A New Technique for Image Retrieval Using its Contents
Keywords:
content-based image retrieval (CBIR), Tree data structures, extracted region features, color space conversion, quantization, denoising, edge detection and segmentationAbstract
Most of the early research on content-based image retrieval (CBIR) has been focused on developing effective global features. While these researches establish the basis of CBIR, the retrieval performance is still far from users’ expectations. The main reason is acknowledged to be the gap between low-level features and high-level concepts. To narrow down this semantic gap, an additive technique has been widely used: region-based features to represent the focus of the user’s perceptions of image content. The primary intent of this paper is to develop a system for efficiently retrieving similar images on the basis of their visual content from large image repositories. Studies on the benefit of various computational features in the description of visual contents of an image and on the grouping of features leading to successful retrieval results are the basis for the development of an image indexing and retrieval algorithm in this paper. This research presents an elegant and efficient system for content-based indexing and retrieval of images. The global and region features are extracted from the images and are used in indexing the same. Tree data structures are used in indexing the extracted region features. The proposed system makes use of the following image processing techniques: color space conversion, quantization, denoising, edge detection, and segmentation.
Downloads
Key Dates
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.