{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T00:59:07Z","timestamp":1770166747974,"version":"3.49.0"},"reference-count":30,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["JP24K15001"],"award-info":[{"award-number":["JP24K15001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>To address the power constraints of the emerging Internet of Things (IoT) era, we propose a compression-efficient feature extraction method for a CMOS image sensor that can extract binary feature data. This sensor outputs six-channel binary feature data, comprising three channels of binarized luminance signals and three channels of horizontal edge signals, compressed via a run length encoding (RLE) method. This approach significantly reduces data transmission volume while maintaining image recognition accuracy. The simulation results obtained using a YOLOv7-based model designed for edge GPUs demonstrate that our approach achieves a large object recognition accuracy (APL50) of 60.7% on the COCO dataset while reducing the data size by 99.2% relative to conventional 8-bit RGB color images. Furthermore, the image classification results using MobileNetV3 tailored for mobile devices on the Visual Wake Words (VWW) dataset show that our approach reduces data size by 99.0% relative to conventional 8-bit RGB color images and achieves an image classification accuracy of 89.4%. These results are superior to the conventional trade-off between recognition accuracy and data size, thereby enabling the realization of low-power image recognition systems.<\/jats:p>","DOI":"10.3390\/s26030962","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T12:46:11Z","timestamp":1770122771000},"page":"962","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Compression-Efficient Feature Extraction Method for a CMOS Image Sensor"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1132-4712","authenticated-orcid":false,"given":"Keiichiro","family":"Kuroda","sequence":"first","affiliation":[{"name":"Graduate School of Science and Engineering, Ritsumeikan University, 1-1-1 Nojihigashi, Kusatsu-shi 525-8577, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Osuka","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Engineering, Ritsumeikan University, 1-1-1 Nojihigashi, Kusatsu-shi 525-8577, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryoya","family":"Iegaki","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Engineering, Ritsumeikan University, 1-1-1 Nojihigashi, Kusatsu-shi 525-8577, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryuichi","family":"Ujiie","sequence":"additional","affiliation":[{"name":"Nisshinbo Micro Devices Inc., 3-10 Nihonbashi Yokoyama-cho, Chuo-ku, Tokyo 103-8456, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hideki","family":"Shima","sequence":"additional","affiliation":[{"name":"Nisshinbo Micro Devices Inc., 3-10 Nihonbashi Yokoyama-cho, Chuo-ku, Tokyo 103-8456, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1293-6415","authenticated-orcid":false,"given":"Kota","family":"Yoshida","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Engineering, Ritsumeikan University, 1-1-1 Nojihigashi, Kusatsu-shi 525-8577, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6422-3703","authenticated-orcid":false,"given":"Shunsuke","family":"Okura","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Engineering, Ritsumeikan University, 1-1-1 Nojihigashi, Kusatsu-shi 525-8577, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"ref_1","unstructured":"Government of Japan, and Cabinet Office (2023, November 05). Society 5.0. Available online: https:\/\/www8.cao.go.jp\/cstp\/english\/society5_0\/index.html."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_3","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_4","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst., 25."},{"key":"ref_5","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014). Microsoft coco: Common objects in context. Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, 6\u201312 September 2014, Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","article-title":"The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale","volume":"128","author":"Kuznetsova","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_11","unstructured":"Chowdhery, A., Warden, P., Shlens, J., Howard, A., and Rhodes, R. (2019). Visual wake words dataset. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2932","DOI":"10.1109\/JSSC.2019.2937437","article-title":"A data-compressive 1.5\/2.75-bit log-gradient QVGA image sensor with multi-scale readout for always-on object detection","volume":"54","author":"Young","year":"2019","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref_13","unstructured":"Yoneda, S., Negoro, Y., Kobayashi, H., Nei, K., Takeuchi, T., Oota, M., Kawata, T., Ikeda, T., and Yamazaki, S. (2019, January 23\u201327). Image Sensor Capable of Analog Convolution for Real-time Image Recognition System Using Crystalline Oxide Semiconductor FET. Proceedings of the 2019 International Image Sensor Workshop (IISW 2019), Snowbird, UT, USA."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Finateu, T., Niwa, A., Matolin, D., Tsuchimoto, K., Mascheroni, A., Reynaud, E., Mostafalu, P., Brady, F., Chotard, L., and LeGoff, F. (2020, January 16\u201320). 5.10 A 1280\u00d7 720 back-illuminated stacked temporal contrast event-based vision sensor with 4.86 \u03bcm pixels, 1.066 GEPS readout, programmable event-rate controller and compressive data-formatting pipeline. Proceedings of the 2020 IEEE International Solid-State Circuits Conference-(ISSCC), San Francisco, CA, USA.","DOI":"10.1109\/ISSCC19947.2020.9063149"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Suh, Y., Choi, S., Ito, M., Kim, J., Lee, Y., Seo, J., Jung, H., Yeo, D.H., Namgung, S., and Bong, J. (2020, January 10\u201321). A 1280\u00d7 960 dynamic vision sensor with a 4.95-\u03bcm pixel pitch and motion artifact minimization. Proceedings of the 2020 IEEE international symposium on circuits and systems (ISCAS), Sevilla, Spain.","DOI":"10.1109\/ISCAS45731.2020.9180436"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Lichtsteiner, P., Posch, C., and Delbruck, T. (2006, January 6\u20139). A 128 x 128 120db 30mw asynchronous vision sensor that responds to relative intensity change. Proceedings of the 2006 IEEE International Solid State Circuits Conference-Digest of Technical Papers, San Francisco, CA, USA.","DOI":"10.1109\/ISSCC.2006.1696265"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Son, B., Suh, Y., Kim, S., Jung, H., Kim, J.S., Shin, C.W., Park, K., Lee, K., Park, J.M., and Woo, J. (2017, January 5\u20139). 4.1 A 640\u00d7480 dynamic vision sensor with a 9\u00b5m pixel and 300Meps address-event representation. Proceedings of the 2017 IEEE International Solid-State Circuits Conference (ISSCC), San Francisco, CA, USA.","DOI":"10.1109\/ISSCC.2017.7870263"},{"key":"ref_18","unstructured":"Okura, S., Otani, A., Itsuki, K., Kitazawa, Y., Yamamoto, K., Osuka, Y., Morikaku, Y., and Yoshida, K. (2023, January 21\u201325). A study on a feature extractable CMOS image sensor for low-power image classification system. Proceedings of the 2023 International Image Sensor Workshop, Crieff, UK."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Morikaku, Y., Ujiie, R., Morikawa, D., Shima, H., Yoshida, K., and Okura, S. (2024). On-Chip Data Reduction and Object Detection for a Feature-Extractable CMOS Image Sensor. Electronics, 13.","DOI":"10.3390\/electronics13214295"},{"key":"ref_20","first-page":"102","article-title":"[Paper] Lightweight Object Detection Model for a CMOS Image Sensor with Binary Feature Extraction","volume":"14","author":"Kuroda","year":"2026","journal-title":"ITE Trans. Media Technol. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 18\u201322). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/LSSC.2025.3628314","article-title":"A 0.8 \u03bcm 32Mpixel Always-On CMOS Image Sensor with Windmill-Pattern Edge Extraction and On-Chip DNN","volume":"8","author":"Sato","year":"2025","journal-title":"IEEE Solid-State Circuits Lett."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Lee, S., Yun, Y.C., Heu, S.M., Lee, K.H., Lee, S.J., Lee, K., Moon, J., Lim, H., Jang, T., and Song, M. (2025). The Design of a Computer Vision Sensor Based on a Low-Power Edge Detection Circuit. Sensors, 25.","DOI":"10.3390\/s25103219"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Okumura, S., Morikaku, Y., Osuka, Y., Ujiie, R., Morikawa, D., Shima, H., and Okura, S. (2023, January 16\u201317). Feature Extractable CMOS Image Sensor Pixel with RGB to Grayscale Conversion. Proceedings of the 2023 IEEE International Meeting for Future of Electron Devices, Kansai (IMFEDK), Kyoto, Japan.","DOI":"10.1109\/IMFEDK60983.2023.10366346"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Takayanagi, I., Yoshimura, N., Mori, K., Matsuo, S., Tanaka, S., Abe, H., Yasuda, N., Ishikawa, K., Okura, S., and Ohsawa, S. (2018). An over 90 dB intra-scene single-exposure dynamic range CMOS image sensor using a 3.0 \u03bcm triple-gain pixel fabricated in a standard BSI process. Sensors, 18.","DOI":"10.3390\/s18010203"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Matsubara, I., Ujiie, R., Morikawa, D., Shima, H., and Okura, S. (2025, January 7\u201310). A Scalable Single-Slope ADC for a Feature-Extractable CMOS Image Sensor. Proceedings of the 2025 International Technical Conference on Circuits\/Systems, Computers, and Communications (ITC-CSCC), Seoul, Republic of Korea.","DOI":"10.1109\/ITC-CSCC66376.2025.11137679"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (2019, January 27\u201328). Searching for mobilenetv3. Proceedings of the EEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_28","unstructured":"Banbury, C., Njor, E., Garavagno, A.M., Mazumder, M., Stewart, M., Warden, P., Kudlur, M., Jeffries, N., Fafoutis, X., and Reddi, V.J. (2024). Wake vision: A tailored dataset and benchmark suite for tinyml computer vision applications. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Verdant, A., Guicquero, W., Coriat, D., Moritz, G., Royer, N., Thuries, S., Mollard, A., Teil, V., Desprez, Y., and Monnot, G. (2024, January 16\u201320). A 450\u03bcW@ 50fps Wake-Up Module Featuring Auto-Bracketed 3-Scale Log-Corrected Pattern Recognition and Motion Detection in a 1.5 Mpix 8T Global Shutter Imager. Proceedings of the 2024 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits), Honolulu, HI, USA.","DOI":"10.1109\/VLSITechnologyandCir46783.2024.10631350"},{"key":"ref_30","first-page":"4","article-title":"PASCALRAW: Raw image database for object detection","volume":"2","author":"Ta","year":"2014","journal-title":"Stanf. Digit. Repos."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/962\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T12:51:00Z","timestamp":1770123060000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/962"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":30,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["s26030962"],"URL":"https:\/\/doi.org\/10.3390\/s26030962","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]}}}