sibuxiangyi

在matlab环境下完成分水岭算法图像分割(Matlab environment in the completion of the watershed image segmentation algorithm)

提出了一种基于图像边缘连接的线段检测方法。数字图像中的线段是由很多线段图元组成,在同一 条线段中,它们的方向是相同的并且受到真实线段的方向约束。因此可以通过提取小的线段图元, 然后分析它们 的连接特性, 进行线段的检测。首先用ADM 算法对图像进行边缘检测, 得到单像素宽的边缘 然后在4 个方向上 进行线段的检测 对初步得到的结果进行合并和验证, 去掉短的线段, 连接临近的线段。经过实验证明, 该方法能 够快速地提取图像中的线段,并且对噪声具有一定的鲁棒性(A line segment connecting a detection method based on image edges. The segment of the digital image is composed by many segments elements, their orientation is the same and by the real line segment direction constraint in the same segment. By extracting a small segment Element can then analyze their connection characteristics for the detection of the line segment. First with ADM algorithm for edge detection on the image to obtain a single-pixel-wide edge then in the four directions on the detection of the line segments merger and verification of the preliminary results obtained, removing the short line segments, the line segments connected near. The experiments show that this method can quickly extract the line segments in the image, and certain robustness to noise)

多尺度的光谱图像分割，有对应的论文和matlab及c++代码(Multiscale spectral image segmentation, there are papers and the corresponding matlab and c++ code)

BP神经网络，可以处理图像进行分类等各种处理的源码(BP neural network image processing source code)

说明：  为了在抑制噪声时尽可能保留图像边缘信息，提出一种自适应各向异性高斯滤波器设计方法. 该方法由独立 强度传播（IDS）模型决定滤波器的长轴尺度，由像素的邻域平滑度决定长短轴的比例，然后根据该处的灰度梯度方 向自适应决定各向异性滤波器的长轴方向. 仿真实验表明，提出的自适应各向异性滤波器具有很强的噪声抑制和 边缘保持能力. (In order to suppress noise, as far as possible to keep the image edge information, an adaptive anisotropic Gaussian filter design methods. The method by the independent strength spread (IDS) model determines the long axis of the filter scale, the pixel neighborhood smoothness determine the ratio of minor axis, and then there' s gray gradient direction of adaptive decision the long axis of anisotropic filter. Simulation results show that the proposed adaptive anisotropic filter has a strong noise suppression and preserve edges.)

基于图像颜色矩和纹理的图像检索系统，matlab语言编写，图像库包含在内(Image color and texture-based image retrieval system, Matlab language, image library included)

说明：  利用matlab对已知多对控制点的情况下进行两张图像校正，该算法能够取得较好的结果(Using matlab to correct two images when multiple pairs of control points are known.The algorithm can get good results.)

说明：  可通过Hog和svm实现小狮子的分类，将其分为两类(The classification of small lions can be realized by hogs and SVM, which can be divided into two categories)

对较真实的运动模糊图像进行恢复，此种运动模糊图像限于水平或垂直的运动模糊图像。 参考文献：Removing Camera Shake from a Single Image ,siggraph06(On the more realistic motion-blurred image restoration, such motion-blurred images limited to horizontal or vertical motion-blurred images. References: Removing Camera Shake from a Single Image, siggraph06)

用于提取图像的Zernike矩特征，从而实现目标识别，可运行(Used to extract the image of the Zernike moment characteristics, so as to realize target identification, can run)