Title :
Indoor-outdoor image classification
Author :
Szummer, Martin ; Picard, Rosalind W.
Author_Institution :
Media Lab., MIT, Cambridge, MA, USA
Abstract :
We show how high-level scene properties can be inferred from classification of low-level image features, specifically for the indoor-outdoor scene retrieval problem. We systematically studied the features of: histograms in the Ohta color space; multiresolution, simultaneous autoregressive model parameters; and coefficients of a shift-invariant DCT. We demonstrate that performance is improved by computing features on subblocks, classifying these subblocks, and then combining these results in a way reminiscent of stacking. State of the art single-feature methods are shown to result in about 75-86% performance, while the new method results in 90.3% correct classification, when evaluated on a diverse database of over 1300 consumer images provided by Kodak
Keywords :
discrete cosine transforms; image classification; image colour analysis; image resolution; query processing; software performance evaluation; statistical analysis; visual databases; Kodak consumer image database; Ohta color space; high-level scene properties; histograms; indoor outdoor image classification; indoor-outdoor scene retrieval; low-level image features; multiresolution simultaneous autoregressive model; performance; shift-invariant DCT; single feature methods; stacking; Color; Computer vision; Discrete cosine transforms; Diversity reception; Histograms; Image classification; Image databases; Image retrieval; Layout; Spatial databases;
Conference_Titel :
Content-Based Access of Image and Video Database, 1998. Proceedings., 1998 IEEE International Workshop on
Conference_Location :
Bombay
Print_ISBN :
0-8186-8329-5
DOI :
10.1109/CAIVD.1998.646032
