摘要
传统模式识别方法在物体、人脸、指纹、军事目标识别等领域中只利用单一的图像信息。当研究对象的图像特征高度相似时,识别率较低,如对于真假目标的识别,仅仅利用物体的图像信息很难得到满意的识别结果。针对上述问题,提出了一种综合利用图像和光谱信息的物体真假模式识别方法。该方法采用卷积神经网络模型,通过迁移学习的方式构建图像识别模型,并依据物体图像的语义特征进行物体类别识别,在此基础上,基于逆传播(back propagation,BP)神经网络模型,结合物体的实测光谱数据进行物体真假识别。为了验证该方法的准确性和有效性,利用真假苹果和葡萄作为测试对象,单独利用图像信息和光谱信息进行识别时,识别率分别为38.50%和63.00%,而利用该综合方法得到的识别率为95.00%。可认为该方法提高了真假目标混杂情况下的识别准确度,可为物体识别、人脸识别、指纹识别、军事目标识别等领域的应用提供重要的参考,也为航天侦查载荷设计提供了新的思路。
At present, pattern recognition technology has been widely used in the fields of objects, faces,fingerprints, military target recognition, etc. However,pattern recognition method still has obvious shortcomings when applied to the above fields. It is currently restricted to the use of image information for identification. When the image features of the research object are highly similar, the accuracy of pattern recognition is low and cannot meet the actual application requirements. For example, in the case of mixed true and false targets, it is difficult to obtain satisfactory recognition results using only image information. Aiming at the above problems, a pattern recognition method integrating image information and spectral information is proposed in this paper. Firstly, the image recognition model based on the convolutional neural network model is built to identify object categories based on the semantic features of objects and obtain preliminary recognition results. Then, on the basis of the preliminary recognition results, the measured spectral data of the object(spectrum range 400-1 000 nm, spectral resolution 2 nm) is used to perform true and fake identification of the object based on the back propagation(BP) neural network model. The principle of true and false recognition is that the true and false targets are different in material, causing significant difference in their hyperspectral information. Finally, recognition results are obtained. In order to verify the accuracy of the proposed method, true and fake apples and grapes are used as experimental subjects and the result is that: The recognition accuracy obtained by using only image information is 38.50%, and the recognition accuracy obtained by using only spectral information is 63.00%, however, the recognition accuracy obtained by the method proposed in this paper is 95.00%. Compared with the existing pattern recognition method without spectral information participation, the pattern recognition method using image information and spectral information proposed in this paper improves the pattern recognition accuracy under the mixed condition of true and false targets, and can be widely applied to object recognition, face recognition, fingerprint recognition, military target recognition and other fields.
引文
[1] Zhang P,Bui T D,Suen C Y. Recognition of Similar Objects Using 2-D Wavelet-Fractal Feature Extraction[C]. IEEE Object Recognition Supported by User Interaction for Service Robots,Quebec City,Canada,2002
[2] Wu Liting,Zhang Yu,Yang Yiping,et al. ThreeDimensional Free-Form Object Recognition Based on Contour Curve and Local Surface Patches in Range Images[J]. Journal of Image and Graphics,2012,17(2):269-278(吴莉婷,张宇,杨一平,等.深度图像中基于轮廓曲线和局部区域特征的3维物体识别[J].中国图象图形学报,2012,17(2):269-278)
[3] Ramadhani A L,Musa P,Wibowo E P. Human Face Recognition Application Using PCA and Eigenface Approach[C]. IEEE International Conference on Informatics and Computing,Jayapura,Indonesia,2017
[4] Hegde N,Preetha S,Bhagwat S. Facial Expression Classifier Using Better Technique:Fisher Face Algorithm[C]. IEEE International Conference on Advances in Computing,Communications and Informatics,Bangalore,India,2018
[5] Wang Y N,Su J B. Symmetry Description and Face Recognition Using Face Symmetry Based on Local Binary Pattern Feature[C]. IEEE 32nd Chinese Control Conference(CCC),Xi’an,China,2013
[6] Ahmad F,Mohamad D. A Review on Fingerprint Classification Techniques[C]. IEEE International Conference on Computer Technology and Development,Kota Kinabalu,Malaysia,2009
[7] Romero A,Ballas N,Kahou S E,et al. ImageNet Classification with Deep Convolutional Neural Networks[C]. International Conference on Learning Representations,San Diego,CA,USA,2015
[8] Simonyan K,Zisserman A. Very Deep Convolutional Networks for Large-scale Image Recognition[OL].https://arxiv. org/abs/1409. 1556, arXiv preprint arXiv:1409. 1556,2014
[9] Szegedy C,Liu W,Jia Y,et al. Going Deeper with Convolutions[C]. The IEEE Conference on Computer Vision and Pattern Recognition,Boston,MA,2015
[10] He K,Zhang X,Ren S,et al. Deep Residual Learning for Image Recognition[C]. The IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas,Nevada,USA,2016
[11] Wang Y,Wu Z,Zhang J. Damaged Fingerprint Classification by Deep Learning with Fuzzy Feature Points[C]. IEEE International Congress on Image and Signal Processing,BioMedical Engineering and Informatics,Datong,China,2016
[12] Setiowati S,Franita E L,Ardiyanto I. A Review of Optimization Method in Face Recognition:Comparison Deep Learning and Non-deep Learning Methods[C]. IEEE 9th International Conference on Information Technology and Electrical Engineering,Phuket,Thailand,2017
[13] Arsenovic M,Sladojevic S,Anderla A,et al. FaceTime—Deep Learning Based Face Recognition Attendance System[C]. IEEE 15th International Symposium on Intelligent Systems and Informatics,Subotica,Serbia,2017
[14] Tong Q,Xue Y,Zhang L. Progress in Hyperspectral Remote Sensing Science and Technology in China over the Past Three Decades[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(1):70-91
[15] Tong Qingxi, Zhang Bing,Zhang Lifu. Current Progress of Hyperspectral Remote Sensing in China[J]Journal of Remote Sensing,2016,20(5):689-707(童庆禧,张兵,张立福.中国高光谱遥感的前沿进展[J].遥感学报,2016,20(5):689-707)
[16] Bidhendi S K,Shirazi A S,Fotoohi N,et al. Material Classification of Hyperspectral Images Using Unsupervised Fuzzy Clustering Methods[C]. The 3rd International IEEE Conference on Signal-Image Technologies and Internet-Based System, Shanghai,China,2007
[17] Kishore M,Kulkarni S B. Approches and Challenges in Classification for Hyperspectral Data:A Review[C]. IEEE International Conference on Electrical,Chennai,India,2016
[18] Liu X,Sun Q,Liu B,et al. Hyperspectral Image Classification Based on Convolutional Neural Network and Dimension Reduction[C]. Chinese Automation Congress,Jinan,China,2018
[19] Zhang L,You J. A Spectral Clustering Based Method for Hyperspectral Urban Image[C]. IEEE Urban Remote Sensing Event,Dubai,United Arab Emirates,2017
[20] Dong Yanni,Du Bo,Zhang Lefei,et al. Hyperspectral Target Detection Based on Locally Adaptive Information-Theoretic Metric Learning Method[J].Geomatics and Information Science of Wuhan University,2018,43(8):1 271-1 277(董燕妮,杜博,张乐飞,等.基于局域自适应信息理论测度学习的高光谱目标探测方法[J].武汉大学学报·信息科学版,2018,43(8):1 271-1 277)
[21] Pan S J,Yang Q. A Survey on Transfer Learning[J]. IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1 345-1 359