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.     

使用振幅调制和功率谱相减的联合变换相关器作多目标检测

提出一种使用振幅调制和功率谱相减的联合变换相关器作多目标检测，这一方法对联合功率谱作了修正，先将联合功率谱减去纯输入景物的功率谱和参考图象的功率谱，再将所得修正的联合功率谱乘以振幅调制滤波函数。分析和量化了输入景物噪声对联合变换相关器性能的影响。这种方法比条纹调节的联合变换相关器和修正的条纹调节的联合变换相关器能产生更好的相关输出和适应输入景物噪声的能力。     

Binary phase only filters for rotation and scale invariant pattern recognition with the joint transform correlator

The joint transform correlator (JTC) is one of the two main optical image processing architecture which provides a highly effective way of comparing images in a wide range of applications. Traditionally, an optical correlator is used to compare an unknown input scene with a pre-captured reference image library, to detect if the reference occurs within the input. Strength of the correlation signal decreases rapidly as the input object rotates or varies in scale relative to the reference object. The aim of this paper is to overcome the intolerance of the JTC to rotation and scale changes in the target image. Many JTC systems are constructed with the use of ferroelectric liquid crystal (FLC) spatial light modulators (SLMs) as they provide fast two-dimensional binary modulation of coherent light. Due to the binary nature of the FLC SLMs used in the JTC systems, any image addressed to the device need to have some form of thresholding. Carefully thresholding the grey scale input plane and the joint power spectrum (JPS) has significant effect on the quality of correlation peaks and zero order (DC) noise. A new thresholding technique to binarise the JPS has been developed and implemented optically. This algorithm selectively enhances the desirable fringes in the JPS which provide correlation peaks of higher intensity. Zero order noise is further reduced when compared to existing thresholding techniques.Keeping in mind the architecture of the JTC and limitations of FLC SLMs, a new technique to design rotation and scale invariant binary phase only filters for the JTC architecture is presented. Filers design with this technique have limited dynamic range, higher discriminability among target and non-target objects, and convenience for implementation on FLC SLMs. Simulation and experiments shows excellent results of various rotation and scale invariant filters designed with this technique. A rotation invariant filter is needed for various machine vision applications of the JTC. By fixing the distance between camera and input object, the scale sensitivity of the correlator can be avoided. In contrast to the industrial machine vision applications, scale factor is very important factor for the applications of the JTC systems in defence and security. A security system using a scale invariant JTC will be able to detect a target object well in advance and will provide more time to take a decision.     

基于多分辨率双边滤波的红外场景杂波抑制

背景杂波是影响红外搜索跟踪系统探测性能的主要因素,针对这一问题,根据红外场景中目标和背景特性,提出了一种基于多分辨率双边滤波的红外场景杂波抑制新方法.首先采用非下采样轮廓波对红外场景图像进行多尺度、多方向分解,提取红外原始场景图像在不同尺度和方向上的细节特征,然后,根据目标和背景信号子带分布特性之差异,通过应用双边滤波调整分解后的各子带系数,最后重构各子带就可将红外场景中目标信号和背景杂波分离,可有效地将背景杂波剔除掉.将本文提出的方法应用于实际的红外场景,实验结果显示,与经典的二维最小均方误差方法相比较,该方法具有更好的杂波抑制能力.     

Spectral band invariant wavelet-modified MACH filter

Filters synthesized with images of a specific spectral band in general fail to recognize targets in a different spectral band. In this paper, we therefore demonstrate the use of the wavelet-modified maximum average correlation height (WaveMACH) filter for automatic target recognition applications in both the visible and infrared (IR) spectral bands. As any input target appears different when imaged through two different sensors, i.e., a CCD or an IR camera, a WaveMACH filter synthesized using a CCD image shows no correlation with the image of the same target from an IR camera and vice-versa. Hence, separate filters are required to match the input targets from the two sensors. To avoid the synthesis and storage of separate filters, the images from CCD and IR camera are fused using Daubechies wavelet and then the rotation-invariant WaveMACH filter generated with the fused image. In all, 18 WaveMACH filters (each of 20° range) are required for in-plane rotation invariance in both the spectral bands for the full range of 0–360°. Computer simulation and experimental results implemented in hybrid digital–optical correlator architecture are shown for the proposed idea. The same filters have also been used to identify multiple targets in a scene. Performance measures like peak-to-sidelobe ratio (PSR), peak correlation energy (PCE) and correlation peak intensity (CPI) have been calculated as metrics of goodness.     

Extended fractional wavelet joint transform correlator

An extended fractional wavelet joint transform correlator is implemented for real-time target recognition applications. The real-time input scene captured using a charge-coupled device camera along with the reference image is fractional Fourier transformed. The obtained joint power spectrum is multiplied by an appropriately scaled wavelet filter and the resultant function is differentiated. The application of wavelet filter enhances the correlation outputs and differential processing of wavelet-filtered joint power spectrum improves the detection efficiency by reducing the zero-order spectra. Targets with Gaussian and speckle noise have also been used to check the correlation output. The performance metrics: correlation peak intensity, peak-to-correlation energy, peak-to-sidelobe ratio and signal to clutter ratio have been calculated. The experimental results are presented in support of the proposed idea.     

Filter design of composite trade-off filter with support regions to obtain invariant pattern recognition with defocused images

The discrimination capacity (DC) measures the ability of the filter in a pattern recognition problem to discriminate the target against other objects in the input scene. If the input scene is degraded by a defect of focus, then the DC is degraded and the pattern recognition process is worse. In this paper, we present a methodology based in the selection of ring frequency bands and in the design of the trade-off filters taking into account these frequencies to obtain several information channels. The information of all the channels is fused by means of the addition of all the channels and the geometric mean of them. Also individual channel analysis is shown. The influence on the DC and SNR of the added white noise in the input image is presented.     

Indirect target detection method in FLIR image sequences

Due to the complexity of the scene, target detection in forward-looking infrared (FLIR) imagery is a challenging problem, especially for occluded target. The main contribution of this paper is to propose an indirect detection method for improving the recognition probability and effectiveness of target detection method in FLIR image sequences under complex conditions. The proposed method mainly includes four steps: preparation of forward-looking reference image of landmark, extraction of the real-time scene image, template matching and target location, in which some key technologies are proposed, such as perspective transformation used to solve projective problems, position prediction for improving real-time performance, and target location used for identifying the target’s position. Experimental results are shown to demonstrate the robustness and efficiency of proposed method in FLIR image sequences.     

层析三维数字化仪层析图像滤波器的设计及研究

提出一种新型的递归中值滤波器，抛掉了统计参数的制约，将滤波算法转化为一种优化处理。该方法兼顾了滤波处理的光滑连续性及抑制噪声的累积特性，可有效地消除脉冲型干扰的影响，同时也从理论的角度上对该算法进行了分析。为消除加性高斯噪声，提出了一种基于图像边缘方向的小波线性滤波器，它仅仅处理边缘信息。该算汉的极大优点是克服了边缘模糊效应，小波的去噪逆向重构的处理方法对边缘为跃型的层析图象非常实用。     

修正振幅调制的光电混合圆谐联合变换相关器作旋转不变的目标检测

提出一种修正振幅调制的光电混合圆谐联合变换相关器作旋转不变的目标检测的实验系统。参考图像（即圆谐展开分量的实部和虚部）、圆盘状的局部偏置函数以及目标图像同时显示于输入面。此方法对联合功率谱作了修正,先将联合功率谱减去纯输入景物（含局部偏置函数）的功率谱和参考图像（含局部偏置函数）的功率谱,再加上局部偏置函数的功率谱,然后将所得修正的联合功率谱乘以振幅调制滤波函数。这种方法能产生比普通的圆谐联合变换     

Complementary-reference and complementary-scene for real-time fingerprint verification using joint transform correlator

In this paper, a new configuration for the input joint images in the joint transform correlator is proposed for fast real-time binary characters and fingerprints verification. In the proposed scheme, the input joint image has a complementary-reference image and a complementary target image in addition to the reference and the target images. We use the cross-correlation peak value between the reference and the complementary target image and the cross-correlation peak value between the complementary reference and the target images as the criteria to perform the recognition of the target in the input scene. It is shown that these two cross-correlation peak values will be zero if and only if the input target matches the reference image. One advantage of using the proposed scheme is the elimination of the usual and necessary time-consuming normalization of the input images in the general correlation-based matching processes. Another advantage of the proposed scheme is the insensitive to light-sources intensity fluctuations that usually limits the matched-based recognition approaches. The scheme is employed to verify binary characters and fingerprints images; further, it is employed to verify occluded fingerprints target images on one hand, and to determine if a specific part or pattern exists in the target fingerprint image on the other hand.     

非重叠背景噪声下的自适应维纳滤波模式识别方法

维纳滤波实现模式识别的关键问题是噪声知识的获得与估计。提出一种非重叠背景噪声的提取方法,首先将对噪声的粗略估计代入维纳滤波函数,得到相关峰。然后由相关峰的位置及参考图像的尺寸确定目标图像的位置和范围,从而提取出背景噪声图像。经过二次维纳滤波,得到改善的相关输出结果,实现了自适应过程。仿真结果表明在非重叠有色噪声环境下,与噪声估计法以及传统的维纳滤波方法相比,此方案具有较好的识别效果。     

Rician noise reduction in magnetic resonance images using adaptive non-local mean and guided image filtering

This paper proposes a Rician noise reduction method for magnetic resonance (MR) images. The proposed method is based on adaptive non-local mean and guided image filtering techniques. In the first phase, a guidance image is obtained from the noisy image through an adaptive non-local mean filter. Sobel operators are applied to compute the strength of edges which is further used to control the spread of the kernel in non-local mean filtering. In the second phase, the noisy and the guidance images are provided to the guided image filter as input to restore the noise-free image. The improved performance of the proposed method is investigated using the simulated and real data sets of MR images. Its performance is also compared with the previously proposed state-of-the art methods. Comparative analysis demonstrates the superiority of the proposed scheme over the existing approaches.     

多通道光谱采集系统滤光片设计方法研究

普通彩色相机加载宽带滤光片构造的多通道光谱采集系统的光谱重建性能与滤光片的选用密切相关。针对上述问题,提出基于主成分分析法的合成滤光片设计方法,旨在获得具有较高光谱重建性能并对所有图像场景均适用的最优滤光片组合。在收集多个宽带滤光片的基础上,测得其透射率并转换成矩阵形式;采用主成分分析方法提取该矩阵的前2个主成分,标准化处理后的主成分即为所求合成滤光片的透射率。为了验证上述方法获得的滤光片的性能,利用色差和光谱均方根误差2个指标对加载了合成滤光片的仿真采集系统的光谱重建精度进行了评价。实验结果表明:采用该方法得到的滤光片组合优于常用方法得到的滤光片组合, 用其构造的成像系统具有较高的色度重建精度和光谱重建精度,此外,改变目标场景颜色特性,其重建性能保持稳定。     

基于干扰对消的红外焦平面非均匀性校正算法

红外焦平面器件的非均匀性产生机理复杂,难以准确拟合探测元响应曲线。提出了一种基于相关干扰抵消的非均匀性校正算法,以预先采集到的一帧黑体面源图像做为自适应干扰对消器的参考输入图像,自适应滤波器由参考输入图像迭代计算出待校正红外图像的空间噪声的最佳估计,实现从空间噪声中提取真实图像信号。自适应滤波算法采用变步长最小均方误差算法,减少了算法的运算量,提高了算法的收敛速度。理论分析以及针对实际红外图像的仿真结果表明,提出的算法校正效果好,收敛速度快,更易于工程实现。     

Time-domain noise reduction based on an orthogonal decomposition for desired signal extraction

This paper addresses the problem of noise reduction in the time domain where the clean speech sample at every time instant is estimated by filtering a vector of the noisy speech signal. Such a clean speech estimate consists of both the filtered speech and residual noise (filtered noise) as the noisy vector is the sum of the clean speech and noise vectors. Traditionally, the filtered speech is treated as the desired signal after noise reduction. This paper proposes to decompose the clean speech vector into two orthogonal components: one is correlated and the other is uncorrelated with the current clean speech sample. While the correlated component helps estimate the clean speech, it is shown that the uncorrelated component interferes with the estimation, just as the additive noise. Based on this orthogonal decomposition, the paper presents a way to define the error signal and cost functions and addresses the issue of how to design different optimal noise reduction filters by optimizing these cost functions. Specifically, it discusses how to design the maximum SNR filter, the Wiener filter, the minimum variance distortionless response (MVDR) filter, the tradeoff filter, and the linearly constrained minimum variance (LCMV) filter. It demonstrates that the maximum SNR, Wiener, MVDR, and tradeoff filters are identical up to a scaling factor. It also shows from the orthogonal decomposition that many performance measures can be defined, which seem to be more appropriate than the traditional ones for the evaluation of the noise reduction filters.     

光子计数激光雷达的时间相关卡尔曼深度估计

在高背景噪声和低积分时间的激光雷达远距离成像场景中,针对传统方法得到的深度图像目标被噪声淹没和深度估计偏差较大的问题,提出了一种基于信号光子时间相关性和自适应卡尔曼滤波器的深度信息估计方法。首先,提取在时间上具有聚集特征的光子计数形成集合;然后,分析了影响信号光子在时间上分布的因素并使用静态高斯线性模型来描述该集合;最后将集合中的所有光子飞行时间乱序,输入改进的自适应卡尔曼滤波器,从而迭代估计深度值。在信号噪声比为1的室内,积分时间分别为10 ms和1 ms时,本文方法相对传统的最大似然方法在均方根误差指标上提升了40%和38%。在信噪比约为0.135的室外2 km目标成像实验中,在信号光子数分别为100、33和17的情况下,本文方法成像效果都优于传统最大似然估计方法和时间相关光子快速去噪方法,得到的深度图像都更清晰,噪声更低。在高噪声和短积分时间下,本文方法可以被运用于激光雷达远距离成像的深度信息估计和图像恢复中。     

The use of a consumer grade photo camera in optical-digital correlator for pattern recognition and input scene restoration

In this work an optical-digital correlator for pattern recognition and input scene restoration is described. Main features of the described correlator are portability and ability of multi-element input scenes processing. The correlator consists of a consumer grade digital photo camera with a diffractive optical element (DOE) inserted as a correlation filter. Correlation of an input scene with a reference image recorded on the DOE are provided optically and registered by the digital photo camera for further processing. Using obtained correlation signals and DOE’s point spread function (PSF), one can restore the image of the input scene from the image of correlation signals by digital deconvolution algorithms.The construction of the correlator based on the consumer grade digital photo camera is presented. The software procedure that is necessary for images linearization of correlation signals is described. Experimental results on optical correlation are compared with numerical simulation. The results of images restoration from conventionally and specially processed correlation signals are reported. Quantitative estimations of accuracy of correlation signals as well as restored images of the input scene are presented.     

Resolution-enhanced 3D image correlator using computationally reconstructed integral images

In this paper, a novel resolution-enhanced three-dimensional (3D) image correlator using the computationally reconstructed integral images is proposed in order to extract target object’s 3D location data in a scene. Elemental images of the reference and target objects are picked up by lenslet arrays and using these elemental images, reference and target plane images are reconstructed on the output plane by means of a modified computational integral imaging reconstruction technique. Then, through cross-correlations between the reconstructed reference and the target plane images, 3D location data of the target object can be extracted from the correlation outputs. With the purpose of showing the feasibility of the proposed method, some computational and optical experiments on the target objects in space are carried out and the results are presented.     

Comparative study of pattern correlation using Mexican hat and Coiflet wavelet-based filtering

In this work, a numerical study on the pattern correlation using wavelet filters is reported. A comparative study of the correlation using the Mexican hat and Coiflets filters is presented. A Coiflet filter acts not only as a band-pass filter but as a high-pass or low-pass filter. Therefore, unlike the Mexican hat-based filter which acts only as a pass-band filter, the Coiflet-based filters allow selecting horizontal, vertical or diagonals details of the original image. Each one of the original images can be discomposed in an average image and several detail images at different levels of multiresolution. We study the numerical correlation between binary patterns using the Mexican hat filter and the first and second multiresolution level obtained by Coiflet filtering. Additionally, an analysis about the noise immunity for the Mexican hat and Coiflet filters is realized. The results show that Coiflet filters are better to identify special characteristics but perform the worst when they are used with noisy images. On the other side, the Mexican filter presents a better noise immunity but performs the worst when is used to compare special characteristics.