127

本程序是多结构元素形态学滤波的探讨，通过选择不同的结构元素多尺度序列Bi，来得到最合适的结果(This program is a multi-structure elements of morphological filtering by selecting different multi-scale structure elements sequence Bi, get the most appropriate results)

基于hessian矩阵的眼底图像血管增强滤波(Vessel Enhanced Filtering of Eyeground Images Based on Hessian Matrix)

指纹图像因设备、图像增强处理等原因造成的纹线断裂会产生伪特征点,会对指纹识别产生负面影响。在结 合传统方法优点的同时,针对间距大、方向偏移小和间距大、方向偏移大的断裂情况,本文设计出窗口制约法和改进的 窗口制约法2 种不同的修复方法。实验结果表明,该方法使修复更加全面、完整,提高了伪特征点去除率,易于编程实 现,对细化指纹图像的断裂有很好的修复效果。(The broken ridge fingerprint image processing equipment, image enhancement and other causes will generate pseudo-feature points to be a negative impact on fingerprint identification. While combining the traditional method has the advantage, for the spacing, direction offset small spacing, direction offset large fracture situation, this design window constraints window method and the improved two kinds of constraints, different repair methods. Experimental results show the method to fix a more comprehensive and complete removal of pseudo-feature points, easy to program, well thinned fingerprint image fracture repair.)

车辆检测跟踪,采用matlab编程，可对车辆进行目标跟踪与检测(Vehicle detection and tracking)

图像处理的偏微分方程方法，包括曲线演化，图像分割，图像滤波，图像复原等的matlab源代码。(Partial differential equations of image processing methods, including curve evolution, image segmentation, image filtering, image restoration, etc. matlab source code.)

基于c5509的jpeg图像压缩实现 ，利用c语言(The jpeg image compression based c5509 achieved using c language)

用kfcm算法实现数据的聚类和分类效果。(Kfcm algorithm is used to achieve data clustering and classification results.)

提取二值图像中的所有非零点坐标，进行矩阵标准化，最后进行二次曲线拟合(Extracting the binary image of all non-zero coordinates, matrix standardized last quadratic curve fitting)

图形裁剪，实现对画的线，多边形，交点进行剪裁，实现图形的规范化(Graphic cutting, to achieve the painting line, polygon, tailoring intersection, graphics standardization)

背景差分法运动目标检测，建立背景模型，然后使用当前模型与背景模型相减，再和阈值相比较，比阈值大的即判断为有运动目标，比阈值小的即判断为没有运动目标，阈值大小可以自己适当调试，根据经验值设置最佳阈值。(Background difference method is used for moving target detection and setting up background model, then using current model and background model subtracting, and comparing with threshold, it is judged to have moving target compared with the threshold value, which is smaller than threshold. The size of threshold can be adjusted properly, and the best threshold is set according to experience value.)