一種基于手形特征點(diǎn)匹配的身份認(rèn)證方法
Atuomated identity verification based on feature points matching of hand shapes
-
摘要: 該文提出了一種基于手形的身份認(rèn)證方法。該方法首先通過對手形圖像的處理,將手形表示為由一系列有序點(diǎn)構(gòu)成的特征點(diǎn)集,然后應(yīng)用基于確定性退火技術(shù)的點(diǎn)匹配算法對兩個(gè)手形的特征點(diǎn)集進(jìn)行匹配,得到用于認(rèn)證的兩個(gè)匹配參數(shù):平均匹配誤差和匹配率,最后設(shè)計(jì)適當(dāng)?shù)姆诸惼?對匹配結(jié)果進(jìn)行分類判決,實(shí)現(xiàn)身份認(rèn)證。考慮到在手形認(rèn)證的研究中都是小樣本情況,因此首次將建立在統(tǒng)計(jì)學(xué)習(xí)理論(SLT)基礎(chǔ)之上的支持向量機(jī)(SVM)應(yīng)用于手形的認(rèn)證中,得到的結(jié)果是令人滿意的。實(shí)驗(yàn)證明,與現(xiàn)有的手形認(rèn)證方法相比,該文的方法不僅提高了認(rèn)證的準(zhǔn)確性,而且增強(qiáng)了認(rèn)證的魯棒性。Abstract: This paper presents a method for identity verification based on matching of hand shapes. The method first represents the shapes of hands by sets of ordered points. Next, the two sets of points are matched using point matching algorithm based on deterministic annealing and get the two matching parameters: mean matching error and matching rate. Finally, the classifier is designed for classification/verification. Considering the research of hand shape verification usually works in practical cases of limited or small samples, Support Vector Machine (SVM) is developed for verification. SVM is a new technique in the field of Statistical Learning Theory (SLT). The preliminary results show that the method can obtain higher levels of accuracy and robustness than the existing systems that based on hand geometry measurements.
-
計(jì)量
- 文章訪問數(shù): 2111
- HTML全文瀏覽量: 159
- PDF下載量: 589
- 被引次數(shù): 0
下載:
