Title :
Image Orientation Detection Based on Camera-subject Distances by Adaptive Control of Conditional Probability
Author :
Takahashi, Yusuke ; Hirata, Kyoji
Author_Institution :
Common Platform Software Res. Labs., NEC Corp., Kawasaki
Abstract :
In this paper, we propose a method of image orientation detection based on camera-subject distances. This method is characterized as an adaptive control of probabilistic decision by subject distances. The control is operated by switching of conditional probabilities of visual features at each subject distance category. The subject distance can be extracted from Exif. Evaluation and comparison is performed on 1681 consumer images. The experimental results show accuracy improvements on all visual feature combinations with negligible computational cost.
Keywords :
adaptive control; feature extraction; image recognition; probability; adaptive control; camera-subject distances; conditional probability; image orientation detection; probabilistic decision; visual feature extraction; Adaptive control; Bayesian methods; Computational efficiency; Digital cameras; Face detection; Laboratories; National electric code; Performance evaluation; Support vector machine classification; Support vector machines;
Conference_Titel :
Consumer Electronics, 2008. ICCE 2008. Digest of Technical Papers. International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-1458-1
Electronic_ISBN :
978-1-4244-1459-8
DOI :
10.1109/ICCE.2008.4587936
