关键词: 生物特征识别, 图像处理, 手掌静脉识别, 方向梯度直方图（HOG）, 支持向量机（SVM）

Abstract: As a new emerging kind of biometrics technology, it plays an increasingly important influence and application in various security fields with the progress of the times. This paper presents an improved palm vein image preprocessing methods, using a pixel gray value mapping to enhance the image of the vein textures to remove other distractions. For palm vein texture feature extraction and recognition, this paper presents a palm vein recognition algorithm based on Histogram of Oriented Gradients（HOG） and improved Threshold Support Vector Machine（T-SVM） to better adapt to the palm vein recognition features. The experimental results demonstrate that the proposed algorithm can not only be more rapid identification and recognition rate but also reach a high accuracy.

Key words: biometrics, image processing, palm vein recognition, Histogram of Oriented Gradients（HOG）, Support Vector Machine（SVM）