Image Segmentation Method of Spiking Neural Network Based on TTFS Coding

doi:10.3969/j.issn.1000-3428.2015.08.042

Abstract

Abstract: Using the Time-to-first-spike(TTFS) coding strategy,a novel image segmentation method of spiking neural network model is proposed.The image pixel values are encoded into the spike timings of neurons in the input layer.The encoded results are delivered into the middle layer of spiking neural network through the different receptive fields,and spikes are triggered by a threshold condition.The spike timings of the neurons in the output layer are divided into two categories by the segmentation threshold.The corresponding image segmentation experiments show that the parameter changes of receptive filed size,threshold potential and segmentation threshold have significant impacts on the image segmentation result which is evaluated by the maximum Shannon entropy.Compared with the maximum between-cluster variance method and the pulse coupled neural network method based on maximum entropy,the proposed method has stronger robustness for image noise in image segmentation.

Key words: spiking neural network, maximum Shannon entropy, image segmentation, receptive field, coding strategy

摘要： 基于首脉冲触发时间编码策略,提出一种应用脉冲神经网络模型进行图像分割的方法。在输入层采用首脉冲触发时间编码策略将图像的像素值转换为神经元的脉冲发放时间,将编码结果以感受野为单位送入中间层,通过阈值电位控制神经元的脉冲发放,在输出层根据分割阈值将神经元的脉冲发放时间分成2类,输出分割结果,并使用最大Shannon熵准则分析感受野大小、阈值电位和分割阈值等参数的变化对图像分割结果的影响。通过对具有噪声的复杂图像进行分割,并与最大类间方差法和基于最大熵的脉冲耦合神经网络方法进行比较,实验结果表明,该方法对噪声图像的鲁棒性较强,能获得较好的分割结果。

关键词: 脉冲神经网络, 最大Shannon熵, 图像分割, 感受野, 编码策略

CLC Number:

TP391

LIN Xianghong,ZHANG Ning,CUI Wenbo,FENG Lixia. Image Segmentation Method of Spiking Neural Network Based on TTFS Coding[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2015.08.042.

蔺想红,张宁,崔文博,冯丽霞. 基于TTFS编码的脉冲神经网络图像分割方法[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2015.08.042.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.3969/j.issn.1000-3428.2015.08.042

http://www.ecice06.com/EN/Y2015/V41/I8/227

References

参考文献［1］Bohte S M.The Evidence for Neural Information Processing with Precise Spike-times:A Survey［J］.Natural Computing,2004,3(2):195-206. ［2］Quiroga R Q,Panzeri S.Principles of Neural Coding［M］.Boca Raton,USA:CRC Press,2013. ［3］Ghosh-Dastidar S,Adeli H.Spiking Neural Net-works［J］.International Journal of Neural Systems,2009,19(4):295-308. ［4］Jose J T,Amudha J,Sanjay G.A Survey on Spiking Neural Networks in Image Processing［M］//El-Alfy E M,Thampi S M,Takagi H,et al.Advances in Intelligent Informatics.Berlin,Germany:Springer,2015:107-115. ［5］Ella H A,Al-Qaheri H,El-Dahshan E S A.Prostate Boundary Detection in Ultrasound Images Using Biologi-cally-inspired Spiking Neural Network［J］.Applied Soft Computing,2011,11(2):2035-2041. ［6］Meftah B,Lezoray O,Benyettou A.Segmentation and Edge Detection Based on Spiking Neural Network Model［J］.Neural Processing Letters,2010,32(2):131-146. ［7］Wu Qingxiang,McGinnity T M,Maguire L,et al.Colour Image Segmentation Based on a Spiking Neural Network Model Inspired by the Visual System［C］//Proceedings of the 6th International Conference on Intelligent Computing.Berlin,Germany:Springer-Verlag,2010:49-57. ［8］Kerr D,Coleman S,McGinnity M,et al.Biologically Inspired Edge Detection［C］//Proceedings of the 11th International Conference on Intelligent Systems Design and Applications.Washington D.C.,USA:IEEE Press,2011:802-807. ［9］Chaturvedi S,Khurshid A A,Dorle S S.Reconfiguration of Spiking Neural Network for Optimization with Applications to Image Processing［C］//Proceedings of the 6th International Conference on Emerging Trends in Engineering and Technology.Washington D.C.,USA:IEEE Press,2013:191-192. ［10］Wang Xiaowei,Wu Qingxiang,Zhang Zhenming,et al.Segmentation Based on Spiking Neural Network Using Color Edge Gradient for Extraction of Corridor Floor［C］//Proceedings of the 3rd International Con-ference on Multimedia Technology.Berlin,Germany:Springer-Verlag,2014:275-285. ［11］Wang Zhaobin,Ma Yide,Cheng Feiyan,et al.Review of Pulse-coupled Neural Networks［J］.Image and Vision Computing,2010,28(1):5-13. ［12］Monica S M,Sahoo S K.Pulse Coupled Neural Networks and Its Applications［J］.Expert Systems with Applications,2014,41(8):3965-3974. ［13］Izhikevich E M.Dynamical Systems in Neuroscience:The Geometry of Excitability and Bursting［M］.Cambridge,USA:MIT Press,2007. ［14］蔡荣太,吴庆祥.基于脉冲神经网络的红外目标提取［J］.计算机应用,2010,30(12):3327-3330. ［15］蔺想红,张田文.指数突触电导IF神经元模型及事件驱动模拟策略［J］.电子学报,2008,36(8):1495-1501. ［16］Thorpe S,Fize D,Marlot C.Speed of Processing in the Human Visual System［J］.Nature,1996,381(6582):520-522. ［17］Kammara A C,Koenig A.Contributions to Integrated Adaptive Spike Coded Sensor Signal Conditioning and Digital Conversion in Neural Architecture［C］//Pro-ceedings of the 17th ITG/GMA Symposium Sensors and Measuring Systems.Nuremberg,Germany:VDE Press,2014:1-6. ［18］Len～ero-Bardallo J A,Serrano-Gotarredona T,Linares-Barranco B.A Five-decade Dynamic-range Ambient-light-independent Calibrated Signed-spatial-contrast AER Retina with 0.1-ms Latency and Optional Time-to-first-spike Mode［J］.IEEE Transactions on Circuits and Systems,2010,57(10):2632-2643. ［19］崔文博,蔺想红,徐满意.脉冲神经网络图像分割的编码方法［J］.计算机工程,2012,38(24):196-199. ［20］Vala M H J,Baxi A.A Review on Otsu Image Segmentation Algorithm［J］.International Journal of Advanced Research in Computer Engineering & Technology,2013,2(2):387-389. ［21］Zhan Yunjun,Yuan Yanbin,Huang Jiejun,et al.RS Image PCNN Automatical Segmentation Based on Information Entropy［C］//Proceedings of the 2nd Inter-national Conference on Multimedia and Information Technology.Washington D.C.,USA:IEEE Press,2010:200-203. 编辑刘冰

[1]	CAO Shuxin, FENG Tengteng, GE Fengpei, LIANG Chunyan. Speaker Recognition Based on Scale Correlation-Bidirectional Long Short-Term Memory Network Model [J]. Computer Engineering, 2023, 49(4): 289-296.
[2]	XU Chaoyue, YU Ying, HE Penghao, LI Miao, MA Yuhui. Multi-Scale Low-Light Image Enhancement Network Based on U-Net [J]. Computer Engineering, 2022, 48(8): 215-223.
[3]	QIAO Caicai, WU Chengmao, LI Changxing, WANG Jiaye. Robust Fuzzy Clustering Algorithm Integrating Membership Degree and Pixel Alternating Guided Filtering [J]. Computer Engineering, 2022, 48(8): 224-233.
[4]	LIN Zhijie, ZHENG Qiulan, LIANG Yong, XING Wei. Medical Image Segmentation Model Based on Involution U-Net [J]. Computer Engineering, 2022, 48(8): 180-186.
[5]	ZHANG Jiajun, TANG Yunqi, YANG Zhixiong. Shoe Type Recognition Algorithm with Adaptive Receptive Field and Multi-Branch Feature [J]. Computer Engineering, 2022, 48(6): 295-303.
[6]	LIU Jiahang, YU Gongjian, LI Peiqi, HUA Xia, CHAI Zhilei, CHEN Wenjie. Performance Optimization of NEST Simulator Based on SNN Neuron Relocation [J]. Computer Engineering, 2022, 48(3): 189-196.
[7]	HUANG Sheng, RAN Haoshan. Refined Edge Detection Method Based on Semantic Information [J]. Computer Engineering, 2022, 48(3): 204-210.
[8]	WANG Wenxin, HE Yuhang, CHEN Gang. UCaps Network Based on EM-Routing Algorithm for Medical Image Segmentation [J]. Computer Engineering, 2022, 48(2): 268-274.
[9]	ZHANG Xiangfen, LIU Yan, YUAN Feiniu. 3D Medical Image Segmentation Based on Inverted Pyramid Deep Learning Network [J]. Computer Engineering, 2022, 48(12): 304-311.
[10]	CHEN Suyang, SONG Xiaoning. Multi-supervision Face Liveness Detection Algorithm Fused with Multi-scale Feature [J]. Computer Engineering, 2022, 48(12): 79-85,94.
[11]	SHANG Jiatong, LEI Tao, ZHANG Dong, DU Xiaogang, ZHAI Yujie. Lightweight Deformable Encoder-Decoder Network for Etched Image Segmentation [J]. Computer Engineering, 2022, 48(12): 203-211,217.
[12]	CAO Jiawang, TIAN Weiwei, LIU Xueling, LI Yuxin, FENG Rui. Segmentation of Brain Substantia Nigra Pars Compacta Based on Improved U-Net [J]. Computer Engineering, 2022, 48(11): 14-21,29.
[13]	LI Qi, XIE Jun, ZHANG Zhe, DONG Junjie, XU Xinying. Research on Online Sequence Extreme Learning Machine Based on Multi-Modal [J]. Computer Engineering, 2021, 47(7): 67-73,80.
[14]	HU Gaozhen, XU Shengjun, MENG Yuebo, LIU Guanghui, FENG Feng, DUAN Zhongxing. Image Segmentation Method Based on MRF with Edge Constrained Local Region [J]. Computer Engineering, 2021, 47(6): 253-261,270.
[15]	YANG Bing, LIU Xiaofang, ZHANG Jiu. Medical Image Segmentation Based on Deep Feature Aggregation Network [J]. Computer Engineering, 2021, 47(4): 187-196.

Please choose a citation manager

Content to export