Difference between revisions of "Smartphone Facial Recognition"
From Psyc 40 Wiki
| Line 3: | Line 3: | ||
'''Note: This page is incomplete.''' | '''Note: This page is incomplete.''' | ||
| − | + | Facial recognition systems are computer programs that match faces against a database [https://en.wikipedia.org/wiki/Facial_recognition_system]. A trivial task for humans, achieving high levels of accuracy in has been difficult for computers until recently. <ref> Brownlee, J. (2019, July 5). ''A gentle introduction to deep learning for face recognition.'' Machine Learning Mastery. Retrieved November 14, 2022, from https://machinelearningmastery.com/introduction-to-deep-learning-for-face-recognition/ </ref> This problem is compounded by the fact that deep learning models [https://en.wikipedia.org/wiki/Deep_learning] popular in modern facial recognition systems use much more memory, disk storage, and computational resources than traditional computer vision, presenting significant challenges to the limited hardware capabilities of smartphones. <ref name="apple"> Computer Vision Machine Learning Team. (2017, November). ''An on-device deep neural network for face detection.'' Apple Machine Learning Research. Retrieved November 14, 2022, from https://machinelearning.apple.com/research/face-detection#1 </ref> Accordingly, smartphone manufacturers have taken to creating processors with dedicated neural engines for deep learning tasks <ref> Samsung. (2018). ''Exynos 9810: Mobile Processor.'' Samsung Semiconductor Global. Retrieved November 14, 2022, from https://semiconductor.samsung.com/processor/mobile-processor/exynos-9-series-9810/ </ref> as well as creating simpler and more compact models that mimic the behavior of more complex models. <ref name="apple" /> The field of | |
== Model == | == Model == | ||
Revision as of 23:31, 21 October 2022
By Kenneth Wu
Note: This page is incomplete.
Facial recognition systems are computer programs that match faces against a database [1]. A trivial task for humans, achieving high levels of accuracy in has been difficult for computers until recently. [1] This problem is compounded by the fact that deep learning models [2] popular in modern facial recognition systems use much more memory, disk storage, and computational resources than traditional computer vision, presenting significant challenges to the limited hardware capabilities of smartphones. [2] Accordingly, smartphone manufacturers have taken to creating processors with dedicated neural engines for deep learning tasks [3] as well as creating simpler and more compact models that mimic the behavior of more complex models. [2] The field of
Contents
Model
History
Applications
References
- ↑ Brownlee, J. (2019, July 5). A gentle introduction to deep learning for face recognition. Machine Learning Mastery. Retrieved November 14, 2022, from https://machinelearningmastery.com/introduction-to-deep-learning-for-face-recognition/
- ↑ 2.0 2.1 Computer Vision Machine Learning Team. (2017, November). An on-device deep neural network for face detection. Apple Machine Learning Research. Retrieved November 14, 2022, from https://machinelearning.apple.com/research/face-detection#1
- ↑ Samsung. (2018). Exynos 9810: Mobile Processor. Samsung Semiconductor Global. Retrieved November 14, 2022, from https://semiconductor.samsung.com/processor/mobile-processor/exynos-9-series-9810/
