Home > In process > Real-Time Emotion Recognition Performance of Mobile Devices: A Detailed Analysis of Camera and TrueDepth Sensors Using Apple's ARKit. > print

001     285257
005     20260217100411.0
024 7 _ |a 10.3390/s26031060
|2 doi
024 7 _ |a pmid:41682575
|2 pmid
024 7 _ |a pmc:PMC12899966
|2 pmc
037 _ _ |a DZNE-2026-00199
041 _ _ |a English
082 _ _ |a 620
100 1 _ |a Aldenhoven, Céline Madeleine
|0 0009-0005-8655-493X
|b 0
245 _ _ |a Real-Time Emotion Recognition Performance of Mobile Devices: A Detailed Analysis of Camera and TrueDepth Sensors Using Apple's ARKit.
260 _ _ |a Basel
|c 2026
|b MDPI
336 7 _ |a article
|2 DRIVER
336 7 _ |a Output Types/Journal article
|2 DataCite
336 7 _ |a Journal Article
|b journal
|m journal
|0 PUB:(DE-HGF)16
|s 1771318847_24677
|2 PUB:(DE-HGF)
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a JOURNAL_ARTICLE
|2 ORCID
336 7 _ |a Journal Article
|0 0
|2 EndNote
520 _ _ |a Facial features hold information about a person's emotions, motor function, or genetic defects. Since most current mobile devices are capable of real-time face detection using cameras and depth sensors, real-time facial analysis can be utilized in several mobile use cases. Understanding the real-time emotion recognition capabilities of device sensors and frameworks is vital for developing new, valid applications. Therefore, we evaluated on-device emotion recognition using Apple's ARKit on an iPhone 14 Pro. A native app elicited 36 blend shape-specific movements and 7 discrete emotions from N=31 healthy adults. Per frame, standardized ARKit blend shapes were classified using a prototype-based cosine similarity metric; performance was summarized as accuracy and area under the receiver operating characteristic curves. Cosine similarity achieved an overall accuracy of 68.3%, exceeding the mean of three human raters (58.9%; +9.4 percentage points, ≈16% relative). Per-emotion accuracy was highest for joy, fear, sadness, and surprise, and competitive for anger, disgust, and contempt. AUCs were ≥0.84 for all classes. The method runs in real time on-device using only vector operations, preserving privacy and minimizing compute. These results indicate that a simple, interpretable cosine-similarity classifier over ARKit blend shapes delivers human-comparable, real-time facial emotion recognition on commodity hardware, supporting privacy-preserving mobile applications.
536 _ _ |a 353 - Clinical and Health Care Research (POF4-353)
|0 G:(DE-HGF)POF4-353
|c POF4-353
|f POF IV
|x 0
588 _ _ |a Dataset connected to CrossRef, PubMed, , Journals: pub.dzne.de
650 _ 7 |a ARKit
|2 Other
650 _ 7 |a emotion recognition
|2 Other
650 _ 7 |a face tracking
|2 Other
650 _ 7 |a real-time
|2 Other
650 _ 7 |a sensors
|2 Other
650 _ 2 |a Humans
|2 MeSH
650 _ 2 |a Emotions: physiology
|2 MeSH
650 _ 2 |a Adult
|2 MeSH
650 _ 2 |a Male
|2 MeSH
650 _ 2 |a Female
|2 MeSH
650 _ 2 |a Mobile Applications
|2 MeSH
650 _ 2 |a Smartphone
|2 MeSH
650 _ 2 |a Young Adult
|2 MeSH
650 _ 2 |a Facial Expression
|2 MeSH
700 1 _ |a Nissen, Leon
|0 0009-0009-3884-0850
|b 1
700 1 _ |a Heinemann, Marie
|0 0009-0001-1402-0876
|b 2
700 1 _ |a Dogdu, Cem
|0 P:(DE-2719)9002372
|b 3
|u dzne
700 1 _ |a Hanke, Alexander
|b 4
700 1 _ |a Jonas, Stephan
|0 0000-0002-3687-6165
|b 5
700 1 _ |a Reimer, Lara Marie
|0 P:(DE-2719)9002403
|b 6
|u dzne
773 _ _ |a 10.3390/s26031060
|g Vol. 26, no. 3, p. 1060 -
|0 PERI:(DE-600)2052857-7
|n 3
|p 1060
|t Sensors
|v 26
|y 2026
|x 1424-8220
856 4 _ |u https://pub.dzne.de/record/285257/files/DZNE-2026-00199.pdf
|y Restricted
856 4 _ |u https://pub.dzne.de/record/285257/files/DZNE-2026-00199.pdf?subformat=pdfa
|x pdfa
|y Restricted
910 1 _ |a Deutsches Zentrum für Neurodegenerative Erkrankungen
|0 I:(DE-588)1065079516
|k DZNE
|b 3
|6 P:(DE-2719)9002372
910 1 _ |a External Institute
|0 I:(DE-HGF)0
|k Extern
|b 6
|6 P:(DE-2719)9002403
913 1 _ |a DE-HGF
|b Gesundheit
|l Neurodegenerative Diseases
|1 G:(DE-HGF)POF4-350
|0 G:(DE-HGF)POF4-353
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-300
|4 G:(DE-HGF)POF
|v Clinical and Health Care Research
|x 0
915 _ _ |a JCR
|0 StatID:(DE-HGF)0100
|2 StatID
|b SENSORS-BASEL : 2022
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0200
|2 StatID
|b SCOPUS
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0300
|2 StatID
|b Medline
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0320
|2 StatID
|b PubMed Central
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0501
|2 StatID
|b DOAJ Seal
|d 2024-04-10T15:28:10Z
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0500
|2 StatID
|b DOAJ
|d 2024-04-10T15:28:10Z
915 _ _ |a Peer Review
|0 StatID:(DE-HGF)0030
|2 StatID
|b DOAJ : Anonymous peer review
|d 2024-04-10T15:28:10Z
915 _ _ |a Creative Commons Attribution CC BY (No Version)
|0 LIC:(DE-HGF)CCBYNV
|2 V:(DE-HGF)
|b DOAJ
|d 2024-04-10T15:28:10Z
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0600
|2 StatID
|b Ebsco Academic Search
|d 2025-11-11
915 _ _ |a Peer Review
|0 StatID:(DE-HGF)0030
|2 StatID
|b ASC
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0199
|2 StatID
|b Clarivate Analytics Master Journal List
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1150
|2 StatID
|b Current Contents - Physical, Chemical and Earth Sciences
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1160
|2 StatID
|b Current Contents - Engineering, Computing and Technology
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0160
|2 StatID
|b Essential Science Indicators
|d 2025-11-11
915 _ _ |a WoS
|0 StatID:(DE-HGF)0113
|2 StatID
|b Science Citation Index Expanded
|d 2025-11-11
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0150
|2 StatID
|b Web of Science Core Collection
|d 2025-11-11
915 _ _ |a IF < 5
|0 StatID:(DE-HGF)9900
|2 StatID
|d 2025-11-11
915 _ _ |a Article Processing Charges
|0 StatID:(DE-HGF)0561
|2 StatID
|d 2025-11-11
915 _ _ |a Fees
|0 StatID:(DE-HGF)0700
|2 StatID
|d 2025-11-11
920 1 _ |0 I:(DE-2719)1011305
|k AG Schneider
|l Translational Dementia Research (Bonn)
|x 0
980 _ _ |a journal
980 _ _ |a EDITORS
980 _ _ |a VDBINPRINT
980 _ _ |a I:(DE-2719)1011305
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21