2D-Gabor filter design and parameter selection based on iris recognition

作者：Huo Guang; Liu Yuanning; Zhu Xiaodong^*

来源：Journal of Information and Computational Science, 2014, 11(6): 1995-2002.

DOI：10.12733/jics20103293

• Equal error rate
• Gabor filter design
• Identification accuracy
• Iris recognition
• Iris texture
• Parameter selection
• Selection methods
• Similarity threshold

The parameter selection is the difficult premise of the feature extraction by 2D-Gabor filter. This paper, based on a detailed analysis of the variation between the frequency, scale, orientation and the decidability index, proposes a suitable selection method for the extraction of the iris texture features with 2D-Gabor filter, and then applies it to achieve the entire iris recognition. The recognition test of system was performed in JLU-V2.0 iris image database of Jilin University, to be specific: the decidability index of the system is 6.704901. When the equal error rate is 0.2296% and similarity threshold equals to 0.340122, the identification accuracy is 99.7704%. Experimental results demonstrate that the method of designing filter has a strong capability of recognition.

• 出版日期2014