Dr. Shun Miura Profile

Dr. Shun Miura

at Fujikura Ltd.

SPIE Involvement:

Author

Publications (2)

This will count as one of your downloads.

You will have access to both the presentation and article (if available).

DOWNLOAD NOW

This content is available for download via your institution's subscription. To access this item, please sign in to your personal account.

Email or Username Forgot your username?

Password Forgot your password?

Show

Keep me signed in

No SPIE account? Create an account

Proceedings Article | 28 May 2024 Presentation + Paper

High accuracy object detection by an optical neural network implementation

Mamoru Otake, Shun Miura, Hiroyuki Kusaka, Masahiro Kashiwagi, Yuichiro Kunai, Takahiro Nambara, Yumi Yamada

Proceedings Volume 13083, 1308303 (2024) https://doi.org/10.1117/12.3020003

KEYWORDS: Object detection, Target detection, Neural networks, Spatial light modulators, Education and training, Phase modulation, Simulations

Read Abstract +

In recent years, AI technology using Neural Network (NN) has made remarkable progress and is used for highly accurate classification, object detection, and anomaly detection in sensing. The difficulties with high-accuracy NN are the long processing time and high-power consumption. As one solution, an optical neural network (ONN), which realizes NN by diffraction and propagation of light, has attracted attention as an implementation method with ultra-high speed and low power consumption. Although many of the prior studies on ONN are related to classification, ONN has the potential to be applied to various tasks. As one example, the use of ONN has the possibility of ultra-fast object detection. In this study, simulations and experiments were conducted to verify the possibility of detection by ONN. Metal nuts were selected as the detection targets as a representative example of mass-produced industrial parts. In the experiment, SLM was used to implement the data input layer as phase input and the trained diffraction layer. First, the case of a single detection target in the input data was demonstrated. The precision for the 551-input data was 96.4 % in the experiment. In the data that could be detected correctly, the root mean square error between the inferred and correct positions was 2.2 % of the metal nut size. Next, another experiment has confirmed that ONN can detect multiple targets accurately. In addition, we examined ONN that uses light transmitted through the sample and found that the inference process finished within 4.17 msec (the response time of the CMOS of this setup). The results show that ONN can accurately and rapidly detect objects.

Proceedings Article | 22 May 2023 Presentation + Paper

High accuracy inference by an optical neural network implementation

Shun Miura, Mamoru Otake, Hiroyuki Kusaka, Masahiro Kashiwagi, Yuichiro Kunai, Takahiro Nambara, Yumi Yamada

Proceedings Volume 12327, 123270E (2023) https://doi.org/10.1117/12.2643679

KEYWORDS: Simulations, Neural networks, Mirrors, Spatial light modulators, Reflection, Image processing, Phase modulation, Neurons, Wavefronts

Read Abstract +

In recent years, sensing and imaging have significantly progressed due to AI algorithms such as Neural Network (NN). The main issues of applying NNs to information processing are the limited processing speed and high energy consumption of electronic processors. Optical Neural Network (ONN), which utilizes diffraction and propagation of light for processing, is an intriguing implementation of an ultra-fast and low-energy-consuming NN. However, previous studies of ONN are mainly on simulations due to the experimental difficulty of processing more than hundreds of input data. In hardware implementations, the performance or the classification accuracy of ONNs can be reduced by the noise and the displacements. Therefore, not only must the ONN achieve high theoretical accuracy, but it must also be robust to these experimental errors. In this study, the classification of 1,000 MNIST input data (100 data for each of 10 classes) was realized experimentally as well as theoretically, taking advantage of our novel setup with a variable spatial light modulator (SLM). With our experimental configuration, we investigated the classification accuracy with several loss functions for the ONN training. The inference accuracy of the MNIST classification task was up to 97% in the simulation and ~95% in the experiment by softmax-cross-entropy (SCE) loss function. Also, the classification accuracy of 98% for a Surface crack classification and 93% for a Pollen classification was achieved experimentally. These results show that SCE can realize high-accuracy classification in the ONN implementation. Our results revealed the high application capability of the optical neural network for practical sensing tasks.

My Library

You currently do not have any folders to save your paper to! Create a new folder below.

Folder Name

Folder Description

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks. You are receiving this notice because your organization may not have SPIE eBooks access.*

*Shibboleth/Open Athens users─please sign in to access your institution's subscriptions.

To obtain this item, you may purchase the complete book in print or electronic format on SPIE.org.

ORGANIZATIONAL
Sign in with credentials provided by your organization.

Organizational Username

Organizational Password

Show/Hide Password

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members:

Non-members: ADD TO CART

Keywords/Phrases

Search In:

Publication Years