Counting the number of blobs in an image

Author

Azuela, Juan Humberto Soma ; Guzman Lugo, G. ; Rangel, Rafael Sotelo

Author_Institution

Centro de Investigacion en Computacion, Instituto Politecnico Nacional, Mexico City, Mexico

Volume

1

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

1086

Abstract

A new way to determine the number of blobs in an image is presented. The technique can be applied to the case of convex or non-convex, elongated or not elongated blobs with a smooth contour without holes, different length, but similar thickness and in the presence of occlusions. The number of blobs in an image can be obtained as a function of three quantities: the number of conglomerates, the number of singular concavity points, and the number of holes in the image. The technique has been tested with several hundreds of syntactically generated gray level images containing elongated convex objects. The preliminary results are very promising. Errors were mainly due to the appearance of some pathological cases and to fact that some concavity points are not correctly detected

Keywords

feature extraction; image processing; object detection; conglomerates; convex blobs; elongated blobs; gray level images; image blob counting; nonconvex blobs; occlusions; singular concavity points; smooth contour; Computer industry; Error correction; Fatigue; Humans; Image generation; Labeling; Pathology; Pixel; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2001. Proceedings. 2001 International Conference on

Conference_Location

Thessaloniki

Print_ISBN

0-7803-6725-1

Type

conf

DOI

10.1109/ICIP.2001.959238

Filename

959238