Integration of semantic and visual hashing for image retrieval

Automatic annotation of images is considered to be an important research problem in image retrieval. Traditional methods are computationally complex and fail to annotate correctly when the number of image classes is large and related. This paper proposes a novel approach, an autoencoder hashing, to categorize images of large-scale image classes. The intra bin classifiers are trained to classify the query image, and the tag weight and tag frequency are computed to achieve a more effective annotation of the query image. The proposed approach has been compared with other existing approaches in the literature using performance measures, such as precision, accuracy, mean average precision (MAP), and F1 score. The experimental results indicate that our proposed approach outperforms the existing approaches.

show abstract

An improved noise loss correction algorithm for learning from noisy labels

Zhang

Lee

Wang

et al. 2020

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Integration of semantic and visual hashing for image retrieval

Cited by 5 publications

References 25 publications

A comparative study of hash based approximate nearest neighbor learning and its application in image retrieval

A comparative study of hash based approximate nearest neighbor learning and its application in image retrieval

Categorization of Images Using Autoencoder Hashing and Training of Intra Bin Classifiers for Image Classification and Annotation

An improved noise loss correction algorithm for learning from noisy labels

Contact Info

Product

Resources

About