Title :
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
fDate :
6/23/1905 12:00:00 AM
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;
Conference_Titel :
Image Processing, 2001. Proceedings. 2001 International Conference on
Conference_Location :
Thessaloniki
Print_ISBN :
0-7803-6725-1
DOI :
10.1109/ICIP.2001.959238