First in this paper we analyze the current situation in samples capturing of palmprint diagnosis , as the existed systems have lots of disadvantages , the demands of sampling capture cannot be fulfilled , we design a capturing system which has a relative high precise rate , and high resolution , and is based on multi - lighting images fusion , and really be able to provide excellent palmprint samples for the later process of palmprint diagnosis 本文首先分析了目前掌纹诊病图像样本的采集现状,目前各种采集系统存在诸多难以克服的缺陷,无法满足现阶段掌纹诊病对于掌纹图像样本要求,因此设计了一套高精度、高分辨率的、基于多方向光源图像融合的掌纹采集系统,满足了掌纹诊病后期诊断对高质量图像的要求。
For the implement of the capturing device module , we first discuss the features of the palm and the palmprint , through which we design a device that has two - direction lighting , and has a very high resolution . through mass experiments on the capturing , the device does have the ability to preserve the details in the palms 对于采集模块的实现,首先详细分析了手掌及掌纹的特点,并针对这些特点,设计了一种双方向照明、高分辨率的采集设备,经大量样本采集实验表明,该设备能够将手掌上诸多尺度的细节特征很好的保存下来,达到较高的空间分辨率。
In this paper , two novel palmprint recognition methods are proposed in order to overcome the drawback of current algorithms . the whole design and implementation of palmprint recognition system including image acquisition , preprocessing , the basic idea and implementation of palmprint feature extraction and automatic palmprint classification and test are given 为了克服现有算法的不足,本文提出两种新的掌纹识别算法,并给出掌纹识别系统的总体设计和实现过程,包括图像获取和预处理,掌纹特征提取方法的基本思想和实现,以及掌纹的自动分类和测试。
Handwritten signature has its own virtues : handwritten signature has been a human behavior characteristic and been widely accepted and applied since ancient times ; online signature capture devices are much cheaper than iris and palmprint devices ; handwritten signature is more difficult imitated than other personal physical characteristics . therefore , online handwritten signature verification is hotspot in the biometrics field 签名鉴别具有其独特的优点:手写签名自古以来就是一种被人们普遍认可并广泛应用的行为特征;手写签名的采集设备价格比虹膜和掌纹等采集设备更低廉;作为一种行为特征,手写签名比人体物理特征更难于模仿等。
Through a lot of merging experiments on the samples , this paper devise a fusion way based on the features of the palm and the palmprint , which is suitable to preserve the multi - scale palmprint features . the merging module finally provides the detailed images that merged form different lighting images for the later modules in palmprint diagnosis , makes it possible to obtain the information that deeply hidden in the complex lines of the palm 图像融合模块则是系统工作的中心,通过大量的样本采集融合实验,本文得出一种依据掌纹特点、最适合保存包含多尺度细节纹理的掌纹图像的融合方法,它为后续掌纹诊病处理提供了融合后的、包含有大量信息的掌纹图像,实现了多方向细节观察的目的。
Finally , combining the two extraction methods with the two classification methods , the thesis put forward four models of palmprint recognition : k - l + ld model , k - l + nn model , nn + ld model and nn + nn model . the experiments show the accuracy , efficiency and the fault tolerance ability of these models . in terms of their characteristic , we can apply them in various fields 论文把两种特征提取方法和两种分类器设计方法进行结合，提出k - l变换与最小分类器、 k - l变换与bp神经网络分类器、线性神经网络与最小分类器、线性神经网络与bp神经网络分类器四种组合，最后对四种识别方法进行比较，根据它们识别的准确率、效率以及容错能力对识别结果进行分析，总结出各种方法的优缺点，根据它们的特点，提出在不同方面的应用。
According to the fact that the basic features of apalmprint , including principal lines , wrinkles and ridges , havedifferent resolutions , in this paper we analyze palmprints using amulti - resolution method and define a novel palmprint feature , whichcalled wavelet energy feature , based on the wavelet transform . wef can reflect the wavelet energy distribution of the principal lines , wrinkles and ridges in different directions at different resolutions scales , thus it can efficiently characterize palmprints . this paperalso analyses the discriminabilities of each level wef and , according to these discriminabilities , chooses a suitable weight for each levelto compute the weighted city block distance for recognition . theexperimental results show that the order of the discriminabilities ofeach level wef , from strong to weak , is the 4th , 3rd , 5th , 2nd and 1stlevel 作为对现有人体生物特征识别技术的重要补充，掌纹识别有着其独特的优点：掌纹比指纹含有更多的可区分信息掌纹采集设备的价格比虹膜采集设备的价格要低廉得多掌纹特征比签名特征更为稳定掌纹识别可获得比人脸识别更高的识别精度掌纹含有独特的线特征包括主线和皱褶，这些线特征具有很强的区分能力，并可以在低分辨率图像中提取出来可以将手掌上的各种特征融合在一起建立一个高精度的生物识别系统等。
