Human Head Portrait Feature Extraction Based on SIFT

Abstract:

As the number of students who attend the arts exams has been growing, each admission institutions need to score the human head portraits of art sketch with the number of ten thousand and even 100 thousand. Thus it is an innovative research on how to conduct image recognition with the help of advanced computer technology. Image Recognition Technology is to give the computer the intelligence of human vision, so that the computer can quickly and accurately recognize the object on the input images. However, in the recognition process such factors as light, rotation and shield increase the difficulty of identifying the human head portrait images. In order to get better recognition performance, this paper studies the feature extraction of human head portrait based on SIFT (Scale Invariant Feature Transform). From the practical application, it can be seen that the approach proposed in this paper is feasible and is of good recognition performance.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 4322-4324
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.4322
• Online since: September 2014
• Authors: Xue Ding*, Shun Han, Hong Hong Yang, Xiao Feng Wang, Kun Wu Yang
• Keywords: Art Sketch, Feature Extraction, Human Head Portrait, SIFT Features

References

[1] David G. Lowe Object Recognition from Local Scale — Invarint Features [C]. International Conference on Computer Vision, 1999, pp.1150-1157.

[2] David G. Lowe. Distinctive Image Features from Scale-Invariant Key-Points. International Journal of Computer Vision. Vol. 60 (2004) No. 2, pp.91-110.

DOI: 10.1023/b:visi.0000029664.99615.94

[3] Krystian Mikolajczyk and Cordelia Schmid. A Performance Evaluation of Local Descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, Vol. 27 (2005) No. 10, pp.1615-1630.

DOI: 10.1109/tpami.2005.188