Automatic context analysis for image classification and retrieval

Authors:
Andrey Vavilin;Kang-Hyun Jo;Moon-Ho Jeong;Jong-Eun Ha;Dong-Joong Kang
Affiliations:
Electrical Engineering Department, University of Ulsan, Korea;Electrical Engineering Department, University of Ulsan, Korea;Kwangwoon University, Korea;Seoul National University of Science, Korea;Pusan National University, Korea
Venue:
ICIC'11 Proceedings of the 7th international conference on Advanced Intelligent Computing
Year:
2011

Citing 6
Cited 0

SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture LIbraries

IEEE Transactions on Pattern Analysis and Machine Intelligence
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

International Journal of Computer Vision
Scene-Centered Description from Spatial Envelope Properties

BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Semantic-Sensitive Classification for Large Image Libraries

MMM '05 Proceedings of the 11th International Multimedia Modelling Conference
Review: Which is the best way to organize/classify images by content?

Image and Vision Computing
CBSA: content-based soft annotation for multimodal image retrieval using Bayes point machines

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a method for image classification and retrieval for natural and urban scenes. The proposed algorithm is based on hierarchical image contents analysis. First image is classified as urban or natural according to color and edge distribution properties. Additionally scene is classified according to its conditions: illumination, weather, season and daytime based on contrast, saturation and color properties of the image. Then image content is analyzed in order to detect specific object classes: buildings, cars, trees, sky, road etc. To do so, image recursively divided into rectangular blocks. For each block probabilities of membership in the specific class is computed. This probability computed as a distance in a feature space defined by optimal feature subset selected on the training step. Blocks which can not be assigned to any class using computed features are separated into 4 sub-blocks which analyzed recursively. Process stopped then all blocks are classified or size of block is smaller then predefined value. Training process is used to select optimal feature subset for object classification. Training set contains images with manually labeled objects of different classes. Each image additionally tagged with scene parameters (illumination, weather etc).