In this paper, we introduce a simple and standalone manual annotation tool for images, audio and video: the VGG Image Annotator (VIA). This is a light weight, standalone and offline software package that does not require any installation or setup and runs solely in a web browser. The VIA software allows human annotators to define and describe spatial regions in images or video frames, and temporal segments in audio or video. These manual annotations can be exported to plain text data formats such as JSON and CSV and therefore are amenable to further processing by other software tools. VIA also supports collaborative annotation of a large dataset by a group of human annotators. The BSD open source license of this software allows it to be used in any academic project or commercial application.
This paper proposes a data driven model to predict the performance of a face recognition system based on image quality features. We model the relationship between image quality features (e. g. pose, illumination, etc ) and recognition performance measures using a probability density function. To address the issue of limited nature of practical training data inherent in most data driven models, we have developed a Bayesian approach to model the distribution of recognition performance measures in small regions of the quality space. Since the model is based solely on image quality features, it can predict performance even before the actual recognition has taken place. We evaluate the performance predictive capabilities of the proposed model for six face recognition systems (two commercial and four open source) operating on three independent data sets: MultiPIE, FRGC and CAS-PEAL. Our results show that the proposed model can accurately predict performance using an accurate and unbiased Image Quality Assessor (IQA). Furthermore, our experiments highlight the impact of the unaccounted quality space -the image quality features not considered by IQA -in contributing to performance prediction errors.
The locations of the eyes are the most commonly used features to perform face normalization (i. e., alignment of facial features), which is an essential preprocessing stage of many face recognition systems. In this paper, we study the sensitivity of open source implementations of five face recognition algorithms to misalignment caused by eye localization errors. We investigate the ambiguity in location of the eyes by comparing the difference between two independent manual eye annotations. We also study the error characteristics of automatic eye detectors present in two commercial face recognition systems. Furthermore, we explore the impact of using different eye detectors for training/enrollment and query phases of a face recognition system. These experiments provide an insight into the influence of eye localization errors on the performance of face recognition systems and recommend a strategy for the design of training and test sets of a face recognition algorithm.
Chapbooks were short, cheap printed booklets produced in large quantities in Scotland, England, Ireland, North America and much of Europe between roughly the seventeenth and nineteenth centuries. A form of popular literature containing songs, stories, poems, games, riddles, religious writings and other content designed to appeal to a wide readership, they were frequently illustrated, particularly on their title-pages. This paper describes the visual analysis of such chapbook illustrations. We automatically extract all the illustrations contained in the National Library of Scotland Chapbooks Printed in Scotland dataset, and create a visual search engine to search this dataset using full or part-illustrations as queries. We also cluster these illustrations based on their visual content, and provide keyword-based search of the metadata associated with each publication. The visual search; clustering of illustrations based on visual content; and metadata search features enable researchers to forensically analyse the chapbooks dataset and to discover unnoticed relationships between its elements. We release all annotations
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.