International Journal of Information Technology & Computer Science ( IJITCS )
Deformable object modeling is an interest topic on biometrics field, such as the facial features detection. One of method used to detect the deformable objects is Active Shape Model method. However, Active Shape Model has some weaknesses, when detection process is performed. The first weakness, ASM needs many training sets to obtain the shape variation. If the movement direction is not covered on the training sets, then ASM cannot overcome the shape movement to the corresponding features. The second weakness, if the shape initialization is not closed to the corresponding features, then the features searching process will need long time and even fail to detect the corresponding features. In this research, we proposed new approach to detect the facial sketch features. The shape will move to the corresponding features based on the greatest gradation, though the movement direction is not covered on the training set. The shape initialization will be located based on three parameters, which are the landmark average, variation average and the difference of the deviation maximum and minimum. We have tested 200 the hatching facial images, they consist of 100 the hatching facial images tilted to the left and the rest is tilted to the right. Experimental shows that detection percentage is 88.47% and 88.86% for the hatching facial sketch tilted to the right and to the left .
: Geometrical stricture, the greatest gradation, facial sketch, feature detection.
- Koichi Ito, Hiroshi Nakajima, Koji Kobayashi, Takafumi Aoki and Tatsuo Higuchi (2004), "A Fingerprint Matching Algorithm Using Phace-Only Correlation", IEICE Transaction Vol. E-87A, No.3, pp. 682-691
- Arif Muntasa, Hariadi M, Mauridhi Hery Purnomo (2009), “A New Formulation of Face Sketch Multiple Features Detection Using Pyramid Parameter Model and Simultaneously Landmark Movement”, International Journal of Computer Science Network and Security, Vol 9.
- Arif Muntasa, Mochammad Kautsar Sophan, Mauridhi Hery P., Kondo Kunio, (2012), “The Hatching Facial Sketch Representation based on Mixture Model”, IJACT: International Journal of Advancements in Computing Technology, Vol. 4, No. 3, pp. 239-249
- Zhang Xiaowe and Zhang Wenjun, (2012), "Face Detection and Feature Points Location and Tracking in Video Sequence", 4th International Conference on Computer Modeling and Simulation, Singapore
- Xiaoguang Lu and Anil K. Jain, (2005). "Multimodal Facial Feature Extraction for Automatic 3D Face Recognition", Dept. of Computer Science & Engineering Michigan State University East Lansing, MI 48824.
- Xiaoou Tang and Xiaogang Wang, (2003). “Face Sketch Synthesis and Recognition”, Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV) 2 Volume Set 0-7695-1950-4.
- Christos Davatzikos, Xiaodong Tao, and Dinggang Shen, (2003), "Hierarchical Active Shape Models, Using the Wavelet Transform", IEEE Transaction on Medical Imaging, VOL. 22, NO. 3, pp. 414-423
- T.F. Cootes, A. Hill, C.J. Taylor, J. Haslam, (1997) "The Use of Active Shape Model for Locating Structures in Medical Images", Image and Vision Computing Vol. 12, No. 6, pp. 355-366
- Bram van Ginneken, Alejandro F. Frangi, Joes J. Staal, Bart M. ter Haar Romeny, and Max A. Viergever, (2002), "Active Shape Model Segmentation With Optimal Features", IEEE Transactions on Medical Images, Vol. 21, No. 8, pp. 924-933
- M.G. Roberts, T.F. Cootes and J.E. Adams, (2005), “Vertebral shape: Automatic Measurement with dynamically sequenced active appearance models”. Proc. MICCAI, Vol. 2, pp.733-740.
- M. G. Roberts, T. F. Cootes and J. E. Adams, (2006), "Automatic segmentation of lumbar vertebrae on digitised radiographs using linked active appearance models", Proc. Medical Image Understanding and Analysis, Vol. 2, pp.120-4.
- M.G. Roberts, T.F. Cootes and J.E. Adams, (2007a), "Vertebral Morphometry: Semi-automatic Determination of Detailed Vertebral Shape from DXA Images using Active Appearance Models", Investigative Radiology Vol.41, No.12,pp.849-859.