Title :
An efficient neural network based indoor-outdoor scene classification algorithm
Author :
Tao, Li ; Kim, Yeong-Hwa ; Kim, Yeong-Taeg
Abstract :
This paper presents an efficient indoor-outdoor scene classification algorithm based on neural network learning. To facilitate the hardware implementation, efficient image (composite) feature extraction based on image color, entropy, DCT coefficients, and edge orientation was developed. The trained scene classifiers demonstrate robust performance.
Keywords :
discrete cosine transforms; edge detection; entropy; feature extraction; image classification; image colour analysis; learning (artificial intelligence); neural nets; DCT coefficients; edge orientation; entropy; image color; image feature extraction; indoor-outdoor scene classification algorithm; neural network learning; Classification algorithms; Discrete cosine transforms; Entropy; Feature extraction; Hardware; Histograms; Image edge detection; Layout; Neural networks; Robustness;
Conference_Titel :
Consumer Electronics (ICCE), 2010 Digest of Technical Papers International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-4314-7
Electronic_ISBN :
978-1-4244-4316-1
DOI :
10.1109/ICCE.2010.5418764
