IEEE Engineering in Medicine and Biology Magazine.

....for enhancing and filtering regions containing a pigmented network. 2.1. Colour Space Transformation We have investigated LAB, IHS and KL transform on colour vectors in the RGB colour space. The LAB colour space has been proposed for automatic colour segmentation of images with skin tumours [8]. The LAB colour space uses a spherical coordinate system to describe the RGB colour space. The RGB space has been defined as a three dimensional orthogonal space with three equally significant components. The distance of a colour to the origin in the RGB space describes the luminance component, ....

....of the segmented regions are shown in Fig. 2. The segmentation result corresponds to the visual classification into three regions. We have compared segmentation results using IHS, La b , Lu v , UV W and LAB colour spaces as well as a KL transform of the vectors in the RGB colour space [12, 8]. Only lesions with well defined borders can be extracted by using a segmentation in the IHS or UV W colour spaces. By using a segmentation based on the chrominance components of the LAB, La b , or Lu v colour spaces we can completely separate the lesion from the surrounding skin even ....

S. E. Umbaugh, R. H. Moss, and W. V. Stoecker. "Automatic color segmentation of images with application to detection of variegated coloring in skin

No context found.

S.E. Umbaugh, R.H. Moss and W.V. Stoecker, Automatic Color Segmentation of Images with application to detection of Variegated Coloring in Skin Tumors, IEEE Engineering in Medicine and Biology 8(4) (1989), 43--52.

No context found.

S.E. Umbaugh, R.H. Moss and W.V. Stoecker, Automatic Color Segmentation of Images with application to detection of Variegated Coloring in Skin Tumors, IEEE Engineering in Medicine and Biology 8(4) (1989), 43--52.

No context found.

Umbaugh, S. E., Moss, R. H. and Stoecker, W. V.: Automatic color segmentation of images with application to detection of variegated coloring in skin tumors, IEEE Eng. Med. Biol. 8(4) (1989), 43--52.

No context found.

S.E. Umbaugh, R.H. Moss and W.V. Stoecker, Automatic Color Segmentation of Images with application to detection of Variegated Coloring in Skin Tumors, IEEE Engineering in Medicine and Biology 8(4) (1989), 43--52.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC