ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2021-08-17 13:55
Study of an Event-Driven CMOS Image Sensor Using Deep Learning (1) -- Verification of Image Classification Using Low Bit-Resolution Feature Images --
Kohei Yamamoto, Kota Yoshida, Shunsuke Okura (Ritsumeikan Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Currently, CMOS image sensors are expected to be integrated with AI using deep learning to create new technologies.
Conventional image sensors output image data with a large amount of information for humans to appreciate as photographs.
However, there is a lo t of useless and unnecessary data for AI to use for image recognition, which is thought to lead to increased power consumption and latency of the entire system.
Therefore, we thought it would be possible to reduce the power consumption of image sensors if image sensors could output images with a small amount of information when performing image recognition and AI could perform recognition.
In this paper, we examined the pixel configuration that enables feature extraction using photoelectric conversion electrons, and verified whether image classification is possible.
We also examined the effect of the bit resolution of the image obtained by intra-pixel arithmetic on the recognition rate of the image in order to achieve low power consumption during the feature extraction operation.
Keyword (in Japanese) (See Japanese page) 
(in English) CMOS / feature extraction / intra-pixel arithmetic / histogram equalization / / / /  
Reference Info. ITE Tech. Rep., vol. 45, no. 21, IST2021-43, pp. 29-33, Aug. 2021.
Paper # IST2021-43 
Date of Issue 2021-08-10 (IST) 
ISSN Print edition: ISSN 1342-6893    Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee IEICE-SDM IEICE-ICD IST  
Conference Date 2021-08-17 - 2021-08-18 
Place (in Japanese) (See Japanese page) 
Place (in English) Online 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Analog, Mixed Analog and Digital, RF, and Sensor Interface, Low Voltage/Low Power Techniques, Novel Devices/Circuits, and the Applications 
Paper Information
Registration To IST 
Conference Code 2021-08-SDM-ICD-IST 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Study of an Event-Driven CMOS Image Sensor Using Deep Learning (1) 
Sub Title (in English) Verification of Image Classification Using Low Bit-Resolution Feature Images 
Keyword(1) CMOS  
Keyword(2) feature extraction  
Keyword(3) intra-pixel arithmetic  
Keyword(4) histogram equalization  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Kohei Yamamoto  
1st Author's Affiliation Ritsumeikan University (Ritsumeikan Univ.)
2nd Author's Name Kota Yoshida  
2nd Author's Affiliation Ritsumeikan University (Ritsumeikan Univ.)
3rd Author's Name Shunsuke Okura  
3rd Author's Affiliation Ritsumeikan University (Ritsumeikan Univ.)
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2021-08-17 13:55:00 
Presentation Time 25 minutes 
Registration for IST 
Paper # IST2021-43 
Volume (vol) vol.45 
Number (no) no.21 
Page pp.29-33 
#Pages
Date of Issue 2021-08-10 (IST) 


[Return to Top Page]

[Return to ITE Web Page]


The Institute of Image Information and Television Engineers (ITE), Japan