搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于随机放电神经元网络的彩色图像感知研究

徐子恒 何玉珠 康艳梅

引用本文:
Citation:

基于随机放电神经元网络的彩色图像感知研究

徐子恒, 何玉珠, 康艳梅

Color image perception based on stochastic spiking neural network

Xu Zi-Heng, He Yu-Zhu, Kang Yan-Mei
PDF
HTML
导出引用
  • 本文基于随机共振原理和人脑感知物体色彩的基本生物物理过程, 提出了一种低照度彩色图像增强的可解释算法. 我们首先研究了电导基积分放电神经元网络中的随机共振现象, 揭示了放电阈值、突触权重和集群规模对输出响应信噪比的影响, 并识别出放电阈值是影响随机共振效应的关键参数. 然后, 在结合彩色图像视觉感知的生理过程的基础上, 给出了一种基于随机放电神经元网络的彩色图像增强算法, 并以峰值信噪比(PSNR)和自然图像质量评估(NIQE)作为提取最优增强图像的度量指标. 注意到待增强的图像是非周期信号, 因此, 为了优化算法的性能, 首次提出了一种基于亮度分布的分位数的阈值选取策略. 数值实验结果表明, 该算法的增强效果良好且性能稳定, 并可用于军事探测和医学图像预处理等信号处理领域.
    Our aim is to present an interpretable algorithm for enhancing low-illuminance color image based on the principle of stochastic resonance and the fundamental biophysical process of human brain perceiving object color. To this end, the phenomenon of stochastic resonance in a conductance-based integrate-and-fire neuronal network is first explored, with the effect of firing threshold, synaptic weight and the population size on the signal-to-noise ratio revealed, and the firing threshold is recognized as the key parameter for the resonance effects. And then, a color image enhancement algorithm, where the peak signal-to-noise ratio and the natural image quality evaluator are adopted as quantifying indexes, is developed by combining the stochastic spiking neuronal network and the involved biophysical process relating to visual perception. Note that the enhanced image is aperiodic, thus in order to optimize the performance of the algorithm, an illuminance distribution based threshold strategy is given by us for the first time. The numerical tests show that the algorithm has good enhancement performance and stability. We wish this algorithm could be applied to relevant signal processing fields such as military detection and medical image preprocessing.
      通信作者: 康艳梅, ymkang@xjtu.edu.cn
    • 基金项目: 国家自然科学基金(批准号: 11772241, 12172268)资助的课题
      Corresponding author: Kang Yan-Mei, ymkang@xjtu.edu.cn
    • Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 11772241, 12172268).
    [1]

    Gonzalez C R, Woods R E 2002 Digital Image Processing (2nd Ed.) (New Jersey: Prentice Hall) pp88–108

    [2]

    Kwong R H, Johnston E W 1992 IEEE Trans. Signal Process. 40 1633Google Scholar

    [3]

    Dai Q, Pu Y F, Rahman Z, Aamir Z 2019 Symmetry Basel 11 574Google Scholar

    [4]

    Benzi R, Sutera A, Vulpiani, A 1981 J. Phys. A-Math. Gen. 14 453Google Scholar

    [5]

    Gammaitoni L, Hanggi P, Jung P, Marchesoni F 1998 Rev. Mod. Phys. 70 223Google Scholar

    [6]

    Simonotto E, Riani M, Seife C, Roberts M, Twitty J, Moss F 1997 Phys. Rev. Lett. 78 1186Google Scholar

    [7]

    Sasaki H, Sakane S, Ishida T, Todorokihara M, Kitamura T, Aoki R 2008 Behav. Brain. Res. 193 152Google Scholar

    [8]

    Yang T 1998 Phys. Lett. A 245 79Google Scholar

    [9]

    Delahaies A, Rousseau D, Fasqueal J B, Chapeau-Blondeau F 2012 J. Opt. Soc. Am. A: 29 1211

    [10]

    Jha R K, Chouhan R 2014 Signal Image Video Process. 8 339Google Scholar

    [11]

    Dylov D V, Fleischer J W 2010 Nat. Photonics 4 323Google Scholar

    [12]

    Patel A, Kosko B 2011 IEEE Trans. Signal Process. 59 488Google Scholar

    [13]

    Itzcovich E, Riani M, Sannita W G 2017 Sci. Rep. 7 12840Google Scholar

    [14]

    Van-der-Groen O, Tang M F, Wenderoth N, Mattingley J B, Jeff B 2018 PLoS Comput. Biol. 14 1

    [15]

    Nnoli U 2019 Optik 195 163111Google Scholar

    [16]

    Kang Y M, Xu J X, Xie Y 2005 Phys. Rev. E 72 021902Google Scholar

    [17]

    Yu Y G, Richard R D, Lee T S 2005 Phys. Rev. Lett. 94 108103Google Scholar

    [18]

    Ashok P, Bart K 2008 IEEE Trans. Neural Networks 19 1993

    [19]

    Purves D 2011 Brains: How They Seem to Work (New Jersey : Financial Times Press Science) pp30–47

    [20]

    Li Z P 2019 Curr. Opin. Neurobiol. 58 1

    [21]

    Fu Y X, Kang Y M, Chen G R 2020 Front. Comput. Neurosci. 14 24Google Scholar

    [22]

    Rolls E L, Loh M, Deco G, Winterer G 2008 Nat. Rev. Neurosci. 9 696Google Scholar

    [23]

    Smith R A 1978 Siggraph Comput. Graph 12 12Google Scholar

    [24]

    Lagnado L 2000 Exp. Physiol. 85 1Google Scholar

    [25]

    Kang Y M, Liu R N, Mao X R 2021 Cognitive Neurodynamics 15 517Google Scholar

    [26]

    Tiwari I, Phogat R, Parmananda P, Ocampo-Espindola J L, Rivera L 2016 Phys. Rev. E 94 022210Google Scholar

    [27]

    Mittal A, Soundararajan R, Bovik A C 2013 IEEE Signal Process. Let. 20 209Google Scholar

    [28]

    Durrant S, Kang Y M, Stocks N, Feng J F 2011 Phys. Rev. E 84 011923Google Scholar

    [29]

    Faisal A A, Selen L P J, Wolpert D P 2008 Nat. Rev. Neurosci. 9 292Google Scholar

    [30]

    Wilke S D, Eurich C 2001 W 10th Computational Neuroscience Meeting Monterey, USA, June, 2001 p1023

    [31]

    Wiesenfeld K, Moss F 1995 Nature 373 33Google Scholar

    [32]

    Levin J E, Miller J P 1996 Nature 380 165Google Scholar

    [33]

    Stacey W C, Durand D M 2000 J. Neurosci. 83 1394

  • 图 1  模型(1)的时间历程图 (a)仅含漏电项的单个神经元膜电位示意图, ${V_{{\text{re}}}}=-0.3$; (b)无噪声时单个神经元的膜电位演化; (c)有噪声时单个神经元的膜电位演化; (d)有噪声的单个神经元的放电序列串; (e)有噪声神经元集群的放电格栅图, 其中实心点代表当前时刻所对应的神经元有动作电位产生. 图(b)至图(e)参数: ${V_{\rm th}} = 0.3$, ${V_{\rm re}} = $$ 0$, ${g_{\rm{l}}} = {g_{\rm{s}}} = 1$, ${C_m} = 1$, ${E_{\rm syn}} = 0$, $\varepsilon = 0.1$, $ \varOmega = 1 $, ${\tau _{{s}}} = 1$, ${\tau _{\rm{d}}} = 0.5$, $N = 50$, $t = 100$; (b) $D = 0$; (c), (e) $D = $$ 0.025$

    Fig. 1.  The evolution diagram of model (1): (a)Single neuron’s potential only with leaky term, ${V_{{\text{re}}}}=-0.3$; (b) single neuron’s membrane potential evolution without noise; (c) single Neuron’s membrane potential evolution with noise; (d) single neuron’s spike train with noise; (e) raster plot of the network where every node denotes a spike at a corresponding time and neuron. Parameters from picture (b) to (e) are set as ${V_{\rm th}} = 0.3$, ${V_{\rm re}} = 0$, ${g_{\rm{l}}} = {g_{\rm{s}}} = 1$, ${C_m} = 1$, ${E_{\rm syn}} = 0$, $\varepsilon = 0.1$, $ \varOmega = 1 $, ${\tau _{{s}}} = 1$, ${\tau _{\rm{d}}} = 0.5$, $N = 50$, $t = 100$; (b)$D = 0$; (c), (e)$D = 0.025$.

    图 2  (a)信噪比随阈值${V_{\rm th}}$, 突触权重$w$变化图; (b)不同阈值信噪比变化情况; (c)不同突触权重信噪比变化情况. 参数${V_{\rm re}} = 0$, ${g_{\rm{l}}} = {g_{\rm{s}}} = 1$, ${C_{\rm{m}}} = 1$, ${E_{\rm syn}} = 0$, $\varepsilon = 0.1$, $ \varOmega = 1 $, ${\tau _{{s}}} = 1$, ${\tau _{\rm{d}}} = 0.5$, $N = 5$, $t = 100$

    Fig. 2.  (a) Signal-to-noise ratio for different threshold Vth and synaptic weight w; (b) signal-to-noise ratio for different threshold Vth; (c) signal-to-noise ratio for different synaptic weight w. Parameters are set as ${V_{\rm re}} = 0$, ${g_{\rm{l}}} = {g_{\rm{s}}} = 1$, ${C_{\rm{m}}} = 1$, ${E_{\rm syn}} = 0$, $\varepsilon = 0.1$, $ \Omega = 1 $, ${\tau _{{s}}} = 1$, ${\tau _{\text{d}}} = 0.5$, $N = 5$, $t = 100$.

    图 3  信噪比随神经元集群尺寸变化图, 参数${V_{\rm th}} = 0.3$, $w = - 0.2$, ${V_{\rm re}} = 0$, ${g_{\rm{l}}} = {g_{\rm{s}}} = 1$, ${C_{\rm{m}}} = 1$, ${E_{\rm syn}} = 0$, $\varepsilon = 0.1$, $ \varOmega = 1 $, ${\tau _{{s}}} = 1$, ${\tau _{\rm{d}}} = 0.5$, $t = 100$

    Fig. 3.  Signal-to-noise ratio for different quantity of neurons with ${V_{\rm th}} = 0.3$, $w = - 0.2$, ${V_{\rm re}} = 0$, ${g_{\rm{l}}} = {g_{\rm{s}}} = 1$, ${C_{\rm{m}}} = 1$, ${E_{\rm syn}} = 0$, $\varepsilon = 0.1$, $ \varOmega = 1 $, ${\tau _{{s}}} = 1$, ${\tau _{\rm{d}}} = 0.5$, $t = 100$.

    图 4  图像增强流程图

    Fig. 4.  The flow chart of dark image enhancement algorithm.

    图 5  编码过程流程图

    Fig. 5.  The flow chart of encoding part.

    图 6  不同神经元个数对最优增强图像质量的影响 (a)神经元个数N=50; (b)神经元个数N=300; (c)峰值信噪比(PSNR)变化曲线, 虚线代表在此噪声强度取得最优图像. 参数${V_{{\text{th}}}} = 0.0667$, $w = - 0.2$, ${V_{{\text{re}}}} = 0$, ${g_{\text{l}}} = {g_{\text{s}}} = 1$, ${C_{\text{m}}} = 1$, ${E_{{\text{syn}}}} = 0$, ${\tau _s} = 1$, ${\tau _{\text{d}}} = 0.5$, $t = 100$

    Fig. 6.  Difference caused by the size of neuron population: (a) N=50; (b) N=300; (c) peak signal-to-noise ratio(PSNR) curve, the dotted line reflects the noise density corresponds to the best enhanced picture. Parameters are set as ${V_{{\text{th}}}} = 0.0667$, $w = - 0.2$, ${V_{{\text{re}}}} = 0$, ${g_{\text{l}}} = {g_{\text{s}}} = 1$, ${C_{\text{m}}} = 1$, ${E_{{\text{syn}}}} = 0$, ${\tau _s} = 1$, ${\tau _{\text{d}}} = 0.5$, $t = 100$.

    图 7  亮度的频数分布直方图 (a) 原始黑暗图像; (b) 0.6分位点最优图像; (c) 0.95分位点最优图像

    Fig. 7.  Frequency histogram of brightness: (a) The origin dark image; (b) best image corresponding to 60 percent quantile; (c) best image corresponding to 95 percent quantile.

    图 8  不同阈值下对应的最优增强图像 (a) 0.6分位点; (b) 0.95分位点; (c) 峰值信噪比变化曲线, 虚线处表示最优噪声强度. 参数$w = - 0.2$, ${V_{{\text{re}}}} = 0$, ${g_{\text{l}}} = {g_{\text{s}}} = 1$, ${C_{\text{m}}} = 1$, ${E_{{\text{syn}}}} = 0$, ${\tau _s} = 1$, ${\tau _{\text{d}}} = 0.5$, $N = 300$, $t = 100$

    Fig. 8.  Best enhanced images with different membrane potential thresholds: (a) 60 percent quantile; (b) 95 percent quantile; (c) peak signal-to-noise ratio(PSNR) curves, the dotted line reflects the noise density corresponds to the best enhanced picture. Parameters are set as $w = - 0.2$, ${V_{{\text{re}}}} = 0$, ${g_{\text{l}}} = {g_{\text{s}}} = 1$, ${C_{\text{m}}} = 1$, ${E_{{\text{syn}}}} = 0$, ${\tau _ s} = 1$, ${\tau _{\text{d}}} = 0.5$, $N = 300$, $t = 100$.

    图 9  图像增强结果 (a) 原始黑暗图像; (b) 原始清晰图像; (c) 本文提出的随机共振方法, $D = 0.0035$, ${V_{{\text{th}}}} = 0.0667$; (d) SSR算法; (e) HE算法; (f) SVD-DSR算法

    Fig. 9.  (a) The origin dark image; (b) the origin bright image; (c) our stochastic-resonance algorithm with $D = 0.0035$and ${V_{{\text{th}}}} = 0.0667$; (d) SSR algorithm; (e) HE algorithm; (f) SVD-DSR algorithm.

    图 10  图像增强结果 (a) 原始黑暗图像; (b) 本文提出的随机共振方法$D = 0.0035$, ${V_{{\text{th}}}} = 0.11$; (c) SSR算法; (d) HE算法; (e) SVD-DSR算法; (f) NIQE变化图

    Fig. 10.  (a) The origin dark image; (b) our stochastic-resonance algorithm with $D = 0.0035$ and ${V_{{\text{th}}}} = 0.11$; (c) SSR algorithm; (d) HE algorithm; (e) SVD-DSR algorithm; (f) NIQE under different noise densities.

    表 1  四种算法的PSNR和NIQE

    Table 1.  PSNR and NIQE of these four algorithms.

    图像质量评价指标本文提出的随机共振算法SSRHESVD-DSR
    PSNR21.58378.008914.653715.9144
    NIQE3.45704.01105.05435.0330
    下载: 导出CSV

    表 2  四种算法的PSNR和NIQE

    Table 2.  PSNR and NIQE of these four algorithms.

    图像质量评价指标本文提出的随机共振算法SSRHESVD-DSR
    NIQE3.68904.37124.65454.9605
    下载: 导出CSV
  • [1]

    Gonzalez C R, Woods R E 2002 Digital Image Processing (2nd Ed.) (New Jersey: Prentice Hall) pp88–108

    [2]

    Kwong R H, Johnston E W 1992 IEEE Trans. Signal Process. 40 1633Google Scholar

    [3]

    Dai Q, Pu Y F, Rahman Z, Aamir Z 2019 Symmetry Basel 11 574Google Scholar

    [4]

    Benzi R, Sutera A, Vulpiani, A 1981 J. Phys. A-Math. Gen. 14 453Google Scholar

    [5]

    Gammaitoni L, Hanggi P, Jung P, Marchesoni F 1998 Rev. Mod. Phys. 70 223Google Scholar

    [6]

    Simonotto E, Riani M, Seife C, Roberts M, Twitty J, Moss F 1997 Phys. Rev. Lett. 78 1186Google Scholar

    [7]

    Sasaki H, Sakane S, Ishida T, Todorokihara M, Kitamura T, Aoki R 2008 Behav. Brain. Res. 193 152Google Scholar

    [8]

    Yang T 1998 Phys. Lett. A 245 79Google Scholar

    [9]

    Delahaies A, Rousseau D, Fasqueal J B, Chapeau-Blondeau F 2012 J. Opt. Soc. Am. A: 29 1211

    [10]

    Jha R K, Chouhan R 2014 Signal Image Video Process. 8 339Google Scholar

    [11]

    Dylov D V, Fleischer J W 2010 Nat. Photonics 4 323Google Scholar

    [12]

    Patel A, Kosko B 2011 IEEE Trans. Signal Process. 59 488Google Scholar

    [13]

    Itzcovich E, Riani M, Sannita W G 2017 Sci. Rep. 7 12840Google Scholar

    [14]

    Van-der-Groen O, Tang M F, Wenderoth N, Mattingley J B, Jeff B 2018 PLoS Comput. Biol. 14 1

    [15]

    Nnoli U 2019 Optik 195 163111Google Scholar

    [16]

    Kang Y M, Xu J X, Xie Y 2005 Phys. Rev. E 72 021902Google Scholar

    [17]

    Yu Y G, Richard R D, Lee T S 2005 Phys. Rev. Lett. 94 108103Google Scholar

    [18]

    Ashok P, Bart K 2008 IEEE Trans. Neural Networks 19 1993

    [19]

    Purves D 2011 Brains: How They Seem to Work (New Jersey : Financial Times Press Science) pp30–47

    [20]

    Li Z P 2019 Curr. Opin. Neurobiol. 58 1

    [21]

    Fu Y X, Kang Y M, Chen G R 2020 Front. Comput. Neurosci. 14 24Google Scholar

    [22]

    Rolls E L, Loh M, Deco G, Winterer G 2008 Nat. Rev. Neurosci. 9 696Google Scholar

    [23]

    Smith R A 1978 Siggraph Comput. Graph 12 12Google Scholar

    [24]

    Lagnado L 2000 Exp. Physiol. 85 1Google Scholar

    [25]

    Kang Y M, Liu R N, Mao X R 2021 Cognitive Neurodynamics 15 517Google Scholar

    [26]

    Tiwari I, Phogat R, Parmananda P, Ocampo-Espindola J L, Rivera L 2016 Phys. Rev. E 94 022210Google Scholar

    [27]

    Mittal A, Soundararajan R, Bovik A C 2013 IEEE Signal Process. Let. 20 209Google Scholar

    [28]

    Durrant S, Kang Y M, Stocks N, Feng J F 2011 Phys. Rev. E 84 011923Google Scholar

    [29]

    Faisal A A, Selen L P J, Wolpert D P 2008 Nat. Rev. Neurosci. 9 292Google Scholar

    [30]

    Wilke S D, Eurich C 2001 W 10th Computational Neuroscience Meeting Monterey, USA, June, 2001 p1023

    [31]

    Wiesenfeld K, Moss F 1995 Nature 373 33Google Scholar

    [32]

    Levin J E, Miller J P 1996 Nature 380 165Google Scholar

    [33]

    Stacey W C, Durand D M 2000 J. Neurosci. 83 1394

  • [1] 王烨花, 何美娟. 高斯色噪声激励下非对称双稳耦合网络系统的随机共振. 物理学报, 2022, 71(19): 190501. doi: 10.7498/aps.71.20220909
    [2] 刘广凯, 全厚德, 康艳梅, 孙慧贤, 崔佩璋, 韩月明. 一种随机共振增强正弦信号的二次多项式接收方法. 物理学报, 2019, 68(21): 210501. doi: 10.7498/aps.68.20190952
    [3] 谢勇, 刘若男. 过阻尼搓板势系统的随机共振. 物理学报, 2017, 66(12): 120501. doi: 10.7498/aps.66.120501
    [4] 李国芳, 孙晓娟. 小世界神经元网络随机共振现象:混合突触和部分时滞的影响. 物理学报, 2017, 66(24): 240501. doi: 10.7498/aps.66.240501
    [5] 刘进军, 冷永刚, 赖志慧, 谭丹. 基于频域信息交换的随机共振研究. 物理学报, 2016, 65(22): 220501. doi: 10.7498/aps.65.220501
    [6] 靳艳飞, 李贝. 色关联的乘性和加性色噪声激励下分段非线性模型的随机共振. 物理学报, 2014, 63(21): 210501. doi: 10.7498/aps.63.210501
    [7] 董小娟, 晏爱君. 双稳态系统中随机共振和相干共振的相关性. 物理学报, 2013, 62(7): 070501. doi: 10.7498/aps.62.070501
    [8] 张静静, 靳艳飞. 非高斯噪声激励下FitzHugh-Nagumo神经元系统的随机共振. 物理学报, 2012, 61(13): 130502. doi: 10.7498/aps.61.130502
    [9] 张路, 钟苏川, 彭皓, 罗懋康. 乘性二次噪声驱动的线性过阻尼振子的随机共振. 物理学报, 2012, 61(13): 130503. doi: 10.7498/aps.61.130503
    [10] 于海涛, 王江, 刘晨, 车艳秋, 邓斌, 魏熙乐. 耦合小世界神经网络的随机共振. 物理学报, 2012, 61(6): 068702. doi: 10.7498/aps.61.068702
    [11] 梁晓冰, 刘希顺, 刘安芝, 王博亮. 弱信号在Hodgkin-Huxley神经元单向耦合系统中的传输特性. 物理学报, 2009, 58(7): 5065-5069. doi: 10.7498/aps.58.5065
    [12] 汪茂胜. 二维映射神经元模型中频率依赖的随机共振. 物理学报, 2009, 58(10): 6833-6837. doi: 10.7498/aps.58.6833
    [13] 林 敏, 黄咏梅, 方利民. 双稳系统随机共振的反馈控制. 物理学报, 2008, 57(4): 2041-2047. doi: 10.7498/aps.57.2041
    [14] 林 敏, 毛谦敏, 郑永军, 李东升. 随机共振控制的频率匹配方法. 物理学报, 2007, 56(9): 5021-5025. doi: 10.7498/aps.56.5021
    [15] 宁丽娟, 徐 伟. 光学双稳系统中的随机共振. 物理学报, 2007, 56(4): 1944-1947. doi: 10.7498/aps.56.1944
    [16] 冷永刚, 王太勇, 郭 焱, 吴振勇. 双稳随机共振参数特性的研究. 物理学报, 2007, 56(1): 30-35. doi: 10.7498/aps.56.30
    [17] 彭建华, 于洪洁. 神经系统中随机和混沌感知信号的联想记忆与分割. 物理学报, 2007, 56(8): 4353-4360. doi: 10.7498/aps.56.4353
    [18] 周小荣, 罗晓曙, 蒋品群, 袁五届. 小世界神经网络的二次超谐波随机共振. 物理学报, 2007, 56(10): 5679-5683. doi: 10.7498/aps.56.5679
    [19] 冷永刚, 王太勇, 郭 焱, 汪文津, 胡世广. 级联双稳系统的随机共振特性. 物理学报, 2005, 54(3): 1118-1125. doi: 10.7498/aps.54.1118
    [20] 邵元智, 钟伟荣, 林光明, 李坚灿. 随机外磁场作用下Ising自旋体系的随机共振. 物理学报, 2004, 53(9): 3157-3164. doi: 10.7498/aps.53.3157
计量
  • 文章访问数:  2886
  • PDF下载量:  104
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-10-25
  • 修回日期:  2021-11-23
  • 上网日期:  2022-01-26
  • 刊出日期:  2022-04-05

/

返回文章
返回