Abstract | ||
---|---|---|
With the prevalence of smartphones, the demand of recognizing the location through their camera and sensors is paid abundant attentions. For constructing a location recognition image database, the crowdsourcing technology is introduced to collect images associated with other sensory data. However, as abundant crowdsourced images evolve, it is essential to select high-quality images to decrease the burden of storage when designing an offline location recognition system directly on mobile devices. To address this problem, we propose an image selection framework, i.e., Informative image Selection Framework (ISF), considering both the diversity in spatial distribution and representativeness of images with high quality. First, for the images corresponding to the same object, we propose the Self-adaptive Space Clustering algorithm to group them into several clusters for maintaining high diversity of the image database. Second, for every cluster, we propose the Crucial Part Feature Detection algorithm to detect representative images. Extensive experiments demonstrate that ISF is effective and efficient for image selection, outperforming other similar image selection schemes around 5%. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/s00530-017-0562-9 | Multimedia Systems |
Keywords | Field | DocType |
Image selection,View direction,Crowdsourcing,Mobile location recognition | Data mining,Mobile location,Pattern recognition,Recognition system,Crowdsourcing,Computer science,Representativeness heuristic,Mobile device,Artificial intelligence,Image database,Cluster analysis,Image selection | Journal |
Volume | Issue | ISSN |
25.0 | SP5 | 1432-1882 |
Citations | PageRank | References |
0 | 0.34 | 19 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hao Wang | 1 | 440 | 127.79 |
Dong Zhao | 2 | 354 | 29.82 |
Huadong Ma | 3 | 2020 | 179.93 |