• E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2021

    5.610

    Impact Factor 2022

    6.247

  • E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2021

    5.610

    Impact Factor 2022

    6.247

  • E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2021

    5.610

    Impact Factor 2022

    6.247

INTERNATIONAL JOURNAL OF INVENTIONS IN ENGINEERING & SCIENCE TECHNOLOGY

International Peer Reviewed (Refereed), Open Access Research Journal
(By Aryavart International University, India)

Paper Details

DIFFERENT TEXTURE CLASSIFICATION AND AGE PREDICTION OF FACE IMAGES USING PEANOCOUNT DECISION CLASSIFIER

BasavaRaju K

Research Scholar, JNTUK, A.P. India

Dr. Y. RamaDevi

HOD in CSE Dept., CBIT, Gandipet, Hyderabad.

Dr. P.V. Kumar

Professor in CSE Dept, OU, Hyderabad

26 - 39 Vol. 1, Jan-Dec, 2015
Receiving Date: 2015-02-01;    Acceptance Date: 2015-02-22;    Publication Date: 2015-03-16
Download PDF

Abstract

Recognition of skin is used in many applications ranging from algorithms for predicting age , face detection, gender classification, and to objectionable image filtering. These data collections are growing rapidly and can therefore be considered as spatial data streams. Time is a major issue for data stream classification,. However, these spatial data sets are too large to be classified effectively in a reasonable amount of time using existing methods. In this work a novel and computational fast algorithm is proposed for predicting age of humans with PeanoCountTree (P-Tree). The predicting system was developed and tested based on texture features extracted local gradient patterns (LGP) and gray level co-occurrence matrix (GLMC) to give better and more predicting accuracy with a range of time period. The PTree is a spatial data organization that provides a lossless compressed representation of a spatial data set and facilitates efficient classification and other data mining techniques. Using P-tree structure, fast calculation of measurements, such as information gain, can be achieved. We compare P-tree decision tree induction classification and a classical decision tree induction method with respect to the speed at which the classifier can be built (and rebuilt when substantial amounts of new data arrive). Experimental results show that the P-tree method is significantly faster than existing classification methods, making it the preferred method for mining on spatial data streams.

Keywords: Feature extraction; Gradient Operator; GLCM; P-Classifier, bSQ, Peano Count Tree, Mining

    References

  1. Hwei-Jen Lin, Shu-Yi Wang, Shwu-Huey, and Yang –Ta-Kao “Face Detection Basedon Skin Color Segmentation and NeuralNetwork” IEEE Transactions on, Volume: 2,pp1144- 1149, ISBN: 0-7803- 9422-4, 2005
  2. Son Lam Phung, AbdesselamBouzerdoum,and Douglas Chai “Skin Segmentation UsingColor and Edge Information” IEEE ISSPAISBN: 0-7803-7946-2 2003
  3. Domingos, P. and Hulten, G., “Mining high-speed data streams”, Proceedings of ACMSIGKDD 2000.
  4. Domingos, P., &Hulten, G., “Catching Up with the Data: Research Issues in Mining DataStreams”, DMKD 2001.
  5. J. R. Quinlan andR. L. Riverst, “Inferring decision trees using the minimum descriptionlength principle”, Information and Computation, 80, 227-248, 1989
  6. Quinlan, J. R., “C4.5: Programs for Machine Learning”, Morgan Kaufmann, 1993
  7. L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, “Classfication and RegressionTrees”, Wadsworth, Belmont, 1984.
  8. R. Agrawal, S. Ghosh, T. Imielinski, B. Iyer, and A. Swami. “An interval classifier fordatabase mining applications”, VLDB 1992.
  9. J. Shafer, R. Agrawal, and M. Mehta, “SPRINT: A scalable parallel classifier for datamining”, VLDB 96.
  10. William Perrizo, Qin Ding, Qiang Ding, Amlendu Roy, “On Mining Satellite and OtherRemotely Sensed Images”, DMKD 2001.
  11. Al abbadi, N.K. et. al., “Skin texture recognition using neural network,” In Proc. of the International Arab Conference on Information Technology, Tunisia, 2008
  12. Parekh, R., Mukherjee, A., “Advances in Telemedicine: A Multimedia-Based Texture Recognition Diagnostic System”, In Proc. of the Business and Health Administration Association (BHAA ‟09) International Conference, Chicago, Illinois, USA, pp. 88-97, March 18-20, 2009
  13. J. Brand and J. Mason, “A Comparative Assessment of Three Approaches to Pixel- Level Human Skin Detection,” Proc. IEEE Int’l Conf. Pattern Recognition, vol. 1, pp. 1056-1059, Sept. 2000.
  14. Smach, F. ET. al., “Design of a neural networks classifier for face detection”, Science Publication, Journal of Computer Science, Vol. 2, issue 3, pp. 257-260, 2006
  15. Smith, J.R. et.al., “Quad tree segmentation for texture based image query”, In Proc. of the second ACM international conference on Multimedia, San Francisco, California, United States, pp. 279 - 286, 1994
  16. Baochang Zhang, YongshengGao, Sanqiang Zhao, and JianzhuangLiuLocal Derivative Pattern Versus Local Binary Pattern: Face Recognition With High-OrderLocal Pattern Descriptor.IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 19, NO. 2, FEBRUARY 2010.
  17. Tinku Acharya “Image Processing Principles and Applications” A JOHN WILEY & SONS,MC. 2005.
  18. Qiang ding, William Perrizo, “Cluster analysis of spatial data using peano count tree”, Proceedings of CATA 2002, San Francisco, USA, April 4-6, 2002
  19. Jiawei Han, MichelineKamber, “Data Mining: Concepts and Techniques”, MorganKaufmann, 2001.
  20. “Association rule mining on remotely sensed images using peano count trees,” Pacific Asia Conference on Knowledge Discovery and Data Mining, pp. 66-79, 2002.
Back