A hybrid approach for solving the range image segmentation/reconstruction problem

The main techniques used to solve the segmentation/reconstruction problem in range image are region growing, split-and-merge, and clustering. Region growing and split-and-merge algorithms present the problem that they have to deal with threshold values that are difficult to obtain. Clustering algori...

Full description

Saved in:
Bibliographic Details
Main Authors: Bellon, O.R.P., Castanho, J.E.C., Tozzi, C.L.
Format: Conference Proceeding
Language:English
Subjects:
Application software
Clustering algorithms
Computer vision
Data mining
Electronic mail
Image edge detection
Image reconstruction
Image segmentation
Image sensors
Partitioning algorithms
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The main techniques used to solve the segmentation/reconstruction problem in range image are region growing, split-and-merge, and clustering. Region growing and split-and-merge algorithms present the problem that they have to deal with threshold values that are difficult to obtain. Clustering algorithms suffer less influence from this kind of problem, although other problems exist. A segmentation/reconstruction technique based on the clustering approach is presented to approximate regions of a range image by planes. The main goal is to reconstruct the image with minimum error and with simplicity. The association with edge detection techniques is proposed to minimize problems of the clustering technique. Some segmentation results using simulated images are presented.
DOI:10.1109/ICSMC.1995.537767