Distortions such as dryness, wetness, blurriness, physical damages and presence of dots in fingerprints are a detriment to a good analysis of them. Even though fingerprint image enhancement is possible through physical solutions such as removing excess grace on the fingerprint or recapturing the fingerprint after some time, these solutions are usually not user-friendly and time consuming. In some cases, the enhancements may not be possible if the cause of the distortion is permanent. In this paper, we are proposing an unpaired image-to-image translation using cycle-consistent adversarial networks for translating images from distorted domain to undistorted domain, namely, dry to not-dry, wet to not-wet, dotted to not-dotted, damaged to not-damaged, blurred to not-blurred. We use a database of low quality fingerprint images containing 11541 samples with dryness, wetness, blurriness, damages and dotted distortions. The database has been prepared by real data from VISA application centres and have been provided for this research by GEYCE Biometrics. For the evaluation of the proposed enhancement technique, we use VGG16 based convolutional neural network to assess the percentage of enhanced fingerprint images which are labelled correctly as undistorted. The proposed quality enhancement technique has achieved the maximum quality improvement for wetness fingerprints in which 94% of the enhanced wet fingerprints were detected as undistorted.
We address multimodal product attribute prediction of fashion items based on product images and titles. The product attributes, such as type, sub-type, cut or fit, are in a chain format, with previous attribute values constraining the values of the next attributes. We propose to address this task with a sequential prediction model that can learn to capture the dependencies between the different attribute values in the chain. Our experiments on three product datasets show that the sequential model outperforms two non-sequential baselines on all experimental datasets. Compared to other models, the sequential model is also better able to generate sequences of attribute chains not seen during training. We also measure the contributions of both image and textual input and show that while text-only models always outperform image-only models, only the multimodal sequential model combining both image and text improves over the text-only model on all experimental datasets.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.