Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel Model
Stereo-orientation selectivity is a fundamental neural mechanism in the brain that plays a crucial role in perception. However, due to the recognition process of high-dimensional spatial information commonly occurring in high-order cortex, we still know little about the mechanisms underlying stereo-...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/1/38 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588959985696768 |
|---|---|
| author | Bin Li Yuki Todo Zheng Tang |
| author_facet | Bin Li Yuki Todo Zheng Tang |
| author_sort | Bin Li |
| collection | DOAJ |
| description | Stereo-orientation selectivity is a fundamental neural mechanism in the brain that plays a crucial role in perception. However, due to the recognition process of high-dimensional spatial information commonly occurring in high-order cortex, we still know little about the mechanisms underlying stereo-orientation selectivity and lack a modeling strategy. A classical explanation for the mechanism of two-dimensional orientation selectivity within the primary visual cortex is based on the Hubel-Wiesel model, a cascading neural connection structure. The local-to-global information aggregation thought within the Hubel-Wiesel model not only contributed to neurophysiology but also inspired the development of computer vision fields. In this paper, we provide a clear and efficient conceptual understanding of stereo-orientation selectivity and propose a quantitative explanation for its generation based on the thought of local-to-global information aggregation within the Hubel-Wiesel model and develop an artificial visual system (AVS) for stereo-orientation recognition. Our approach involves modeling depth selective cells to receive depth information, simple stereo-orientation selective cells for combining distinct depth information inputs to generate various local stereo-orientation selectivity, and complex stereo-orientation selective cells responsible for integrating the same local information to generate global stereo-orientation selectivity. Simulation results demonstrate that our AVS is effective in stereo-orientation recognition and robust against spatial noise jitters. AVS achieved an overall over 90% accuracy on noise data in orientation recognition tasks, significantly outperforming deep models. In addition, the AVS contributes to enhancing deep models’ performance, robustness, and stability in 3D object recognition tasks. Notably, AVS enhanced the TransNeXt model in improving its overall performance from 73.1% to 97.2% on the 3D-MNIST dataset and from 56.1% to 86.4% on the 3D-Fashion-MNIST dataset. Our explanation for the generation of stereo-orientation selectivity offers a reliable, explainable, and robust approach for extracting spatial features and provides a straightforward modeling method for neural computation research. |
| format | Article |
| id | doaj-art-31568c7fb0964b55bb5b4def0df871a6 |
| institution | Kabale University |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-31568c7fb0964b55bb5b4def0df871a62025-01-24T13:24:41ZengMDPI AGBiomimetics2313-76732025-01-011013810.3390/biomimetics10010038Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel ModelBin Li0Yuki Todo1Zheng Tang2Division of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa-shi 920-1192, JapanFaculty of Electrical, Information and Communication Engineering, Kanazawa University, Kanazawa-shi 920-1192, JapanInstitute of AI for Industries, Chinese Academy of Sciences, 168 Tianquan Road, Nanjing 211100, ChinaStereo-orientation selectivity is a fundamental neural mechanism in the brain that plays a crucial role in perception. However, due to the recognition process of high-dimensional spatial information commonly occurring in high-order cortex, we still know little about the mechanisms underlying stereo-orientation selectivity and lack a modeling strategy. A classical explanation for the mechanism of two-dimensional orientation selectivity within the primary visual cortex is based on the Hubel-Wiesel model, a cascading neural connection structure. The local-to-global information aggregation thought within the Hubel-Wiesel model not only contributed to neurophysiology but also inspired the development of computer vision fields. In this paper, we provide a clear and efficient conceptual understanding of stereo-orientation selectivity and propose a quantitative explanation for its generation based on the thought of local-to-global information aggregation within the Hubel-Wiesel model and develop an artificial visual system (AVS) for stereo-orientation recognition. Our approach involves modeling depth selective cells to receive depth information, simple stereo-orientation selective cells for combining distinct depth information inputs to generate various local stereo-orientation selectivity, and complex stereo-orientation selective cells responsible for integrating the same local information to generate global stereo-orientation selectivity. Simulation results demonstrate that our AVS is effective in stereo-orientation recognition and robust against spatial noise jitters. AVS achieved an overall over 90% accuracy on noise data in orientation recognition tasks, significantly outperforming deep models. In addition, the AVS contributes to enhancing deep models’ performance, robustness, and stability in 3D object recognition tasks. Notably, AVS enhanced the TransNeXt model in improving its overall performance from 73.1% to 97.2% on the 3D-MNIST dataset and from 56.1% to 86.4% on the 3D-Fashion-MNIST dataset. Our explanation for the generation of stereo-orientation selectivity offers a reliable, explainable, and robust approach for extracting spatial features and provides a straightforward modeling method for neural computation research.https://www.mdpi.com/2313-7673/10/1/38stereo-orientation selectivityHubel-Wiesel modelartificial visual system |
| spellingShingle | Bin Li Yuki Todo Zheng Tang Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel Model Biomimetics stereo-orientation selectivity Hubel-Wiesel model artificial visual system |
| title | Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel Model |
| title_full | Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel Model |
| title_fullStr | Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel Model |
| title_full_unstemmed | Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel Model |
| title_short | Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel Model |
| title_sort | artificial visual system for stereo orientation recognition based on hubel wiesel model |
| topic | stereo-orientation selectivity Hubel-Wiesel model artificial visual system |
| url | https://www.mdpi.com/2313-7673/10/1/38 |
| work_keys_str_mv | AT binli artificialvisualsystemforstereoorientationrecognitionbasedonhubelwieselmodel AT yukitodo artificialvisualsystemforstereoorientationrecognitionbasedonhubelwieselmodel AT zhengtang artificialvisualsystemforstereoorientationrecognitionbasedonhubelwieselmodel |