Modified wavelet based morphological correlation for rotation-invariant recognition

A wavelet-based rotation invariant morphological correlation (WBRIMC) is proposed as a new architecture to improve the properties of the classical rotation invariant morphological correlation (RIMC). For the WBRIMC, the JPS of the RIMC is filtered by an appropriately dilated power spectrum function of wavelet. Simulation results confirm that the WBRIMC has higher discrimination capability with sharp and intense correlation signals, and is more tolerant to the salt-and-pepper noise and white additive Gaussian noise than is the Circular harmonic filter (CHF), the phase only CHF (POCHF) and the RIMC.     

Rotation-invariant pattern recognition using morphological phase-only correlation

We present a rotation-invariant nonlinear correlator based on the circular harmonic filter (CHF) and the previously proposed morphological phase-only correlator (MPC) [Q. Wang, S. Liu, Opt. Commun. 244 (2005) 93]. We refer to this correlator as a rotation-invariant MPC (RIMPC). Through computer simulation, we compare the output results of RIMPC with those of rotation-invariant MC (RIMC) and CHF when input scene is corrupted by salt-and-pepper noise, white additive Gaussian noise and cluttered background. Our results show that RIMPC yields higher discriminability, sharper and higher correlation peaks and displays better stability against the above three kinds of noise than do the RIMC and common CHF.     

Wavelet-modified binary phase-only morphological correlation for color pattern recognition

This paper reports a morphological phase-only correlation technique based on bit-map representation for recognition of color as well as grey images in a hybrid digital-optical correlation architecture. The color image is decomposed into its R, G and B components, and each component is further decomposed into eight disjoint elementary images depending upon the bit-map representation of the color value at each pixel. Bit-map representation of the pixel values of an image reduces the required computational time. A set of twenty-four disjoint wavelet-modified binary phase-only filters (WBPOFs) are generated from these bit-map decomposed images. The target image is similarly decomposed into eight disjoint images each of R, G and B and their digital Fourier transforms multiplied with the corresponding WBPOFs. The product functions thus obtained are added up to form a single resultant product function, whose optical Fourier transformation gives the correlation peaks for the presence of R, G and B components in the image. The single product function overcomes the necessity of obtaining the final optical Fourier transformation of the R, G and B components separately. The novelty of this approach lies in the fact that the WBPOFs synthesized by this procedure are thus able to identify both colored as well as gray images and can tolerate salt-and-pepper noise to a considerable extent.     

Rotation-invariant pattern recognition using morphological fringe-adjusted joint transform correlation

We propose a rotation-invariant nonlinear correlator based on circular harmonic filter (CHF) and morphological Fringe-adjusted Joint Transform correlation (MFJTC). We refer to this correlator as a rotation-invariant MFJTC (RIMFJTC). Through computer simulation, we compare the output results of RIMFJTC with those of rotation-invariant MC (RIMC) and CHF when input scene is corrupted by salt-and-pepper noise, white additive Gaussian noise and cluttered background. Our results show that RIMFJTC yields higher discriminability, sharper and higher correlation peaks, and displays better stability against the above three kinds of noise than do the RIMC and common CHF.     

Shift- and scale-invariant pattern recognition using morphological phase-only correlation

We propose a non-linear correlation to realize scale-invariant recognition, called shift- and scale-invariant morphological phase-only correlation (SSIMPC), which is a combination of radial harmonic filter (RHF) and morphological phase-only correlation (MPC). We form SSIMPC using phase-only RHFs (PORHF) instead of common RHFs in every sub-correlations of morphological radial harmonic correlation (MRHC). Computer simulation results demonstrate that the performance of SSIMPC is better than that of MRHC in discrimination and robustness against non-Gaussian noise, such as salt-and-pepper noise and cluttered background, and above of all, SSIMOC realizes approximately full scale-invariance. In addition, we devise an optoelectronic scheme, which is identical to the setup for MPC, to implement SSIMPC.     

Shift- and scale-invariant pattern recognition using morphological fringe-adjusted joint transform correlation

A shift- and scale-invariant version of morphological fringe-adjusted joint transform correlation (MFJTC) is proposed in this paper, which we call shift- and scale-invariant MFJTC (SIMFJTC). SIMFJTC is combination of MFJTC and conventional radial harmonic filter (RHF). Using computer simulation, we compare the output results of SIMFJTC with those of morphological radial harmonic correlation (MRHC) and SDF-based FPFJTC when input scene is corrupted by salt-and-pepper noise and cluttered background. Our results show that SIMFJTC has higher discriminability and displays better stability against salt-and-pepper noise and cluttered background. Moreover, scale-invariance of SIMFJTC is much stricter than MRHC and SDF-based FPFJTC.     

Existence problem of optical correlation based pattern recognition

The existence problem of optical correlation based pattern recognition, namely its range of validity and its limitation, is discussed in this paper conjointly with the function approximation theory of neural networks. The conclusion is that only if the sets to be recognized are linearly separable (which is rare) or the subsets, in which a segmental sample of the targets is involved, are linearly separable, can the classical 4f optical correlation system carry out the task of recognition inerrably. The recognition principle of a joint transform correlator is the same as that of a 4f system, and so is its range of validities. Based on the demonstration of the existence problem of optical correlation based pattern recognition an evaluation on some important problems that were studied in this field over the past 40 years is presented explicitly.     

A multi-resolution wavelet algorithm for hand vein pattern recognition

A novel hand vein recognition algorithm is developed based on multi-resolution wavelet analysis. The texture feature of hand vein can be extracted by three-level wavelet decomposition. Furthermore, Knearest neighbor (KNN) with support vector machines (SVM) and minimum distance classifier (MDC) are employed for feature matching. Finally, the experiments are respectively performed in identification and verification modes using Tianjin University (TJU) hand vein image database constructed by our group.The results show the feasibility and effectiveness of the proposed method.     

Rotational-InVariant pattern recognition using circular optical wavelet transform

An improved shift- and rotational-invariant filter using wavelet transform and circular harmonic filtering at the same time is proposed. Computer simulation has shown that this is better than using a phase-only circular harmonic filter in peak sharpness, discriminating ability, SNR and tolerance of position error of the filter. Furthermore, this filter possesses moderate diffraction efficiency.     

A new method for optical pattern recognition by correlation measurements

The method of computing correlation functions using a coherent optical analogue computer is well known. In this letter we describe a new method for the recognition of binary patterns. Usually the peak of maximum intensity in the correlation plane is taken as a “measure of similarity”. Instead of this “measure of similarity” we introduce a “measure of distance”. By the method proposed here the pattern to be recognized is detected by a zero in the intensity distribution in the correlation plane.     

Design of correlation filters for pattern recognition using a noisy reference

We present the design of correlation filters for detection of a target in a noisy input scene when the object of interest is given in a noisy reference image. The target signal, shape and location in the reference image are assumed to be unknown. Two signal models are considered for the input scene: additive and nonoverlapping. The design of the filters consists of automated estimation of needed parameters from a noisy reference image and maximization of the peak-to-output energy ratio criterion. Two filter variants are proposed. The matching error metric is used to determine the regions of the parameter space where each filter variant performs better. Computer simulation results obtained with the proposed filters are presented and evaluated in terms of discrimination capability, location errors, and tolerance to input noise.     

Distortion-invariant pattern recognition using synthetic discriminant function based multiple phase-shifted-reference fringe-adjusted joint transform correlation

This paper proposes a novel pattern recognition system for invariance to noise and distortions. The technique first generates a synthetic discriminant function of the target image from its different distorted versions. It then takes four different phase-shifted versions of the reference image, which are individually joint transform correlated with the given input scene. Thus the proposed algorithm produces a single cross-correlation signal corresponding to each potential target. Also a fringe-adjusted filter is designed to generate a delta-like correlation peak with high discrimination between the signal and the noise. The pattern recognition system is also designed for the identification of multiple targets belonging to multiple reference objects simultaneously in a given input scene. The proposed technique is investigated using computer simulation including real-life images in different complex environments.     

基于小波不变矩的多类目标特征选择算法

特征选择是目标识别中的重要问题。对于有着3个参数（m,n,q）的小波矩来说更是如此。基于2类模式的特征选择思想,提出多类模式下绝对可分的特征选择算法,给出图像数值化处理中参数(m,n,q)的合理取值范围。实验结果表明：无论是对差别比较大、差别比较小还是混合型的多类目标,经过此特征提取出来的小波矩都有着较好的识别效果。     

基于提升小波和FLD的人脸表情识别

提出一种基于提升小波和Fisher线性判别法(FLD)相结合的人脸表情特征提取方法。提升小波是完全基于时空域的变换,具有多分辨率的特征,更有利于表情细节信息的提取,并且运算时间短,便于实现。图像经过提升小波变换后,取其低频分量和高频分量相结合作为整体特征,实验证明保存了绝大部分的表情分量,然后用Fisher线性判别法(FLD)进行特征提取,采用K-近邻法进行分类。在JAFFE数据库中,分辨率达到94.3%,识别时间为2.9s,证明了方法的有效性。     

Target recognition in clutter scene based on wavelet transform

Edge extraction based on wavelet for optical correlation detection is presented. Optical experiments with joint transform correlator (JTC) show that there is a bright application prospect in the field of optical correlation detection by extracting the edge features of input image with the method of wavelet transform. In the course of processing, the multi-scale character of wavelet is used sufficiently. The energy of correlation peaks and the detection ratio of various targets are greatly enhanced by the approach. To demonstrate the feasibility of edges extraction based on WT, small targets and targets in clutter scene are successfully detected.     

基于图像模式识别技术的牛顿环检测

利用图像模式识别技术对牛顿环条纹进行自动识别，不仅速度快、精度高，而且克服了通过移测显微镜判读条纹而引起的视差．     

Simulation and experiment research of face recognition with modified multi-method morphological correlation algorithm

Morphological definition of similarity degree of gray-scale image and general definition of morphological correlation (GMC) are proposed. Hardware and software design for a compact joint transform correlator are presented in order to implement GMC. Two kinds of modified general morphological correlation algorithm are proposed. The gray-scale image is decomposed into a set of binary image slices in certain decomposition method. In the first algorithm, the edge of each binary joint image slice is detected, width adjustability of which is investigated, and the joint power spectrum of the edge is summed. In the second algorithm, the joint power spectrum of each pair is binarized or thinned and then summed in one situation, and the summation of the joint power spectrums of these pairs is binarized or thinned in the other situation. Computer-simulation results and real face image recognition results indicate that the modified algorithm can improve the discrimination capabilities with respect to the gray-scale face images of high similarity.     

Wavelet-based morphological correlation

A wavelet-based morphological correlation (WBMC) is proposed as a new architecture to improve the properties of the classical morphological correlation (MC). For the WBMC, a dilated wavelet intensity function is introduced to filter the joint power spectrum (JPS) of the MC before final inverse Fourier transform. Computer simulation results show that, as compared with the linear correlation (LC), the conventional MC and the joint wavelet transform correlation (JWTC), the WBMC provides better discrimination capability with sharp and unmistakable correlation signal and its performance metrics are more stable under input outlier noise (salt-and-pepper noise). Although the WBMC loses illumination-invariance when input illumination factor is larger than unity, considerable discrimination capability is still maintained.     

基于小波变换的新型数字散斑相关方法

通过将小波分析的方法应用到传统的空域相关计算中,提出了基于小波变换的数字散斑相关方法。详细介绍了该方法的原理,并对传统空域相关方法与小波相关方法进行了实验计算比较。实验结果表明,与传统的空域相关方法相比,基于小波变换的数字散斑相关方法大大提高了相关计算的精度,精度由0 05像素提高到了0 01像素以下。最后利用该方法测量了编织结构复合材料板在三点弯曲载荷作用下的位移场。     

基于Gabor小波纹理特征的目标识别新方法

给出了一种基于Gabor小波纹理特征的目标识别新方法．主要是利用Gabor小波设计了一种多通道小波滤波器。对图像目标直接进行小波变换，用Gabor小波变换系数的模的平均值和其标准方差来表示抽取的图像目标的特征，把获得的小波特征归一化后输入到改进的BP神经网络分类器进行分类识别．最后。进行了一系列的仿真实验，结果表明，这种特征提取方法能有效提取图像目标纹理特征，并且对噪音和形状的变化具有鲁棒性．在应用于目标识别时，神经网络的训练时间减少到lOmin，识别率达到94％．