Smartphone Facial Recognition - Revision history

User: /* Gallery */

2022-10-22T03:37:50Z

‎Gallery

User at 03:37, 22 October 2022

2022-10-22T03:37:49Z

User at 03:37, 22 October 2022

2022-10-22T03:37:49Z

User at 03:37, 22 October 2022

2022-10-22T03:37:49Z

User: /* Apple / FaceID */

2022-10-22T03:34:26Z

‎Apple / FaceID

User: /* Applications */

2022-10-22T03:34:22Z

‎Applications

User: /* Apple / FaceID */

2022-10-22T03:34:20Z

‎Apple / FaceID

User: /* Hardware */

2022-10-22T03:34:18Z

‎Hardware

User: /* Hardware */

2022-10-22T03:34:18Z

‎Hardware

User: /* Hardware */

2022-10-22T03:34:17Z

‎Hardware

@@ Line 49: / Line 49: @@
 [[File:Convolutional Layer.gif]]
 A demonstration of the convolutional process.
 [[File:Pooling Layer.gif]]
 A demonstration of the pooling layer.
 [[File:Pruning.png]]
 A visual of how pruning works.
 [[File:Quantizing.png]]
 A visual of how quantizing works.
 [[File:VGG-16 Architecture.jpg]]
 A diagram of the VGG-16 architecture, a popular CNN model for facial recognition.
 == References ==
 <references />

@@ Line 48: / Line 48: @@
 ==Gallery==
 == References ==
 <references />

← Older revision		Revision as of 03:37, 22 October 2022
Line 45:		Line 45:

	On most of its phones, Samsung uses a traditional camera setup to take a picture of the face and analyze its features.<ref name="scan"> Zdziarski, Z. (2020, December 24). ''Apple's and Samsung's face unlocking technologies.'' Zbigatron. Retrieved November 15, 2022, from https://zbigatron.com/apples-and-samsungs-face-unlocking-technologies/ </ref> Since it has been available since 2011, prior to the convolutional neural network revolution in facial recognition, it is unlikely that Samsung currently uses deep learning for its facial recognition software.<ref name="scan" /> Because it has no way to create a 3D map, its current devices can be unlocked with a photograph of the face and may not register if the user changes their appearance significantly.<name="scan" /> For two phones, the Galaxy S8 and the Galaxy S9, Samsung used iris scanning with an infrared camera.<ref name="scan" />. In the Galaxy S9, iris scanning was done with traditional facial recognition as part of its "Intelligent Scan," but can also be fooled with a picture and a contact lense.<ref name="scan" /> This was discontinued in later generations because the infrared camera was removed, and it is not clear what processes powered these systems or if neural networks were leveraged.<ref name="scan" /> To their credit, Samsung's processors incorporate convolutional neural networks into their design.<ref> Samsung. (n.d.). ''On-device AI: Mobile AI.'' Samsung Semiconductor Global. Retrieved November 15, 2022, from https://semiconductor.samsung.com/insights/topic/ai/on-device-ai/ </ref>		On most of its phones, Samsung uses a traditional camera setup to take a picture of the face and analyze its features.<ref name="scan"> Zdziarski, Z. (2020, December 24). ''Apple's and Samsung's face unlocking technologies.'' Zbigatron. Retrieved November 15, 2022, from https://zbigatron.com/apples-and-samsungs-face-unlocking-technologies/ </ref> Since it has been available since 2011, prior to the convolutional neural network revolution in facial recognition, it is unlikely that Samsung currently uses deep learning for its facial recognition software.<ref name="scan" /> Because it has no way to create a 3D map, its current devices can be unlocked with a photograph of the face and may not register if the user changes their appearance significantly.<name="scan" /> For two phones, the Galaxy S8 and the Galaxy S9, Samsung used iris scanning with an infrared camera.<ref name="scan" />. In the Galaxy S9, iris scanning was done with traditional facial recognition as part of its "Intelligent Scan," but can also be fooled with a picture and a contact lense.<ref name="scan" /> This was discontinued in later generations because the infrared camera was removed, and it is not clear what processes powered these systems or if neural networks were leveraged.<ref name="scan" /> To their credit, Samsung's processors incorporate convolutional neural networks into their design.<ref> Samsung. (n.d.). ''On-device AI: Mobile AI.'' Samsung Semiconductor Global. Retrieved November 15, 2022, from https://semiconductor.samsung.com/insights/topic/ai/on-device-ai/ </ref>
−

	==Gallery==		==Gallery==

@@ Line 45: / Line 45: @@
 On most of its phones, Samsung uses a traditional camera setup to take a picture of the face and analyze its features.<ref name="scan"> Zdziarski, Z. (2020, December 24). ''Apple's and Samsung's face unlocking technologies.'' Zbigatron. Retrieved November 15, 2022, from https://zbigatron.com/apples-and-samsungs-face-unlocking-technologies/ </ref> Since it has been available since 2011, prior to the convolutional neural network revolution in facial recognition, it is unlikely that Samsung currently uses deep learning for its facial recognition software.<ref name="scan" /> Because it has no way to create a 3D map, its current devices can be unlocked with a photograph of the face and may not register if the user changes their appearance significantly.<name="scan" /> For two phones, the Galaxy S8 and the Galaxy S9, Samsung used iris scanning with an infrared camera.<ref name="scan" />. In the Galaxy S9, iris scanning was done with traditional facial recognition as part of its "Intelligent Scan," but can also be fooled with a picture and a contact lense.<ref name="scan" /> This was discontinued in later generations because the infrared camera was removed, and it is not clear what processes powered these systems or if neural networks were leveraged.<ref name="scan" /> To their credit, Samsung's processors incorporate convolutional neural networks into their design.<ref> Samsung. (n.d.). ''On-device AI: Mobile AI.'' Samsung Semiconductor Global. Retrieved November 15, 2022, from https://semiconductor.samsung.com/insights/topic/ai/on-device-ai/ </ref>
 == References ==
 <references />

@@ Line 40: / Line 40: @@
 ===Apple / FaceID===
 Apple's FaceID facial recognition works by combining cameras with neural networks powered by its Bionic neural engine.<ref name="id"> Tillman, M. (2022, March 4). ''What is Apple Face ID and how does it work?'' Pocket-Lint. Retrieved November 15, 2022, from https://www.pocket-lint.com/phones/news/apple/142207-what-is-apple-face-id-and-how-does-it-work </ref> Using a dot projector that puts 30,000 points on a person's face and an infrared camera, the hardware system allows for detection of depth, preventing users from unlocking a phone with a picture.<ref name="id" /> Apple reveals that it uses a deep convolutional neural network to power face detection,<ref name="apple" /> but does not reveal the model for facial recognition. The process involves an initial setup by looking at the phone and rotating the user's head.<ref name="implement"> Di Palo, N. (2018, March 12). ''How I Implemented iPhone X’s FaceID Using Deep Learning in Python.'' Towards Data Science. Retrieved November 15, 2022, from https://towardsdatascience.com/how-i-implemented-iphone-xs-faceid-using-deep-learning-in-python-d5dbaa128e1d </ref> The speed of setup indicates that much of the neural network was pretrained.<ref name="implement" /> While speculative, a recreation of FaceID was made using a Siamese neural network [https://en.wikipedia.org/wiki/Siamese_neural_network] trained to maximize the distances between faces of different people.<ref name="implement" /> Siamese neural networks use twin neural networks that share all weights and can learn to compute distances between inputs, like images, which are mapped onto a low-dimensional feature space.<ref name="implement" /> The network is then trained so points from different classes (features of the face) are as far apart as possible.<ref name="implement" /> Thus, camera input can be compared to the reference image, which can be updated as appearance changes due to facial hair or makeup, creating a fully functioning neural net that becomes increasingly better at distinguishing between the user's face and others'.<ref name="implement" />
 == References ==
 <references />

@@ Line 34: / Line 34: @@
 ===Hardware===
-Since at least 2018, mobile chipmakers have focused on incorporating neural networks into their chip units, from the iPhone's Bionic Chip with a Neural Engine to Huawei's Neural Processing Unit.<ref> Neuromation. (2018, November 30). ''What's the deal with "Ai chips" in the latest smartphones?'' Medium. Retrieved November 15, 2022, from https://medium.com/neuromation-blog/whats-the-deal-with-ai-chips-in-the-latest-smartphones-28eb16dc9f45 </ref> The Kirin 970 aboard Huawei's P20 was the first to incorporate a separate neural processing unit for deep learning tasks, rather than rely on the CPU or GPU.<ref name="huawei"> Ignatov, A., Timofte, R., Chou, W., Wang, K., Wu, M., Hartley, T., & Van Gool, L. (2018). Ai benchmark: Running deep neural networks on android smartphones. In ''Proceedings of the European Conference on Computer Vision (ECCV) Workshops'' (pp. 0-0). </ref> This was followed by Samsung's Exynos 9810 chip<ref name="samsung" /> and Apple's A11 chip, which uses two separate cores for neural computation, which it uses in FaceID.<ref> Apple. (2018). ''iPhone XS Specs.'' Apple. Retrieved November 15, 2022, from https://web.archive.org/web/20190104041336/https://www.apple.com/iphone-xs/specs/ </ref> Notably, hardware acceleration for deep learning tasks for modern chips includes quantization up to one bit.<ref name="huawei" /> Additionally, mobile chipmaker Qualcomm has filed a patent for a method to jointly prune and quantize a deep neural network based on the operational abilities of a device.<ref> Qualcomm. (2021, March 25). ''Joint pruning and quantization scheme for deep neural networks patent application.'' USPTO.report. Retrieved November 15, 2022, from https://uspto.report/patent/app/20210089922 </ref>
+Since at least 2018, mobile chipmakers have focused on incorporating neural networks into their chip units, from the iPhone's Bionic Chip with a Neural Engine to Huawei's Neural Processing Unit.<ref> Neuromation. (2018, November 30). ''What's the deal with "Ai chips" in the latest smartphones?'' Medium. Retrieved November 15, 2022, from https://medium.com/neuromation-blog/whats-the-deal-with-ai-chips-in-the-latest-smartphones-28eb16dc9f45 </ref> The Kirin 970 aboard Huawei's P20 was the first to incorporate a separate neural processing unit for deep learning tasks, rather than rely on the CPU or GPU.<ref name="huawei"> Ignatov, A., Timofte, R., Chou, W., Wang, K., Wu, M., Hartley, T., & Van Gool, L. (2018). Ai benchmark: Running deep neural networks on android smartphones. In ''Proceedings of the European Conference on Computer Vision (ECCV) Workshops'' (pp. 0-0). </ref> This was followed by Samsung's Exynos 9810 chip<ref name="samsung" /> and Apple's A11 chip, which uses two separate cores for neural computation, which it uses in FaceID.<ref> Apple. (2018). ''iPhone XS Specs.'' Apple. Retrieved November 15, 2022, from https://web.archive.org/web/20190104041336/https://www.apple.com/iphone-xs/specs/ </ref> Notably, hardware acceleration for deep learning tasks for modern chips includes quantization up to one bit.<ref name="huawei" /> Additionally, mobile chipmaker Qualcomm has filed a patent for a method to jointly prune and quantize a deep neural network based on the operational abilities of a device.<ref> Qualcomm. (2021, March 25). ''Joint pruning and quantization scheme for deep neural networks patent application.'' USPTO.report. Retrieved November 15, 2022, from https://uspto.report/patent/app/20210089922 </ref> Pure performance increases of mobile chips have fueled the surge of neural networks in smartphones: The neural engine of Apple's latest chip (A16 Bionic) is capable of 17 trillion operations per second, almost 30 times the speed of the original, introduced five years prior, at 600 billion operations per second.<ref> Hristov, V. (2022, September 17). ''A16 Bionic explained: What's new in Apple's pro-grade Mobile chip? Phone Arena.'' Retrieved November 15, 2022, from https://www.phonearena.com/news/A16-Bionic-explained-whats-new_id142438 </ref>
 == Applications ==