Natural Scene Classification Based on Integrated Topic Simplex

• Published in: IEICE Transactions on Information and Systems Vol. E92.D; no. 9; pp. 1811 - 1814
• Main Authors: YINGJUN, Tang, DE, Xu, XU, Yang, QIFANG, Liu
• Format: Journal Article
• Language: English
• Published: Oxford The Institute of Electronics, Information and Communication Engineers 2009; Oxford University Press
• Subjects: Applied sciences; Categories; CC-LDA; Classification; Correlation; Exact sciences and technology; Human; ILTM; Information, signal and communications theory; LDA; Mathematical models; Recognition; scene classification; Signal and communications theory; Signal representation. Spectral analysis; Signal, noise; Tasks; Telecommunications and information theory; Training; Performance evaluation; Discriminant analysis; Automatic classification; Natural scene; CC-LDA; LDA; Signal classification; Implementation; Learning; Image analysis; Scene analysis; scene classification; ILTM
• ISSN: 0916-8532; 1745-1361; 1745-1361
• DOI: 10.1587/transinf.E92.D.1811

We present a novel model named Integrated Latent Topic Model (ILTM), to learn and recognize natural scene category. Unlike previous work, which considered the discrepancy and common property separately among all categories, Our approach combines universal topics from all categories with specific topics from each category. As a result, the model is implemented to produce a few but specific topics and more generic topics among categories, and each category is represented in a different topics simplex, which correlates well with human scene understanding. We investigate the classification performance with variable scene category tasks. The experiments have shown our model outperforms latent-space methods with less training data.