SIMPLIcity: semantics-sensitive integrated matching for picture libraries

TLDR

Images are represented by regions corresponding to objects, characterized by color, texture, shape, and location. The study introduces SIMPLIcity, an image retrieval system that combines semantic classification, wavelet‑based feature extraction, and integrated region matching via image segmentation. SIMPLIcity classifies images into semantic categories and computes overall similarity using a region‑matching scheme that integrates color, texture, shape, and location of all regions. SIMPLIcity improves retrieval performance, achieving faster and more accurate results than existing systems while remaining robust to image alterations.

Abstract

We present here SIMPLIcity (semantics-sensitive integrated matching for picture libraries), an image retrieval system, which uses semantics classification methods, a wavelet-based approach for feature extraction, and integrated region matching based upon image segmentation. An image is represented by a set of regions, roughly corresponding to objects, which are characterized by color, texture, shape, and location. The system classifies images into semantic categories. Potentially, the categorization enhances retrieval by permitting semantically-adaptive searching methods and narrowing down the searching range in a database. A measure for the overall similarity between images is developed using a region-matching scheme that integrates properties of all the regions in the images. The application of SIMPLIcity to several databases has demonstrated that our system performs significantly better and faster than existing ones. The system is fairly robust to image alterations.