Abstract:

In order to achieve quick and reliable assessment of finger vein image, the paper proposes an assessment method of vein image quality based on the features of regional column average gradient and texture roughness. In this method, firstly, the feature of regional column average gradient is defined on the basis of which the first quality assessment is made. If the requirement is met, finger registration will be done directly. Otherwise the second assessment is conducted based on the feature of texture roughness. If the requirement is met this time, finger registration will be done. If not, the system prompts the user for another finger to register. The results of simulation experiment show that this method is effective and efficient and it is able to meet the requirement of finger vein recognition.

Key words: regional column average gradient;texture roughness;finger vein recognition;image quality assessment