Palmistry is an ancient type of art and is trusted by generations of people. Our system aims at introducing this ancient science to the modern technology. Instead of traditional face-to-face palm reading, our online fortune telling system is where the users submit their hand images online and get the predictions immediately. The major line patterns in palmistry are summarized to become the models for online fortune telling through palm reading. The images are converted to Hough space to extract principal lines. This is a novel approach to the application of the Hough transform for feature extraction of palmprint. A principal line detection mechanism in transformed space is also proposed based on a flooding process, which is motivated by Rainfalling Watershed segmentation algorithm. The local neighbourhood information of principal lines is used as a means to measure similarity as well. The experiment results show that we achieve low time complexity with high accuracy.
[1]
Xiaozhou Yu,et al.
Palmprint identification using Hausdorff distance
,
2004,
IEEE International Workshop on Biomedical Circuits and Systems, 2004..
[2]
Yee-Hong Yang,et al.
Dynamic two-strip algorithm in curve fitting
,
1990,
Pattern Recognit..
[3]
David Zhang,et al.
Palmprint Identification by Fourier Transform
,
2002,
Int. J. Pattern Recognit. Artif. Intell..
[4]
Anil K. Jain,et al.
Matching of palmprints
,
2002,
Pattern Recognit. Lett..
[5]
David Zhang,et al.
Palmprint recognition using eigenpalms features
,
2003,
Pattern Recognit. Lett..
[6]
David Zhang,et al.
On hierarchical palmprint coding with multiple features for personal identification in large databases
,
2004,
IEEE Transactions on Circuits and Systems for Video Technology.