Accurate tag relevance prediction for image search
US10235623B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 8, 2016 |
| Grant date | Mar 19, 2019 |
| Priority date | — |
| Expiry date | Apr 8, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.