基于ARM与WinCE的掌纹鉴别系统

Palmprint identification system based on ARM and WinCE

掌纹识别是个人身份识别的一种有效手段,而识别设备的小型化则将掌纹鉴别推向更广阔的应用领域。实现了一种基于ARM和WinCE的掌纹鉴别系统方案,ARM处理器从数字摄像头获取掌纹图像,提取特征,与掌纹特征库中的对应模板比对,根据匹配的结果给出一个开关信号量。实验证明该系统能以较高精度鉴别掌纹,软件采用的算法具有平移、旋转不变,光照与仿射部分不变等优点,对手掌的姿态、距离、位置变化具有较高的容纳能力,用非接触式的掌纹采集方式,不需要定位装置,充分体现该系统的用户亲和力。此外,该系统还具有体积小、成本低、低功耗等优点,适合应用于成本和功耗敏感的民用系统中。

Palmprint recognition is an efficient method to identify a person. The small size of palmprint identification equipment will facilitate applications and extend application scope. This paper implements a practical schema of the palmprint identification system based on ARM and WinCE. The ARM processor acquires the palm image from a digital camera, extracts the features from the palm image and matches the feature with corresponding template in the database, finally gives out the identification result. Experimentations proved that the proposed system could identify palmprints with high accuracy. Fur- thermore, the proposed algorithm is invariant to image translation and rotation, and is partially invariant to affine distortion, image scale, changes in 3D viewpoint and illumination. The palmprint could be captured in contactless manner and does not need any fixing facility, which is much friendly to the users. Besides, the proposed system has the merits of small size, cost-effective and low-power, which are appropriate to be adopted in power and cost sensitive civilian applications.