Efficient Image Recognition Technique Using Invariant Moments and Principle Component Analysis

Image recognition is widely used in different application areas such as shape recognition, gesture recognition and eye recognition. In this research, we introduced image recognition using efficient invariant moments and Principle Component Analysis (PCA) for gray and color images using different number of invariant moments. We used twelve moments for each image of gray images and Hu’s seven moments for color images to decrease dimensionality of the problem to 6 PCA’s for gray and 5 PCA’s for color images and hence the recognition time. PCA is then employed to decrease dimensionality of the problem and hence the recognition time and this is our main objective. The PCA is derived from Karhunen-Loeve’s transformation. Given an N-dimensional vector representation of each image, PCA tends to find a K-dimensional subspace whose basis vectors correspond to the maximum variance direction in the original image space. This new subspace is normally lower dimensional (K N). Three known datasets are used. The first set is the known Flower dataset. The second is the Africans dataset, and the third is the Shapes dataset. All these datasets were used by many researchers.

An Invariance Algorithm of Synergetic Pattern Recognition一种协同模式识别不变性算法

提出一种协同模式识别的不变性算法,利用协同模式识别的有势动力学理论,求取测试样本的仿射变换参数。通过原型模式对测试样本的自适应或原型模式对测试样本的同化,由序参量动力学演化过程得到正确的识别模式。此算法避免利用傅立叶等方法进行变换域的处理,而且更符合人的认知过程。仿真实验验证了算法的有效性和鲁棒性。

Blur Image Edge to Enhance Zernike Moments for Object Recognition

Zernike moments (ZMs) are a set of orthogonal moments which have been successfully used in the fields of image processing and pattern recognition. A combination of edge blurring with ZMs computation was introduced. In this study, several kinds of artificial binary stripe images were used to investigate the effects of edge blurring on the absolute mean error of reconstructed image from high-order ZMs. After the blurring process, the reconstruction errors were increased dramatically at edge pixels, but decreased on non-edge pixels. The experimental results demonstrated that 2-pixel blurring approach provided better performance for reducing reconstruction error. Finally, a template matching between two real images was simulated to illustrate the effectiveness of the proposed method.

Offline Handwritten Characters Recognition Using Moments Features and Neural Networks

In this paper we revise the moment theory for pattern recognition designed, to extract patterns from the noisy character datas, and develop unconstrained handwritten. Amazigh character recognition method based upon orthogonal moments and neural networks classifier. We argue that, given the natural flexibility of neural network models and the extent of parallel processing that they allow, our algorithm is a step forward in character recognition. More importantly, following the approach proposed, we apply our system to two different databases, to examine the ability to recognize patterns under noise. We discover overwhelming support for different style of writing. Moreover, this basic conclusion appears to remain valid across different levels of smoothing and insensitive to the nuances of character patterns. Experiments tested the effect of set size on recognition accuracy which can reach 97.46%. The novelty of the proposed method is independence of size, slant, orientation, and translation. The performance of the proposed method is experimentally evaluated and the promising results and findings are presented. Our method is compared to K-NN （k-nearest neighbors） classifier algorithm; results show performances of our method.

Information Moment for Chinese Character Recognition

Moment invariants firstly introduced by M. K Hu in 1962, has some shortcomings. After counting a large number of statistical distribution information of Chinese characters,the authors put forward the concept of information moments and demonstrate its invariance to translation,rotation and scaling.Also they perform the experiment in which information moments compared with moment invaiants for the effects of similar Chinese characters and font recognition.At last they show the recognition rate of 88% by information moments,with 70% by moment inariants.

Practical Issues Concerning Moment Invariants

In this report several practical issues about moment invariants with application to image classification are concerned. A modified formulation for the approximation of the moments of digital images is suggested. Four computational procedures and their corresponding noise performances are studied in detail.

Method to generate training samples for neural network used in target recognition

Training neural network to recognize targets needs a lot of samples.People usually get these samples in a non-systematic way,which can miss or overemphasize some target information.To improve this situation,a new method based on virtual model and invariant moments was proposed to generate training samples.The method was composed of the following steps：use computer and simulation software to build target object＇s virtual model and then simulate the environment,light condition,camera parameter,etc.;rotate the model by spin and nutation of inclination to get the image sequence by virtual camera;preprocess each image and transfer them into binary image;calculate the invariant moments for each image and get a vectors＇ sequence.The vectors＇ sequence which was proved to be complete became the training samples together with the target outputs.The simulated results showed that the proposed method could be used to recognize the real targets and improve the accuracy of target recognition effectively when the sampling interval was short enough and the circumstance simulation was close enough.

A NEW FAST ALGORITHM OF 2-D MOMENT INVARIANT BASED ON PROJECTION

In this paper,we advanced a new fast algorithm of 2-D moment in-variant based on image projection,by means of projection transformation it can com-press the information of a 2-D image into 1-D information.Thus,the amount ofcomputation and data size are decreased greatly and,moreover,the projection trans-formation,which is merely an operation of additions,is easier to be achieved onhardwares.The results of computer simulation proved the correctness and quicknessof our method.

TWO NEW RECOGNITION METHODS FOR SPATIAL PLANAR POLYGONS

Two new recognition methods for the spatial planar POlygon using perspective invariants are presented. The corss-ratio (R c) of a vetex and the co-base area rotio (RA) of a edge in a spatial planar polygon are proposed and used as the invariant primitive of the recognition eigenvector. The second distance error decision rule (SD EDR) estimating the relative error of RA is introduced also too. The mthods could recognize a spatial planar polygon with an arbitrary orientation through only a single perspective view. Experimental examples are gievn.

Centre symmetric quadruple pattern-based illumination invariant measure

A centre symmetric quadruple pattern-based illumination invariant measure(CSQPIM)is proposed to tackle severe illumination variation face recognition.First,the subtraction of the pixel pairs of the centre symmetric quadruple pattern(CSQP)is defined as the CSQPIM unit in the logarithm face local region,which may be positive or negative.The CSQPIM model is obtained by combining the positive and negative CSQPIM units.Then,the CSQPIM model can be used to generate several CSQPIM images by controlling the proportions of positive and negative CSQPIM units.The single CSQPIM image with the saturation function can be used to develop the CSQPIM-face.Multi CSQPIM images employ the extended sparse representation classification(ESRC)as the classifier,which can create the CSQPIM image-based classification(CSQPIMC).Furthermore,the CSQPIM model is integrated with the pre-trained deep learning(PDL)model to construct the CSQPIM-PDL model.Finally,the experimental results on the Extended Yale B,CMU PIE and Driver face databases indicate that the proposed methods are efficient for tackling severe illumination variations.

Image Analysis by Two Types of Franklin-Fourier Moments

In this paper,we first derive two types of transformed Franklin polynomial:substituted and weighted radial Franklin polynomials.Two radial orthogonal moments are proposed based on these two types of polynomials,namely substituted Franklin-Fourier moments and weighted Franklin-Fourier moments(SFFMs and WFFMs),which are orthogonal in polar coordinates.The radial kernel functions of SFFMs and WFFMs are transformed Franklin functions and Franklin functions are composed of a class of complete orthogonal splines function system of degree one.Therefore,it provides the possibility of avoiding calculating high order polynomials,and thus the accurate values of SFFMs and WFFMs can be obtained directly with little computational cost.Theoretical and experimental results show that Franklin functions are not well suited for constructing higher-order moments of SFFMs and WFFMs,but compared with traditional orthogonal moments(e.g.,BFMs,OFMs and ZMs)in polar coordinates,the proposed two types of Franklin-Fourier Moments have better performance respectively in lower-order moments.

Illumination Invariant Recognition of Three-Dimensional Texture in Color Images

In this paper, illumination-affine invariant methods are presented based onaffine moment normalization techniques, Zernike moments, and multiband correlation functions. Themethods are suitable for the illumination invariant recognition of 3D color texture. Complex valuedmoments (i.e., Zernike moments) and affine moment normalization are used in the derivation ofillumination affine invariants where the real valued affine moment invariants fail to provide affineinvariants that are independent of illumination changes. Three different moment normalizationmethods have been used, two of which are based on affine moment normalization technique and thethird is based on reducing the affine transformation to a Euclidian transform. It is shown that fora change of illumination and orientation, the affinely normalized Zernike moment matrices arerelated by a linear transform. Experimental results are obtained in two tests: the first is usedwith textures of outdoor scenes while the second is performed on the well-known CUReT texturedatabase. Both tests show high recognition efficiency of the proposed recognition methods.

离散不变矩算法及其在目标识别中的应用

该文分析了在离散状态下不变矩特征受比例因子变化的影响,提出了一种修正归一化中心矩的方法,保证了不变矩特征具有平移、旋转和比例因子的不变性,并将此用于目标识别,最后通过仿真实验,比较了修正前后的识别率,表明本文采用的方法是行之有效的方法。

基于不变矩特征的沥青路面破损图像识别

提出了一种减少沥青路面破损图像识别计算量的图像分割方法。将路面图像等分为64×64像素的子块图像,并用灰度方差值描述子块图像特征。设计了基于BP神经网络的子块图像模式分类器,利用子块图像模式分类结果所组成的矩阵作为路面破损图像分割结果。并将路面破损图像子块模式矩阵的不变矩作为路面破损图像的整体特征,在此基础上设计了基于全局优化算法的路面破损前馈神经网络分类器。最后进行了路面破损图像识别试验,识别率达到83 3%。

CADCAM开发平台及其发展趋势

基于CADCAM平台的系统开发是一种重要的开发方式,研究平台对CADCAM系统的开发有重要意义.介绍了三种主流CADCAM系统开发平台ACIS,CAS.CADE和PARASOLID,阐述了平台的主要功能、开发接口和数据结构,并分析其各自特色,最后总结了CADCAM平台的发展趋势.

基于EMD-WVD振动谱时频图像SVM识别的内燃机故障诊断

为了充分提取基于内燃机振动信号形成的振动谱时频图像的二维时频信息,实现基于内燃机振动谱时频图像特征自动提取及识别,提出了一种基于EMD-WVD(EMD-Wign-er-Ville Distributions)振动谱时频图像SVM识别的内燃机故障诊断方法。该方法利用二进制小波对振动信号进行预处理,然后利用EMD-Wigner-Ville时频分布生成不同工况下振动信号的时频图像,并通过提取振动信号的EMD-WVD振动谱时频图像的不变矩特征形成诊断特征向量,利用一种基于类识别率排序的二叉树SVM分类器进行模式识别。在BF4L1011F型内燃机上进行了6种不同工况下气门故障模拟试验,诊断结果表明总体诊断正确率为98.57%。

高精度自动贴片机视觉对准系统及其图像处理

阐述了高精度自动贴片机视觉对准系统的构成和原理。介绍了利用模式识别理论和图像的不变矩实现定位标志存在性判断的原理及算法和定位标志对准的原理及相关的图像处理算法,以及其中的点模式匹配算法。试验结果表明,定位标志存在性判断算法可以有效地区分不同的定位标志和判断定位标志是否在视场之内;定位标志对准算法在输入图像旋转、平移、定位标志被部分遮挡时,能精确地得到定位标志的位置偏差。

基于骨架提取的航拍绝缘子图像分步识别方法

在无人机电网巡线的研究中,为提高绝缘子识别的正确率,结合航拍图像和绝缘子串的特点,提出了一种粗细定位相结合的航拍绝缘子图像分步识别方法。利用灰度化和图像增强对绝缘子图像进行预处理,基于形态学算法和连通域思想改进传统最大类间方差(OTSU)阈值分割算法并分割图像背景;提取绝缘子图像骨架,针对绝缘子串骨架为一条近似直线的特点及与其他输电设备(如杆塔等)骨架的差异,通过检测直线进行绝缘子串粗定位;计算粗定位区域不变矩特征,运用由Ada Boost算法训练的分类器进行对粗定位区域遍历识别,实现绝缘子串细定位。实验结果表明,基于骨架提取的绝缘子分步识别方法能够有效地识别出航拍图像中的绝缘子串,与单独利用图像特征和分类算法直接识别绝缘子的方法相比,其表现得更稳定,正确率有显著提高,更适用于无人机电网巡线。

一种新的不变矩特征在图像识别中的应用

分析了在离散状态下比例因子对不变矩特征的影响,构造了一种新的不变矩,使其具有平移、旋转和比例因子的不变性。在仿真实验中,采用新的不变矩对图像进行了识别、识别的成功率为95%;而采用原来的不变矩,识别的成功率仅为70%左右。由此表明本文构造的新不变矩具有一定的利用价值。

灰度图像质心快速算法

对矩因子xpyq 做差分变换为函数F1( ) ,将图像函数f(x ,y)做累进求和变换为函数F2 ( ) 用F1( )和F2 ( )相乘求取质心 由于 0阶和 1阶矩因子中的 p ,q不大于 1,经差分后的F1( )除右端点外 ,其值都为 1,乘 1的运算当然可以不做 ,从而消去了乘法运算 对任意大小和任意级别的灰度图像 ,乘除法运算次数仅为 3次 ,而加法运算次数也有降低 文中算法计算结果精确 。