Abstract | ||
---|---|---|
Modern image sharing platforms such as instagram or flickr support an easy publication of photos to the internet, thus leading to great numbers of available photos. However, many of the images are not properly tagged so that there is no notion of what they are showing. For the example of mountain recognition it is advisable to create reference silhouettes from digital elevation maps. Those are matched with the silhouette extracted from a given image in order to recognise the mountain. It is therefore necessary to obtain a very precise silhouette from the query image. In this paper, we present AdaMS, an adaptive grid segmentation algorithm, that extracts the silhouette from an image. By the help of an artefact detection method, we find erroneous parts in the silhouette and show how our algorithm uses this information to recalculate the silhouette in the surroundings of the error. We also show that our method yields good results by evaluating our approach on an existing data set of mountain images. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-41920-6_8 | Lecture Notes in Artificial Intelligence |
Field | DocType | Volume |
Anomaly detection,Computer vision,Computer graphics (images),Silhouette,Computer science,Image sharing,Artificial intelligence,Color image segmentation,Polygonal chain,The Internet | Conference | 9729 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Braun | 1 | 0 | 0.34 |
Michael Singhof | 2 | 0 | 0.34 |
Stefan Conrad | 3 | 168 | 105.91 |