本文在研究和分析方差法和方向圖法的基礎(chǔ)上，提出了一種基于最大類間方差的指紋圖像分割方法，即采用最大類間方差與圖像分塊處理相結(jié)合的方法來(lái)分割指紋圖像。實(shí)驗(yàn)結(jié)果表明，該方法無(wú)論是對(duì)高對(duì)比度的指紋圖像還是對(duì)低對(duì)比度的指紋圖像均有良好的分割效果；相對(duì)于傳統(tǒng)的指紋圖像分割方法，本文的方法不僅具有無(wú)需根據(jù)經(jīng)驗(yàn)來(lái)選擇閾值的優(yōu)點(diǎn)，而且該方法在運(yùn)算速度上比傳統(tǒng)方法更快，更適合于實(shí)時(shí)處理。
關(guān)鍵詞：指紋圖像；最大類間方差；分割

Research on the Segmenting Methods of Fingerprint Image Zhang ZhengYan, Xu RongQing （School of Electronics and Information Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003） Abstract: The two common means for segmenting the fingerprint image are variance method and directional method. After investigating and analyzing the two methods, this paper presents a new approach to segmenting the fingerprint images based on the maximum between-cluster variance (MBV). This method segments the fingerprint images by means of the MBV and the technology of dividing the images into blocks. The experimental results indicate that this method performs well on the fingerprint images with high and low contrast.. Compared with the two common methods, this new method not only has the advantage in choosing the threshold without the experience, but also works faster. This method is more suitable for real-time processing.
Key words: fingerprint images; MBV; segmentation