交叉点的神经网络识别及联机手写字符的概率神经网络识别初探
|
摘要
人工神经网络发展到今天，已有五十多年的历史。在一代又一代学者的不懈努力下，不但理论基础逐渐充实、成熟，而且在信号处理、计算机视觉、模式识别、专家系统、工业控制与气象预测等许多领域有了广泛的应用。神经网络模式识别方法是近几年兴起的模式识别领域的一个新的研究方向。神经网络模式识别系统的研究，无论对神经网络理论的发展，还是对模式识别技术的实际应用，都有特别重要的意义。
BP网络是当前应用最广泛的一种人工神经网络。已被人们广泛的应用于神经网络模式识别(特别是图像及字符的识别)问题。
Kohonen提出的自组织特征映射(Self-Organizing Feature Map)神经网络(SOFM)因具有较强的拓扑组织能力和抗干扰能力，也广泛于应用于神经网络模式识别领域。
在1960年末被提出的HMM模型，已经被应用的连续的和演讲者无关的自动演讲识别中。近几年它也开始被广泛的应用于字符识别的工作中。
本文的工作主要是以下两个方面，都是侧重于有关神经网络的实际应用方面。
1．交叉点的神经网络识别。提出了一种识别灰度图像中交叉点的神经网络方法。用自组织特征映射网络和BP网络组成多分类器，识别图像中的二交叉点、三交叉点和四交叉点。在加入8％的干扰时，仍能达到85％左右的识别率。
2．概率神经网络用于联机手写字符的识别。由于计算机技术的高速发展，人们可以快速处理大量的数据，但数据的输入速度远远低于数据处理的速度，这大大妨碍了人们对计算机的使用。而且用键盘作为输入会打断正在进行的思维。所以研究一种方便的手写输入方法是很有必要的。到现在，单字符手写体识别，尤其是数字识别率接近95％，但对于连续的字符书写，尤其是有数学符号的情况下，由于联机手写的随意性比较大，写作不规范，还没有一个成熟的产品。本文应用HMM概率模型和神经网络结合，对联机手写数字和数学符号进行识别。对概率神经网络模型应用于联机手写识别进行了有益的探索。
与其他学者的一些工作相比，本文侧重于对使用概率神经网络的方法对联机手写进行识别，既利用了神经网络优异的分类性能，又避免了一般的神经网络实时性差的弱点。由于特征提取技术的局限性及算法的不成熟，本文的工作距离实际应用阶段还有很长的一段，有待进一步的改进完成。但是我们的试验结果表明，概率神经网络可以成功的用于联机手写字符的识别问题。
The neural network has a history of over fifty years now. Generations of researchers have been making great efforts to build up its theoretical foundation and to apply it in many areas such as signal processing, machine vision, pattern recognition, expert system, industry control and weather forecast. In recent years, the pattern recognition based on neural networks has become a new active field. The study of the neural networks-based pattern recognition system is very important, not only to the development of neural networks theories, but also to the application of the pattern recognition techniques.
The multi-layer feedforward back-propagation neural network has found a widely expanding range of applications. It has been used extensively for image and character recognition.
The SOFM proposed by Kohonen is also used in the area of pattern recognition for its strong organizing ability on topology and its robustness.
Since HMM was introduced at the end of 1960, it has been applied to the connected, speaker-independent, automatic speech recognition with the advantage of modeling various patterns. Recently it has also been widely adapted to character recognition.
The work we have done is mainly focused on the following two problems.
The first one is junction recognition using neural networks. Combining SOFM network and BP network we construct a multi-classifier to recognize junctions in images. When noises up to 8% are added, the system can still achieve a high recognition ratio of around 85%.
Secondly, we use the HMM neural network to recognize on-line handwritten character. With the developing of computer technique, people can process data quickly. But the speed of typing data into computer is lower than the speed of processing data. It's precluding people from using the computer. Furthermore, input with the keyboard would break thinking. So it's necessary to find a convenient way of inputting. By this time, the rate of single handwritten character recognition, especially figure recognition, has reached 95%. But to the sequential characters, or mathematic character recognition there is not a perfect product. We recognize on-line handwritten figure and some mathematic characters using the HMM neural networks, and achieve a better result.
Compared with other people's work, we focus on recognizing characters with combination of HMM and neural networks. It makes use of the good performance of neural networks, and avoid the limitation that neural networks are not good at performing the real-time work. Due to the limitation of the characteristic selected and the algorithms used, the model we proposed still needs further improvement for practical application. But the results have shown that the HMM neural network can work successfully on the recognition of handwritten characters.
BP网络是当前应用最广泛的一种人工神经网络。已被人们广泛的应用于神经网络模式识别(特别是图像及字符的识别)问题。
Kohonen提出的自组织特征映射(Self-Organizing Feature Map)神经网络(SOFM)因具有较强的拓扑组织能力和抗干扰能力，也广泛于应用于神经网络模式识别领域。
在1960年末被提出的HMM模型，已经被应用的连续的和演讲者无关的自动演讲识别中。近几年它也开始被广泛的应用于字符识别的工作中。
本文的工作主要是以下两个方面，都是侧重于有关神经网络的实际应用方面。
1．交叉点的神经网络识别。提出了一种识别灰度图像中交叉点的神经网络方法。用自组织特征映射网络和BP网络组成多分类器，识别图像中的二交叉点、三交叉点和四交叉点。在加入8％的干扰时，仍能达到85％左右的识别率。
2．概率神经网络用于联机手写字符的识别。由于计算机技术的高速发展，人们可以快速处理大量的数据，但数据的输入速度远远低于数据处理的速度，这大大妨碍了人们对计算机的使用。而且用键盘作为输入会打断正在进行的思维。所以研究一种方便的手写输入方法是很有必要的。到现在，单字符手写体识别，尤其是数字识别率接近95％，但对于连续的字符书写，尤其是有数学符号的情况下，由于联机手写的随意性比较大，写作不规范，还没有一个成熟的产品。本文应用HMM概率模型和神经网络结合，对联机手写数字和数学符号进行识别。对概率神经网络模型应用于联机手写识别进行了有益的探索。
与其他学者的一些工作相比，本文侧重于对使用概率神经网络的方法对联机手写进行识别，既利用了神经网络优异的分类性能，又避免了一般的神经网络实时性差的弱点。由于特征提取技术的局限性及算法的不成熟，本文的工作距离实际应用阶段还有很长的一段，有待进一步的改进完成。但是我们的试验结果表明，概率神经网络可以成功的用于联机手写字符的识别问题。
The neural network has a history of over fifty years now. Generations of researchers have been making great efforts to build up its theoretical foundation and to apply it in many areas such as signal processing, machine vision, pattern recognition, expert system, industry control and weather forecast. In recent years, the pattern recognition based on neural networks has become a new active field. The study of the neural networks-based pattern recognition system is very important, not only to the development of neural networks theories, but also to the application of the pattern recognition techniques.
The multi-layer feedforward back-propagation neural network has found a widely expanding range of applications. It has been used extensively for image and character recognition.
The SOFM proposed by Kohonen is also used in the area of pattern recognition for its strong organizing ability on topology and its robustness.
Since HMM was introduced at the end of 1960, it has been applied to the connected, speaker-independent, automatic speech recognition with the advantage of modeling various patterns. Recently it has also been widely adapted to character recognition.
The work we have done is mainly focused on the following two problems.
The first one is junction recognition using neural networks. Combining SOFM network and BP network we construct a multi-classifier to recognize junctions in images. When noises up to 8% are added, the system can still achieve a high recognition ratio of around 85%.
Secondly, we use the HMM neural network to recognize on-line handwritten character. With the developing of computer technique, people can process data quickly. But the speed of typing data into computer is lower than the speed of processing data. It's precluding people from using the computer. Furthermore, input with the keyboard would break thinking. So it's necessary to find a convenient way of inputting. By this time, the rate of single handwritten character recognition, especially figure recognition, has reached 95%. But to the sequential characters, or mathematic character recognition there is not a perfect product. We recognize on-line handwritten figure and some mathematic characters using the HMM neural networks, and achieve a better result.
Compared with other people's work, we focus on recognizing characters with combination of HMM and neural networks. It makes use of the good performance of neural networks, and avoid the limitation that neural networks are not good at performing the real-time work. Due to the limitation of the characteristic selected and the algorithms used, the model we proposed still needs further improvement for practical application. But the results have shown that the HMM neural network can work successfully on the recognition of handwritten characters.
引文
[1] Aleksander I. and Morton H., An Introdution to Neural Computing, Chapman & Hall, London, 1990
[2] Darwiche, E, Pandya, A. S., and Mandalia, A.D., Automated optical recognition of degraded handwritten characters, SPIE, vol.1661, pp. 203-214, 1992.
[3] K. R. Castleman, Digital Image Processing, Prentice Hall, 1996.
[4] Baykal, N. and Yalabik, N., Object orientation detection and character recognition using optimal feed-forward network and Kohonen' s feature map, SPIE, 1992. vol. 1709, pp. 292-303.
[5] Andreas Kosmala, Joerg Rottland, Gerhard Rigoll. Improved On-Line Handwriting Recognition Using Context Dependent Hidden Markov Models. Document Analysis and Recognition, 1997. Proceedings of the Fourth International Conference on. vol. 2 P. 641-644.
[6] Andreas Kosmala, Joerg Rottland, Gerhard Rigoll. An Investigation of the use of trigraphs for large vocabulary cursive handwriting recognition. Acoustics, Speech, And Signal Processing, 1997. ICASSP-97. vol. 4 pp. 3373-3376.
[7] Anja Brakensiek Andreas Kosmala Gerhard Rigoll. Writer Adaptation for Online Handwriting Recognition. 23rd Symposium of the German Association for Pattern Recognition (DAGM 2001),Munich, Germany, September 12-14, 2001. p. 32-37.
[8] Rabiner, L.R., Turorial on hidden Markov model and selected application in speech recognition. In: Proc. IEEE, Vol.77, No. 2, pp. 257-285.
[9] K.C. Jung, S.M. Yoon, H.J. Kim. Continuous HMM applied to quantization of on-line Korean character spaces. Pattern Recognition Letters 21(2000). pp. 303-310.
[10] Kim, H.J., Kim, S.K., et al., An HMM-based character recognition network using level building. Pattern Recognition 30(3), pp. 491-502.
[11] Cho, S.B., Kim, J.H., Integrating hidden Markov model and neural network classifier for on-line handwritten character recognition(in Korean). Journal of Korea Information Science Society20(3), pp328-337.
[12] H.-J. Winkler, H. Fahrner, M. Lang. A soft-decision approach for structural analysis of handwritten mathematical expressions, ICASSP 95, Detroit, pp. 2459-2462.
[13] M. Koschinski, H.-J. Winkler, M. Lang Segmentation and recognition of symbols within handwritten mathematical expressions. ICASSP 95, Detroit, pp. 2439—2442.
[14] H.-J. Winkler. HMM-based handwritten symbol recognition using on-line and off-line features. ICASSP96, Atanta, pp. 3438-3441.
[15] H.J. Winkler, Manfred Lang, On-line symbol segmentation and recognition in handwritten mathematical expressions, ICASSP 97, pp. 3377-3380.
[16] Zi-Xiong Wang, Claudie Faure. Structural analysis of handwritten mathematical expressions. Pattern Recognition, 1988 vol. 1 pp. 32-34.
[17] Kunihiko Fukushima, Taro Imagawa. Recognition and segmentation of connected characters with selective attention. Neural Networks. Vol. 6, pp 33-41,1993.
[18] Kunikiko Fukushima. Neocognitron of a new version:Handwritten digit recognition.
Artificial neural networks - ICANN 2001. pp. 987-992.
[19] K. Fukushima. Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Networks, 1[2], pp. 119-130(1998).
[20] K. Fukushima, M. Tanigawa. Use of different thresholds in learning and recognition. Neurocomputing, 11[1], pp. 1-17(1996).
[21] Kunihiko Fukushima, Nobuaki Wake. Handwritten alphanumeric character recognition by the neocognitron. IEEE Trans. On Neural Networks, Vol. 2, No. 3(1991),pp. 355-365.
[22] Stefan Manke, U. Bodenhausen. A Connectionist Recognizer for Cursive Handwriting Recognition. Proceedings of the ICASSP-94, Adelaide, April 1994.
[23] M. Dehghan, K. Faez, M. Ahmadi, g. Shridhar. Handwritten Farsi(Arabic) word recognition: a holistic approach using discrete HMM. Pattern Recognition 34(2001) 1057-1065.
[24] Yannis A. Dimitriadis, Juan Lopez Coronado. Towards an ART-based mathematical editor, that uses on-line handwritten symbol recognition. Pattern Recognition, Vol. 28, No. 6, pp. 807-822,1995.
[25] G.A. Carpenter, S. Grossberg, J.H. Reynolds,. ARTMAP: Supervised real-time learning and classigication of nonstationary data by a self-organizing neural network. Neural Networks4,565-588(1991).
[26] N. Arica, F.T. Yarman-Vural. One-dimensional representation of two-dimensional information for HMM based handwriting recognition. Pattern Recognition Letters 21(2000) pp. 583-592.
[27] Kam-Fai Chan, Dit-Yan Yeung. Error detection, error correction and performance evaluation in on-line mathematical expression recognition. Pattern Recgnition 34(2001) pp. 1671-1684.
[28] K.F. Chan, D.Y. Yeung. An efficient syntactic approach to structural analysis of on-line handwritten mathematical expressions. Pattern Recognition 33(3)(2000), pp. 375-384.
[29] K.F. Chan, D.Y. Yeung. Recognizing on-line handwritten alphanumeric characters through flexible structural matching. Pattern Recognition 32(7) (1999), pp. 1099-1114.
[30] X. Li, N.S. Hall. Corner detection and shape classification of on-line handprinted kanji strokes. Pattern Recognition, vol. 26, No. 9, pp. 1315-1334,1993.
[31] D. de Brucq, M. Amara, V. Ruiz. On-line handwritten segmentation in linear drawings. Pattern Recognition Letters 18(1997), pp. 193-202.
[32] XIAOLIN LI, DIT-YAN YEUNG. On-Line handwritten alphanumeric character recognition using dominant points in strokes. Pattern Recognition, Vol. 30, No. 1, pp. 31-44, (1997).
[33] Sang Kyoon Kim, Se Myung Park. On-line recognition of Korean characters using ART neural network and hidden Markov model. Journal of Systems Architecture 44(1998), pp. 971-984.
[34] Kam-Fai Chan, Dit-Yan Yeung. Mathematical Expression Recognition: A Survey
[35] K.C. Jung, H.J. Kim. Korean character recognition using a TDNN and an HMM. Pattern Recognition Letters, 20(1999), pp. 551-563.
[36] Y. Le Cun, I. Guyon. Handwritten Digit Recognition: Applications of Neural Network Chips and Automatic Learning. IEEE. Communications Magazine, November 1989, pp. 41-46.
[37] Park, H.S., Lee, S.W., Off-line recognition of large-set handwritten characters with multiple hidden Markov models. Pattern Recognition 29(2), pp. 231-244.
[38] Sean R. Eddy. Profile Hidden Markov Models; review. Bioihformatics, Vol. 14, No. 9,1998, pp. 755-763.
[39] G. Bradski, G.A. Capenter, S. Grossberg. Working memories for storage and recall of arbitrary temporal sequences. Int. Joint. Conf. Neural Networks, Ⅱ, Baltimore Maryland, pp. 57-62.
[40] 黄襄念，程萍，赵学军．自由手写拉丁字母联机识别．计算机应用2000，pp．40-42
[41] 赵学军，余楚中，乔进．联机方法与脱机方法相结合识别自有手写数字．重庆大学学报(自然科学版)，Vol．21，No．5(1998)，pp．70-74．
[42] 赵学军，余楚中，潘保昌．联机数字符号的基元识别方法．重庆大学学报，1998(2)．pp．327-334．
[43] 朱小燕，史一凡，马少平．手写体字符识别研究．模式识别与人工智能．Vol．13 No．2(2000)，pp．174-180．
[44] 徐秉铮，张百灵，韦岗．《神经网络理论与应用》．华南理工大学出版社1994年
[45] 黄德双 《神经网络模式识别系统理论》．第一版．电子工业出版社1996年
[46] Abhijit S. Pandya, Robert B. Macy(著)，徐勇 荆涛(译)．《神经网络模式识别及其实现》．电子工业出版社
[47] 夏良正(主编)．《数字图像处理》第一版．东南大学出版社1996年
[48] 郭力宾，吴微．二维图像中交叉点的神经网络识别(已经接收) 大连理工大学学报2003年
[2] Darwiche, E, Pandya, A. S., and Mandalia, A.D., Automated optical recognition of degraded handwritten characters, SPIE, vol.1661, pp. 203-214, 1992.
[3] K. R. Castleman, Digital Image Processing, Prentice Hall, 1996.
[4] Baykal, N. and Yalabik, N., Object orientation detection and character recognition using optimal feed-forward network and Kohonen' s feature map, SPIE, 1992. vol. 1709, pp. 292-303.
[5] Andreas Kosmala, Joerg Rottland, Gerhard Rigoll. Improved On-Line Handwriting Recognition Using Context Dependent Hidden Markov Models. Document Analysis and Recognition, 1997. Proceedings of the Fourth International Conference on. vol. 2 P. 641-644.
[6] Andreas Kosmala, Joerg Rottland, Gerhard Rigoll. An Investigation of the use of trigraphs for large vocabulary cursive handwriting recognition. Acoustics, Speech, And Signal Processing, 1997. ICASSP-97. vol. 4 pp. 3373-3376.
[7] Anja Brakensiek Andreas Kosmala Gerhard Rigoll. Writer Adaptation for Online Handwriting Recognition. 23rd Symposium of the German Association for Pattern Recognition (DAGM 2001),Munich, Germany, September 12-14, 2001. p. 32-37.
[8] Rabiner, L.R., Turorial on hidden Markov model and selected application in speech recognition. In: Proc. IEEE, Vol.77, No. 2, pp. 257-285.
[9] K.C. Jung, S.M. Yoon, H.J. Kim. Continuous HMM applied to quantization of on-line Korean character spaces. Pattern Recognition Letters 21(2000). pp. 303-310.
[10] Kim, H.J., Kim, S.K., et al., An HMM-based character recognition network using level building. Pattern Recognition 30(3), pp. 491-502.
[11] Cho, S.B., Kim, J.H., Integrating hidden Markov model and neural network classifier for on-line handwritten character recognition(in Korean). Journal of Korea Information Science Society20(3), pp328-337.
[12] H.-J. Winkler, H. Fahrner, M. Lang. A soft-decision approach for structural analysis of handwritten mathematical expressions, ICASSP 95, Detroit, pp. 2459-2462.
[13] M. Koschinski, H.-J. Winkler, M. Lang Segmentation and recognition of symbols within handwritten mathematical expressions. ICASSP 95, Detroit, pp. 2439—2442.
[14] H.-J. Winkler. HMM-based handwritten symbol recognition using on-line and off-line features. ICASSP96, Atanta, pp. 3438-3441.
[15] H.J. Winkler, Manfred Lang, On-line symbol segmentation and recognition in handwritten mathematical expressions, ICASSP 97, pp. 3377-3380.
[16] Zi-Xiong Wang, Claudie Faure. Structural analysis of handwritten mathematical expressions. Pattern Recognition, 1988 vol. 1 pp. 32-34.
[17] Kunihiko Fukushima, Taro Imagawa. Recognition and segmentation of connected characters with selective attention. Neural Networks. Vol. 6, pp 33-41,1993.
[18] Kunikiko Fukushima. Neocognitron of a new version:Handwritten digit recognition.
Artificial neural networks - ICANN 2001. pp. 987-992.
[19] K. Fukushima. Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Networks, 1[2], pp. 119-130(1998).
[20] K. Fukushima, M. Tanigawa. Use of different thresholds in learning and recognition. Neurocomputing, 11[1], pp. 1-17(1996).
[21] Kunihiko Fukushima, Nobuaki Wake. Handwritten alphanumeric character recognition by the neocognitron. IEEE Trans. On Neural Networks, Vol. 2, No. 3(1991),pp. 355-365.
[22] Stefan Manke, U. Bodenhausen. A Connectionist Recognizer for Cursive Handwriting Recognition. Proceedings of the ICASSP-94, Adelaide, April 1994.
[23] M. Dehghan, K. Faez, M. Ahmadi, g. Shridhar. Handwritten Farsi(Arabic) word recognition: a holistic approach using discrete HMM. Pattern Recognition 34(2001) 1057-1065.
[24] Yannis A. Dimitriadis, Juan Lopez Coronado. Towards an ART-based mathematical editor, that uses on-line handwritten symbol recognition. Pattern Recognition, Vol. 28, No. 6, pp. 807-822,1995.
[25] G.A. Carpenter, S. Grossberg, J.H. Reynolds,. ARTMAP: Supervised real-time learning and classigication of nonstationary data by a self-organizing neural network. Neural Networks4,565-588(1991).
[26] N. Arica, F.T. Yarman-Vural. One-dimensional representation of two-dimensional information for HMM based handwriting recognition. Pattern Recognition Letters 21(2000) pp. 583-592.
[27] Kam-Fai Chan, Dit-Yan Yeung. Error detection, error correction and performance evaluation in on-line mathematical expression recognition. Pattern Recgnition 34(2001) pp. 1671-1684.
[28] K.F. Chan, D.Y. Yeung. An efficient syntactic approach to structural analysis of on-line handwritten mathematical expressions. Pattern Recognition 33(3)(2000), pp. 375-384.
[29] K.F. Chan, D.Y. Yeung. Recognizing on-line handwritten alphanumeric characters through flexible structural matching. Pattern Recognition 32(7) (1999), pp. 1099-1114.
[30] X. Li, N.S. Hall. Corner detection and shape classification of on-line handprinted kanji strokes. Pattern Recognition, vol. 26, No. 9, pp. 1315-1334,1993.
[31] D. de Brucq, M. Amara, V. Ruiz. On-line handwritten segmentation in linear drawings. Pattern Recognition Letters 18(1997), pp. 193-202.
[32] XIAOLIN LI, DIT-YAN YEUNG. On-Line handwritten alphanumeric character recognition using dominant points in strokes. Pattern Recognition, Vol. 30, No. 1, pp. 31-44, (1997).
[33] Sang Kyoon Kim, Se Myung Park. On-line recognition of Korean characters using ART neural network and hidden Markov model. Journal of Systems Architecture 44(1998), pp. 971-984.
[34] Kam-Fai Chan, Dit-Yan Yeung. Mathematical Expression Recognition: A Survey
[35] K.C. Jung, H.J. Kim. Korean character recognition using a TDNN and an HMM. Pattern Recognition Letters, 20(1999), pp. 551-563.
[36] Y. Le Cun, I. Guyon. Handwritten Digit Recognition: Applications of Neural Network Chips and Automatic Learning. IEEE. Communications Magazine, November 1989, pp. 41-46.
[37] Park, H.S., Lee, S.W., Off-line recognition of large-set handwritten characters with multiple hidden Markov models. Pattern Recognition 29(2), pp. 231-244.
[38] Sean R. Eddy. Profile Hidden Markov Models; review. Bioihformatics, Vol. 14, No. 9,1998, pp. 755-763.
[39] G. Bradski, G.A. Capenter, S. Grossberg. Working memories for storage and recall of arbitrary temporal sequences. Int. Joint. Conf. Neural Networks, Ⅱ, Baltimore Maryland, pp. 57-62.
[40] 黄襄念，程萍，赵学军．自由手写拉丁字母联机识别．计算机应用2000，pp．40-42
[41] 赵学军，余楚中，乔进．联机方法与脱机方法相结合识别自有手写数字．重庆大学学报(自然科学版)，Vol．21，No．5(1998)，pp．70-74．
[42] 赵学军，余楚中，潘保昌．联机数字符号的基元识别方法．重庆大学学报，1998(2)．pp．327-334．
[43] 朱小燕，史一凡，马少平．手写体字符识别研究．模式识别与人工智能．Vol．13 No．2(2000)，pp．174-180．
[44] 徐秉铮，张百灵，韦岗．《神经网络理论与应用》．华南理工大学出版社1994年
[45] 黄德双 《神经网络模式识别系统理论》．第一版．电子工业出版社1996年
[46] Abhijit S. Pandya, Robert B. Macy(著)，徐勇 荆涛(译)．《神经网络模式识别及其实现》．电子工业出版社
[47] 夏良正(主编)．《数字图像处理》第一版．东南大学出版社1996年
[48] 郭力宾，吴微．二维图像中交叉点的神经网络识别(已经接收) 大连理工大学学报2003年
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |