Indoor-outdoor image classification

被引：0

作者：

Szummer, M ^{[1
]}

Picard, RW ^{[1
]}

机构：

[1] MIT, Media Lab, Cambridge, MA 02139 USA

来源：

1998 IEEE INTERNATIONAL WORKSHOP ON CONTENT-BASED ACCESS OF IMAGE AND VIDEO DATABASE, PROCEEDINGS | 1998年

关键词：

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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: (1) histograms In the Ohta color space (2) multiresolution: simultaneous autoregressive model parameters (3) coefficients of a shift-invariant DCT. We demonstrate that performance is improved by computing features an 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% re correct classification? when evaluated on a diverse database of over 1300 consumer images provided by Kodak.

引用

页码：42 / 51

页数：10