A Multi-Scale Algorithm for Graffito Advertisement Detection from Images of Real Estate

Authors:
Jun Yang;Shi-Jiao Zhu
Affiliations:
School of Computer and Information Engineering, Shanghai University of Electric Power, Shanghai, China 200090;School of Computer and Information Engineering, Shanghai University of Electric Power, Shanghai, China 200090
Venue:
AICI '09 Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence
Year:
2009

Citing 4
Cited 0

Neural network-based text location in color images

Pattern Recognition Letters
A Scale-Space Approach to Pre-Attentive Texture Discrimination

ICIAP '99 Proceedings of the 10th International Conference on Image Analysis and Processing
A multiscale representation including opponent color features for texture recognition

IEEE Transactions on Image Processing
Invariance properties of Gabor filter-based features-overview and applications

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

There is a significant need to detect and extract the graffito advertisement embedded in the housing images automatically. However, it is a hard job to separate the advertisement region well since housing images generally have complex background. In this paper, a detecting algorithm which uses multi-scale Gabor filters to identify graffito regions is proposed. Firstly, multi-scale Gabor filters with different directions are applied to housing images, then the approach uses these frequency data to find likely graffito regions using the relationship of different channels, it exploits the ability of different filters technique to solve the detection problem with low computational efforts. Lastly, the method is tested on several real estate images which are embedded graffito advertisement to verify its robustness and efficiency. The experiments demonstrate graffito regions can be detected quite well.