Fourier Descriptors with Different Shape Signatures:a Comparative Study for Shape Based Retrieval of Kinematic Constraints

Fourier Descriptors（FD） has been widely used in image analysis and computer vision for shape recognition as they can be made independent of translation,rotation,as well as scaling.They have also been used for developing methods for the analysis and synthesis of four-bar linkages for path generation.This paper focuses on a comparative study of Fourier descriptors derived from various shape signatures of planar closed curves.This includes representations based on Cartesian coordinates,centroid distance,cumulative angle,and curvature.The comparison is conducted not only using commonly used criteria for shape representation and identification but also in the context of shape based retrieval of kinematic constraints for task centered mechanism design.Examples are provided to seek to extract geometric constraints such as circle,circular arc,ellipse and line-segment from a given motion.

Recognition of 3-D Aircrafts by Fourier Descriptors with Fast and Efficient Library Search

Fourier descriptors are used as features for 3-D aircraft classification and pose determination from a 2-D image recorded at an arbitrary viewing angle. By the feature ranking of Fourier descriptors, a classification procedure based on the fast nearest neighbour rule is proposed to save the matching time of an unknown aircraft with a partial library search. The testing results of some typical examples indicate this method is generally applicable and efficient in 3-D aircraft recognition.

Using three-dimensional discrete spherical Fourier descriptors based on surface curvature voxels for pollen particle recognition

This paper presents a new method for extract three-dimensional （3D） discrete spherical Fourier descriptors based on surface curvature voxels for pollen particle recognition. In order to reduce the high amount of pollen information and noise disturbance, the geometric normalized curvature voxels with the principal curvedness are first extracted to represent the intrinsic pollen volumetric data. Then the curvature voxels are decomposed into radial and angular components with spherical harmonic transform in spherical coordinates. Finally the 3D discrete Fourier transform is applied to the decomposed curvature voxels to obtain the 3D spherical Fourier descriptors for pollen recognition. Experimental results show that the presented descriptors are invariant to different pollen particle geometric transformations, such as pose change and spatial rotation, and can obtain high recognition accuracy and speed simultaneously.

The Use of Fourier Descriptors for the Classification and Analysis of Peripheral Blood Smears Image

The article discusses the use of Fourier descriptors for the analysis and classification of blood cells. A model describing the contour boundaries in the form of two-dimensional numerical sequence Fourier descriptors. The influence of the shape and orientation of the figures on the parameters of the Fourier descriptors. Explore ways to ensure the invariance of the Fourier descriptors with respect to geometric transformations. A model of the graphical representation of the Fourier descriptors of computer graphics tools. A method of forming a space of informative features based on Fourier descriptors for the neural network, classifying the contours of borders image segments.

Extracting and smoothing contours in mammograms using Fourier descriptors

Contour is an important pattern descriptor in image processing and particularly in region description, registration and length estimation. In many applications where contour is used, a good segmentation and an efficient smoothing method are needed. In X-ray images, such as mammograms, where object edge is not clearly discernible, estimating the object’s contour may yield substantial shift along the boundary due to noise or segmentation drawbacks. An appropriate smoothing is therefore required to reduce these effects. In this paper, an approach based on local adaptive threshold segmentation to extract contour and a new smoothing approach founded on Fourier descriptors are introduced. The experimental results of extraction obtained from a set of mammograms and compared with the breast regions delineated by radiologists yielded a percent overlap area of 98.7% ± 0.9% with false positive and negative rates of 0.36 ± 0.74 and 0.93 ± 0.44 respectively. The proposed method was tested on a set of images and improved the accuracy, leading to an average error of less than one pixel.

Facial Expression Recognition Based on Local Fourier Coefficients and Facial Fourier Descriptors

The recent boom of mass media communication (such as social media and mobiles) has boosted more applications of automatic facial expression recognition (FER). Thus, human facial expressions have to be encoded and recognized through digital devices. However, this process has to be done under recurrent problems of image illumination changes and partial occlusions. Therefore, in this paper, we propose a fully automated FER system based on Local Fourier Coefficients and Facial Fourier Descriptors. The combined power of appearance and geometric features is used for describing the specific facial regions of eyes-eyebrows, nose and mouth. All based on the attributes of the Fourier Transform and Support Vector Machines. Hence, our proposal overcomes FER problems such as illumination changes, partial occlusion, image rotation, redundancy and dimensionality reduction. Several tests were performed in order to demonstrate the efficiency of our proposal, which were evaluated using three standard databases: CK+, MUG and TFEID. In addition, evaluation results showed that the average recognition rate of each database reaches higher performance than most of the state-of-the-art techniques surveyed in this paper.

Extract the Output Signal Characteristics of DC-DC Converter Based on Fourier Descriptor

The precondition of realizing feedback controlling DC DC converter to avoid chaotic state is to judge the behavior of the converter and take corresponding measures. In this paper, the output signals under different circuit parameters of the PWM buck converter have been analyzed. The method of using Fourier descriptor to extract output signals characteristics is put forward and proved to be a gist of identifying and classifying the behavior of DC DC converter. This method can establish a good foundation fo...

Shape retrieval using multi-level included angle functions-based Fourier descriptor

An effective shape signature namely multi-level included angle functions MIAFs is proposed to describe the hierarchy information ranging from global information to local variations of shape.Invariance to rotation translation and scaling are the intrinsic properties of the MIAFs.For each contour point the multi-level included angles are obtained based on the paired line segments derived from unequal-arc-length partitions of contour.And a Fourier descriptor derived from multi-level included angle functions MIAFD is presented for efficient shape retrieval.The proposed descriptor is evaluated with the standard performance evaluation method on three shape image databases the MPEG-7 database the Kimia-99 database and the Swedish leaf database. The experimental results of shape retrieval indicate that the MIAFD outperforms the existing Fourier descriptors and has low computational complexity.And the comparison of the MIAFD with other shape description methods also shows that the proposed descriptor has the highest precision at the same recall value which verifies its effectiveness.

Modified Fourier descriptor for shape feature extraction

A modified Fourier descriptor was presented. Information from a local space can be used more efficiently. After the boundary pixel set of an object was computed, centroid distance approach was used to compute shape signature in the local space. A pair of shape signature and boundary pixel gray was used as a point in a feature space. Then, Fourier transform was used for composition of point information in the feature space so that the shape features could be computed. It is proved theoretically that the shape features from modified Fourier descriptors are invariant to translation, rotation, scaling, and change of start point. It is also testified by measuring the retrieval performance of the systems that the shape features from modified Fourier oescriptors are more discriminative than those from other Fourier descriptors.

基于傅里叶描述子的手势识别方法

手势识别是计算机视觉人机交互应用领域关键技术,手势轮廓携带有手势重要特征,准确捕获手势轮廓对提高手势识别具有重要意义。针对手掌轮廓特征提取困难和手势识别率低问题,提出了基于傅里叶描述子的手势识别方法,按照候选窗口最大轮廓傅里叶描述子匹配度和置信度分割出手掌区域;跟踪手掌轮廓计算其傅里叶描述子得到手势轮廓特征值;将16个手势轮廓特征值作为BP人工神经网络的输入,利用BP人工神经网络识别手势。实验表明,该方法能有效捕获手势轮廓和识别19种手势,具有识别率高、性能优良和鲁棒性好等优点。

Fourier 描述符的印鉴识别方法

基于手刻或机刻两枚具有相同字符内容的印鉴其字符骨架线的空间分布不可能完全相同，介绍了用匹配字符轮廓线的测度方法，并选用字符的包络线作为匹配的骨架线．提出了基于Ｆｏｕｒｉｅｒ描述符的轮廓匹配的印鉴识别方法，其主要优点是可以在很少约束条件下获取印鉴图象．

一种基于DCT系数和Fourier描述子的人脸识别方法

研究了一种基于人脸细节信息和外形轮廓信息相结合的人脸识别方法.用DCT(离散余弦变换)系数集表示人脸细节信息,傅立叶描述子集表示人脸轮廓信息,用基于相似性的匹配方式将待测人脸的两种信息分别与数据库中的人脸进行匹配,并根据光照条件将两个匹配结果进行合理的融合作为最终的匹配结果.由于人脸外形比较稳定,并且傅立叶描述子对旋转不敏感,最重要的是,在匹配过程中创造性地利用了实时光照信息进行融合,因此,这种方法不仅稳定,还可以较好地弥补传统二维人脸识别系统极易受到光照、姿态等因素影响的这个缺点.

FDTD中近远场变换计算天线方向图的新方法

针对FDTD中时域近远场外推求方向图的方法运算量太大的缺点,提出一种在时域迭代中对等效面上的场进行傅立叶变换,时域迭代完后得到频域场,再进行频域近远场变换求天线方向图的方法。对该方法的消耗额外内存和消耗额外机时(相对于仅算近场而言)进行分析,数值试验表明,该方法的优点是计算量小而且简单。

基于Fourier描述器的汉字字形生成及合成的改进算法

对基于 Fourier描述器的汉字字形生成及合成算法进行了改进 .通过增加重复点和线段细分 ,改善了汉字的重构效果 .提供了汉字笔划顺序调整、笔划起点调整和跟踪方向的一致性处理算法 ,处理后的汉字可完全满足使用

基于FrFT-FD和KPCA模拟电路故障特征提取方法

为获得有效的故障特征信息,提出一种基于分数阶傅里叶变换分形维的模拟电路故障特征提取方法。首先,把原始数据空间中的特征数据映射到不同的分数阶空间,分别计算不同分数阶次下故障响应信号的分形维数;然后,采用核主元分析进一步对候选特征实施降维;最后,将优化后的特征向量作为故障特征,利用神经网络进行分类诊断。仿真结果表明,本方法能很好地获取不同故障响应信号的细微差异,增强不同故障模式的可分性,提高故障诊断准确率。

基于椭圆Fourier描述子的旋转机械振动信号分析

基于椭圆Fourier描述子,对转子同一截面上相互垂直的两个传感器测取的同源振动信号进行融合分析,从理论上推导出滤波轴心轨迹的表达式。研究对比全谱、全息谱和矢谱,建立三种谱分析方法的统一理论框架,给出三种谱分析方法的理论表达式,并设计利用一次快速Fourier变换实现三种谱图的数值方法。在融合全谱、全息谱和矢谱三种谱分析方法的基础上,提出基于椭圆Fourier描述子的矢椭谱分析方法,用于分析转子的同源振动信号。应用对比验证了矢椭谱的简洁可行性。

改进的Fourier-Mellin描述子在图像匹配中的应用

Fourier-Mellin描述子被广泛应用于数字图像匹配中,但由于频谱混叠等噪声及误差的存在,不能保证变化后得到的相关值分布形式是一个标准的二维脉冲函数。本文在此基础上引入带核函数的加权距离公式,先用小波变换在频域中提取出稳定的特征点形成特征向量;然后利用核函数对特征向量进行修正,使之形成标准的二维脉冲函数,以便计算出正确的匹配参数,从而达到两幅图像的匹配。实验结果表明了新算法的有效性和可靠性。

基于多尺度Fourier描述符的二维轮廓曲线匹配

根据破碎物体碎片拼接的需求,提出一种多尺度Fourier描述符的二维曲线匹配方法.利用不同尺度的Gaussian函数对轮廓曲线进行滤波后,以Fourier变换的系数作为曲线的特征矢量,通过比较2条轮廓曲线特征矢量来判断轮廓曲线的相似性,实现曲线匹配和碎片拼接.结果表明该算法具有准确性、鲁棒性和容错性.

基于Fourier描绘子的脑部切片匹配方法

本文提出一种基于Fourier描绘子匹配脑部切片的算法 ,用于汇聚组合来自不同动物的生理数据。首先 ,将大鼠中脑组织切片数字化 ,用三条封闭特征轮廓表示 ,一组大鼠中脑 38张的连续切片被作为与其它任何切片匹配的标准模板。然后 ,将每一切片的轮廓作Fourier展开 ,通过计算两切片对应轮廓的尤拉距离 ,结合三轮廓的权重 ,定义两切片间的“相似函数”。最后 ,根据实验组切片与标准模板切片之间相似函数的大小实现两者的匹配。本算法已成功应用于调幅声敏感听觉细胞功能组织的研究。

计算机图像处理技术在鞋服款式识别中的应用研究

本文旨在探索一种基于鞋服轮廓形状特征的款式识别方法,针对当前研究中存在的主要难点问题,提出了相应的解决方案。在计算机图像处理技术的概念和应用场景的理论基础上,介绍了一种基于边缘检测和形态学操作的鞋服图像预处理算法,该算法能够有效分割出鞋服轮廓,并消除噪声和细节干扰。同时,提出了一种基于傅里叶描述子的轮廓特征提取方法,有效描述鞋服轮廓的形状特征,并利用支持向量机(Support Vector Machine,SVM)进行轮廓特征的分类。