A contour extraction algorithm for digital images based on water balloons snake model

Due to weak edges and low contrast areas in digital images, such as a left ventricle in Magnetic Resonance Imaging (MRI) images, a deformation curve may leak from the outer boundary when images are segmented using the traditional snake model. An improved algorithm based on the water balloons snake model is introduced to solve this problem. Firstly, the barycenter and the boundary shape area of the left ventricle in a digital MRI image are obtained through mathematical morphology. The left ventricular watershed line is obtained next using a watershed transform algorithm, which is taken as the initial deformation curve in a balloon snake model to capture the contour. Different snake models are tested to digitally tagged MRI images of left ventricles of small pigs. Contrast results indicate that the water balloons snake model can solve the leakage problem in traditional snake and balloon snake models. In addition, the processing speed is improved significantly.     

面向植物生长智能监控的叶颜色特征提取

根据植物生长智能监控的需求,设计了叶颜色特征提取方法：首先提取叶整体颜色特征,根据特征数据能够判断植物叶是健康、存在整体颜色变异还是存在局部颜色变异;如果存在局部颜色变异,进行局部颜色变异部分分割、颜色特征提取和空间分布特征提取。将一组具有不同程度颜色变异的植物叶的阳面和阴面图像作为两个系列进行了对比测试。测试数据表明：特征参数能够区分健康的叶和存在变异的叶,能够区分不同类型和不同程度的颜色变异,能够为后续决策处理提供数据支持,特征提取方法适合植物生长智能监控。     

A method for feature contour extraction of triangular meshesbased on multi seed points

An algorithm for extracting feature curves of triangular meshes based on multi seed points is proposed. First, feature contour positions of triangular meshes are detected on the basis of curvature value and normal vector, and these positions are highlighted with difference colours. Then, several seed points on the proper position are assigned and their feature attributes are computed. Next, their node assessment functions are constructed and correct path nodes are chosen. Finally, the curves extracted from the triangular meshes are smoothed. Experimental results show that the method is not only effective to extract closed feature curves and sharp edges, but also useful for opened feature curves and the region that the features change gently. It has higher accuracy than other methods to detect feature at the branch feature regions.     

A fast segmentation algorithm for images with intensity in-homogeneity

A novel fast method based on local region active contour model is proposed to overcome the difficult and ineffective segmentation of in-homogenous images. A new energy function is defined by combining kernel function and cut metric. On one hand,kernel function is favor of computing the in-homogenous distribution of local regions effectively;on the other hand,better approximation of the curve length by cut metric can help contours to quickly evolve into the object’s boundary. In addition,in the evolving process of contours,a max-flow method is adopted,instead of traditional computational level set method. Experimental results of synthetic and real images show that the proposed method can effectively segment objects with weak boundary in in-homogenous images,as well as the complex structure objects with multi-gray levels. At the same time,it is robust to noise and the initial contours.     

面向植物分类的被子植物叶形特征自动提取

在植物分类学中,叶的形态特征是重要的分类依据。根据被子植物分类对叶特征提取的要求,设计了植物叶形特征自动提取方案：使用扫描仪进行植物叶图像采集;对原始图像进行预处理,包括去除背景、去除叶柄、叶片方位校正;根据预处理后的图像进行叶形特征提取,获得纵横比、位置度两个特征数据。根据特征数据结合植物分类学知识能够识别叶片的基本形状。通过测试验证了方案的有效性。     

The switching median filter denoising algorithm for encrypted images

Sometimes it is necessary to send the image data to the third party device to process. To ensure the image safety, it is necessary to encrypt the image before processing. A new algorithm for encrypted image processing is proposed. The image owner encrypts     

Fusion method for infrared and visible light images based on image segmentation and stationary wavelet transform

A novel image fusion method based on image segmentation and stationary wavelet transform (SWT) is proposed to improve the visual effect of fused infrared and visible light images. Infrared image is firstly separated into object and background region utilizing Otsu combined with edge detection. Then a multiresolution decomposition using SWT is made to the background region of the infrared image and the visible light image. Neighborhood spatial frequency and absolute value are adopted as fusion rules in low-frequency and high-frequency coefficients. The background fused image is reconstructed by inverse SWT. The final infrared and visible light fused image is obtained by fusing the background fused image and the object region of infrared image base on weighted fusion rule. The experimental results show that the object information of the infrared image is obviously highlighted and the scene information of the visible light image is well represented. The visual effect of fused image is improved efficiently by utilizing the proposed method. The proposed method works better than the traditional Laplacian Pyramid and wavelet transform fusion algorithms in terms of standard deviation, comentropy and mutual information. Experimental results verify its effectiveness.     

植物叶裂特征自动提取研究

为了实现叶裂特征自动提取,构造了植物叶片凸包距离函数,通过分析该函数,判断是否存在叶裂,如果存在叶裂,进一步判别叶裂类型,获取叶裂数量与深度数据。利用树叶数据库中的图像对方案进行了测试,结果显示：叶裂存在性参数对叶片是否具有叶裂区分明显,叶裂位置检测、叶裂数目判定准确,叶裂类型判别参数体现了不同叶裂类型的差异,叶裂深度参数体现了叶裂的深度差异。测试表明方案切实可行,可用于植物的种类自动识别和长势监控系统。     

Eye localization and state analysis for driver fatigue detection

To solve the problem of eye precise localization in head multi-position,an algorithm based on skin color and texture feature is proposed. Face is detected based on skin color and according to the gray difference between eyes and other parts,and eye candidate areas are found with the method of binarization and morphological image processing. Eyes are detected by calculating the texture characteristics values of candidate areas. The method of black fleck fitting elliptic is used to check the factuality of the 2 detected eyes and measure the eye opening extent. The experimental results demonstrate the texture characteristics values of candidate areas are still different when head angle changes and the proposed method can accurately detect eyes. The method is simple and fast,and not influenced by driver head posture.