Visual Pattern Discovery and Recognition by Hongxing Wang Chaoqun Weng & Junsong Yuan

Author:Hongxing Wang, Chaoqun Weng & Junsong Yuan
Language: eng
Format: epub
Publisher: Springer Singapore, Singapore

Feature

VPL-SC ()

k-means (Chap. 2)

VPL-SC ()

CH

59.7%

44.79%

55.1%

TH

68.0%

55.69%

61.8%

pHOG

60.0%

52.37%

58.2%

TH+CH+pHOG

70.0%

61.61%

64.5%

VPL-SC-MF ()

MCAC (Chap. 2)

VPL-SC-MF ()

Multi-feature fusion

78.7%

70.14%

72.2%

3.3.3 Scene Categorization

In the third experiment, to illustrate the discriminativeness of the proposed algorithms, we perform scene categorization on the 15-scene dataset.

The 15-scene dataset is gradually collected by [8, 17]. It contains totally 4485 images from 15 categories of outdoor and indoor scenes, including bedroom, living room, suburb, industrial, kitchen, coast, forest, highway, inside city, mountain, open country, street, tall building, office, and store. For each category, there are about 216 to 410 images of size about pixels. In Table 3.3, we show some example images from the 15-scene dataset.Table 3.3Sample images of the 15-scene dataset

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.