What is it about?
In this work, a novel image feature extraction method is proposed, where image features have been extracted from different multi-resolutions using statistical parameters for retrieving images from dataset based on given query image. Since existing similarity measure between images requires some high computational cost. To overcome this, new threshold based similarity measure is proposed in this work.
Photo by Mo on Unsplash
Why is it important?
The image feature extraction algorithm and similarity measure proposed by authors is novel for image retrieval process.
Read the Original
This page is a summary of: A Novel Similarity Measure for Content Based Image Retrieval in Discrete Cosine Transform Domain, Fundamenta Informaticae, October 2017, IOS Press, DOI: 10.3233/fi-2017-1605.
You can read the full text:
The following have contributed to this page