Advertisement
Published in:
2018 | OriginalPaper | Chapter
7. Similarity-Based Image Retrieval
Authors : Borko Furht, Esad Akar, Whitney Angelica Andrews
Published in: Digital Image Processing: Practical Approach
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
So far, we have only dealt with topics involving one or two images. The program demos were mostly about loading an image and performing a task e.g. converting to grayscale or hiding data in an image. With image retrieval, however, our task is to search for images from a large collection or database that are similar, in some manner, to a selected image. Measuring similarity can be done in many ways and depends on the problem at hand. There are techniques that involve analyzing images based on metadata e.g. file name, tags, etc. that are affiliated with the image. Other ways are based on the content of the image rather than metadata by processing the pixel values in some way. For this chapter, we’ve collected 200 images of various scenes and objects that make up the database which can be found in the ‘db’ folder in this chapter’s directory. The demo program is hard coded to work with these image, but you may change that by altering the source code and recompiling.