Recognition of natural scene images based on graphs

The interpretation of natural scenes, generally so obvious and effortless for humans, still remains a challenge in computer vision. In this paper we propose to design binary classifiers capable to recognize some generic natural scene images, the countryside class and the city class for instance. Aft...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE International Conference on Progress in Informatics and Computing Vol. 1; pp. 132 - 135
Main Authors Qiangrong Jiang, Weina Wei
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2010
Subjects
Accuracy
Cities and towns
Computers
feature extraction
graph edit distance
image classification
Image recognition
Image segmentation
Pipelines
region representation
Online AccessGet full text

Cover

More Information
Summary:The interpretation of natural scenes, generally so obvious and effortless for humans, still remains a challenge in computer vision. In this paper we propose to design binary classifiers capable to recognize some generic natural scene images, the countryside class and the city class for instance. After the segmentation each image is represented by a set of regions. Then the propounded 1*12 vectors are used to describe the regions. Finally, we propose a new simple kernal function based on graph edit distance and raise the question that Munkres' algorithm can be used to measure the similarity between the images. Experiments show that the improvements are effective.
ISBN:1424467888
9781424467884
DOI:10.1109/PIC.2010.5687416