A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells

Motion direction detection is an essential task for both computer vision and neuroscience. Inspired by the biological theory of the human visual system, we proposed a learnable horizontal-cell-based dendritic neuron model (HCdM) that captures motion direction with high efficiency while remaining hig...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianqi Chen, Yuki Todo, Zhiyu Qiu, Yuxiao Hua, Hiroki Sugiura, Zheng Tang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Biomimetics
Subjects:
Online Access:https://www.mdpi.com/2313-7673/10/5/286
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327631793651712
author Tianqi Chen
Yuki Todo
Zhiyu Qiu
Yuxiao Hua
Hiroki Sugiura
Zheng Tang
author_facet Tianqi Chen
Yuki Todo
Zhiyu Qiu
Yuxiao Hua
Hiroki Sugiura
Zheng Tang
author_sort Tianqi Chen
collection DOAJ
description Motion direction detection is an essential task for both computer vision and neuroscience. Inspired by the biological theory of the human visual system, we proposed a learnable horizontal-cell-based dendritic neuron model (HCdM) that captures motion direction with high efficiency while remaining highly robust. Unlike present deep learning models, which rely on extension of computation and extraction of global features, the HCdM mimics the localized processing of dendritic neurons, enabling efficient motion feature integration. Through synaptic learning that prunes unnecessary parts, our model maintains high accuracy in noised images, particularly against salt-and-pepper noise. Experimental results show that the HCdM reached over 99.5% test accuracy, maintained robust performance under 10% salt-and-pepper noise, and achieved cross-dataset generalization exceeding 80% in certain conditions. Comparisons with state-of-the-art (SOTA) models like vision transformers (ViTs) and convolutional neural networks (CNNs) demonstrate the HCdM’s robustness and efficiency. Additionally, in contrast to previous artificial visual systems (AVSs), our findings suggest that lateral geniculate nucleus (LGN) structures, though present in biological vision, may not be essential for motion direction detection. This insight provides a new direction for bio-inspired computational models. Future research will focus on hybridizing the HCdM with SOTA models that perform well on complex visual scenes to enhance its adaptability.
format Article
id doaj-art-37958391b14f40fda4eeb226c387a20c
institution Kabale University
issn 2313-7673
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-37958391b14f40fda4eeb226c387a20c2025-08-20T03:47:49ZengMDPI AGBiomimetics2313-76732025-05-0110528610.3390/biomimetics10050286A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal CellsTianqi Chen0Yuki Todo1Zhiyu Qiu2Yuxiao Hua3Hiroki Sugiura4Zheng Tang5Division of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, JapanFaculty of Electrical, Information and Communication Engineering, Kanazawa University, Kanazawa 920-1192, JapanDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, JapanDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, JapanDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, JapanInstitute of AI for Industries, Chinese Academy of Sciences Nanjing, Nanjing 210008, ChinaMotion direction detection is an essential task for both computer vision and neuroscience. Inspired by the biological theory of the human visual system, we proposed a learnable horizontal-cell-based dendritic neuron model (HCdM) that captures motion direction with high efficiency while remaining highly robust. Unlike present deep learning models, which rely on extension of computation and extraction of global features, the HCdM mimics the localized processing of dendritic neurons, enabling efficient motion feature integration. Through synaptic learning that prunes unnecessary parts, our model maintains high accuracy in noised images, particularly against salt-and-pepper noise. Experimental results show that the HCdM reached over 99.5% test accuracy, maintained robust performance under 10% salt-and-pepper noise, and achieved cross-dataset generalization exceeding 80% in certain conditions. Comparisons with state-of-the-art (SOTA) models like vision transformers (ViTs) and convolutional neural networks (CNNs) demonstrate the HCdM’s robustness and efficiency. Additionally, in contrast to previous artificial visual systems (AVSs), our findings suggest that lateral geniculate nucleus (LGN) structures, though present in biological vision, may not be essential for motion direction detection. This insight provides a new direction for bio-inspired computational models. Future research will focus on hybridizing the HCdM with SOTA models that perform well on complex visual scenes to enhance its adaptability.https://www.mdpi.com/2313-7673/10/5/286motion direction detectionartificial visual systemdendritic neuron modelsynaptic learningmachine learningbio-inspired model
spellingShingle Tianqi Chen
Yuki Todo
Zhiyu Qiu
Yuxiao Hua
Hiroki Sugiura
Zheng Tang
A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells
Biomimetics
motion direction detection
artificial visual system
dendritic neuron model
synaptic learning
machine learning
bio-inspired model
title A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells
title_full A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells
title_fullStr A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells
title_full_unstemmed A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells
title_short A Bio-Inspired Learning Dendritic Motion Detection Framework with Direction-Selective Horizontal Cells
title_sort bio inspired learning dendritic motion detection framework with direction selective horizontal cells
topic motion direction detection
artificial visual system
dendritic neuron model
synaptic learning
machine learning
bio-inspired model
url https://www.mdpi.com/2313-7673/10/5/286
work_keys_str_mv AT tianqichen abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT yukitodo abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT zhiyuqiu abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT yuxiaohua abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT hirokisugiura abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT zhengtang abioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT tianqichen bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT yukitodo bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT zhiyuqiu bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT yuxiaohua bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT hirokisugiura bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells
AT zhengtang bioinspiredlearningdendriticmotiondetectionframeworkwithdirectionselectivehorizontalcells