caa a22 4500 605540691 CHVBK 20210128100912.0 cr unu---uuuuu 210128e20150401xx s 000 0 eng 10.1007/s00371-014-0931-8 doi (NATIONALLICENCE)springer-10.1007/s00371-014-0931-8 Optimized recognition with few instances based on semantic distance [Elektronische Daten] [Hao Wu, Zhenjiang Miao, Yi Wang, Manna Lin] In this paper, we present a new object recognition model with few instances based on semantic distance. Learning objects with many instances have been studied in computer vision for many years. However, in many cases, not enough positive instances occur, especially for some special categories. We must take full advantage of all instances, including those that do not belong to the category. The main insight is that, given a few positive instances from one category, we can define some other candidate instances as positive instances based on semantic distance to learn this model. Our model responds more strongly to instances with closer semantic distance to positive instances than to instances with farther semantic distance to positive instances. We use a regularized kernel machine algorithm to train the images from the database. The superiority of our method to existing object recognition methods is demonstrated. Experiments using an image database show that our method not only reduces the number of learning instances but also keeps the accurate rate of recognition. Springer-Verlag Berlin Heidelberg, 2014 Semantic distance nationallicence Object recognition nationallicence GIST nationallicence SIFT nationallicence AP value nationallicence AUC value nationallicence Wu Hao School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China aut Miao Zhenjiang School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China aut Wang Yi School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China aut Lin Manna School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China aut The Visual Computer Springer Berlin Heidelberg 31/4(2015-04-01), 367-375 0178-2789 31:4<367 2015 31 371 https://doi.org/10.1007/s00371-014-0931-8 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00371-014-0931-8 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Wu Hao School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China aut NATIONALLICENCE 700 1- Miao Zhenjiang School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China aut NATIONALLICENCE 700 1- Wang Yi School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China aut NATIONALLICENCE 700 1- Lin Manna School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China aut NATIONALLICENCE 773 0- The Visual Computer Springer Berlin Heidelberg 31/4(2015-04-01), 367-375 0178-2789 31:4<367 2015 31 371