出版社:Academy & Industry Research Collaboration Center (AIRCC)
摘要:Iris recognition systems have attracted much attention for their uniqueness, stability andreliability. However, performance of this system depends on quality of iris image. Thereforethere is a need to select good quality images before features can be extracted. In this paper, irisquality is done by assessing the effect of standard deviation, contrast, area ratio, occlusion,blur, dilation and sharpness on iris images. A fusion method based on principal componentanalysis (PCA) is proposed to determine the quality score. CASIA, IID and UBIRIS databasesare used to test the proposed algorithm. SVM was used to evaluate the performance of theproposed quality algorithm. . The experimental results demonstrated that the proposedalgorithm yields an efficiency of over 84 % and 90 % Correct Rate and Area under the Curverespectively. The use of character component to assess quality has been found to be sufficientfor quality detection.
关键词:Image quality; Iris recognition; Principal Component Analysis; Support Vector Machine.