科技日新月異,產品越做越小,指紋感測器面積和擷取的 DPI 也越來 越小, 指紋影像的解析度或是影像複雜度都會影響辨識的結果,傳統的單 一種辨識方法已經不敷使用,在此提出特徵點辨識和非特徵點辨識兩種辨識 方法再加以融合,非特徵點辨識方法使用了統計和機率類神經網路,經過指 紋的訓練再加以分類來達到目的,最後用決策融合的方法上實驗了 max 和 two-stage 等融合方式,決策融合後 two-stage 模式的錯誤率低於特徵點和非 特徵點辨識方法。;Product get smaller and technological improve every day, relatively small area of the fingerprint sensor to capture the DPI is also getting smaller and smaller, resolution or image complexity will affect the image of the fingerprint identification result, the traditional approach has been to identify a single one inadequate use of feature points presented in this recognition and non-recognition feature points plus two kinds of identification method to fusion, non-feature point identification method uses a statistical and probability neural network, coupled with training through fingerprint classification to achieve their goals in decision fusion experiments on the max and two-stage and other fusion methods, and finally decision fusion experiment error rate lower than the previous two individual identification party.
