Supporting Historical Photo Identification with Face Recognition and Crowdsourced Human Expertise (Extended Abstract)

Mohanty, Vikram; Thames, David; Mehta, Sneha; Luther, Kurt

doi:10.24963/ijcai.2020/660

“…Moddrop [20] is based on multi-scale and multi-modal deep learning for gesture detection and localization. Photo Sleuth [48] is a web-based platform for user authentication, which can help users successfully identify unknown portraits. Song [49] utilized a single stereo camera to track the body and hands and adopt modelbased methods and particle filters to reconstruct body posture in 3D space to achieve human-computer interaction.…”

Section: Vision-based Motion Recognitionmentioning

confidence: 99%

Wi-ID: WiFi-Based Identification System Using Rock-Paper-Scissors Hand Gestures

Zheng

¹

,

Yu

²

,

Zhang

³

et al. 2022

Wireless Pers Commun

3

0

View full text Add to dashboard Cite

This paper proposes using a WiFi-based identification system, Wi-ID, to identify users from their unique hand gestures. Hand gestures from the popular game rock-paper-scissors are utilized for the system's user authentication commands. The whole feature of three hand gestures is extracted instead of the single gesture feature extracted by the existing methods. Dynamic time warping (DTW) is utilized to analyze the amplitude information in the time domain based on linear discriminant analysis (LDA), while extract amplitude kurtosis (AP-KU) and shape skewness (SP-SK) are utilized to analyze the Wi-Fi signals energy distribution in the frequency domain. Based on the contributions of the extracted features, the random forests algorithm is utilized for weight inputs in the LSTM model. The experiment is conducted on a computer installed with an Intel 5300 wireless networking card to evaluate

show abstract

“…Users can carefully inspect individual search results to determine whether they are facially similar to the query photo and whether the biographical information (e.g., military service records) line up with the visual clues of the query photo (e.g., uniform insignia). However, prior work has shown that the correct match is often ranked beyond the top-5 and top-50 face recognition results [4,5]. SleuthTalk provides an intelligent user interface to allow users add any potential matches to a shortlist from the facial recognition results and then create a project for analyzing these shortlisted candidates in a focused manner.…”

Section: Intelligent Shortlistsmentioning

confidence: 99%

SleuthTalk: Identifying Historical Photos with Intelligent Shortlists, Private Collaboration, and Structured Feedback

Yuan

¹

,

Mohanty

²

,

Luther

³

2021

Companion Publication of the 2021 Conference on Computer Supported Cooperative Work and Social Computing

Self Cite

0

View full text Add to dashboard Cite

Identifying people in photographs is an important task in many fields, including history, journalism, genealogy, and collecting, but accurate person identification remains challenging. Researchers especially struggle with the "last-mile proble" of historical person identification, where they must make a selection among a small number of highly similar candidates. We present SleuthTalk, a webbased collaboration tool integrated into the public website Civil War Photo Sleuth which addresses the last-mile problem in historical person identification by providing support for shortlisting potential candidates from face recognition results, private collaborative workspaces, and structured feedback. CCS CONCEPTS• Human-centered computing → Collaborative and social computing systems and tools; • Applied computing → Arts and humanities; • Computing methodologies → Biometrics.

show abstract

Wi-ID: WiFi-Based Identification System Using Rock-Paper-Scissors Hand Gestures

Zheng

¹

,

Yu

²

,

Zhang

³

et al. 2022

Preprint

1

0

View full text Add to dashboard Cite

This paper proposes using a WiFi-based identification system, Wi-ID, to identify users from their unique hand gestures. Hand gestures from the popular game rock-paper-scissors are utilized for the system’s user authentication commands. The whole feature of three hand gestures is extracted instead of the single gesture feature extracted by the existing methods. Dynamic time warping (DTW) is utilized to analyze the amplitude information in the time domain based on linear discriminant analysis (LDA), while extract amplitude kurtosis (AP-KU) and shape skewness (SP-SK) are utilized to analyze the Wi-Fi signals energy distribution in the frequency domain. Based on the contributions of the extracted features, the random forests algorithm is utilized for weight inputs in the LSTM model. The experiment is conducted on a computer installed with an Intel 5300 wireless networking card to evaluate the effectiveness and robustness of the Wi-ID system. The experiment results showed the accuracy of the proposed Wi-ID system has a personal differentiation accuracy rate over 92%, and with an average accuracy of 96%. Authorized persons who performed incomplete hand gestures are identified with an accuracy of 92% and hostile intruders can be identified with a probability of 90%. Such performance demonstrates that the Wi-ID system achieved the aim of user authentication.

show abstract

Supporting Historical Photo Identification with Face Recognition and Crowdsourced Human Expertise (Extended Abstract)

Cited by 3 publications

References 2 publications

Wi-ID: WiFi-Based Identification System Using Rock-Paper-Scissors Hand Gestures

Wi-ID: WiFi-Based Identification System Using Rock-Paper-Scissors Hand Gestures

SleuthTalk: Identifying Historical Photos with Intelligent Shortlists, Private Collaboration, and Structured Feedback

Wi-ID: WiFi-Based Identification System Using Rock-Paper-Scissors Hand Gestures

Contact Info

Product

Resources

About