Feature Compensation Combining SNR‐Dependent Feature Reconstruction and Class Histogram Equalization

In this letter, we propose a new histogram equalization technique for feature compensation in speech recognition under noisy environments. The proposed approach combines a signal‐to‐noise‐ratio–dependent feature reconstruction method and the class histogram equalization technique to effectively reduce the acoustic mismatch present in noisy speech features. Experimental results from the Aurora 2 task confirm the superiority of the proposed approach for acoustic feature compensation.     

采用特征分类直方图均衡化的鲁棒性语音识别

大部分噪声会引起语音倒谱域特征参数的非线性失真,导致识别系统性能下降。直方图均衡化方法是一种非线性补偿变换技术,较传统的基于线性变换技术的抗噪声方法进一步提高了系统的鲁棒性。但实际识别系统中,除了噪声引起语音特征的非线性失真外,还存在训练和测试数据的语音特征类分布不一致问题,从而难以保证传统的直方图均衡化方法发挥其优势。本文提出一种基于特征分类的直方图均衡化方法,首先对初步均衡化后的含噪语音特征矢量进行K均值分类,然后对各类别下的特征矢量再进行直方图均衡变换。实验结果表明,低信噪比时无论在平稳噪声还是非平稳噪声环境下,与传统的直方图均衡化方法相比都进一步增强了识别系统的鲁棒性。      

Contrast enhancement using feature-preserving bi-histogram equalization

A new contrast enhancement algorithm is proposed, which is based on the fact that, for conventional histogram equalization, a uniform input histogram produces an equalized output histogram. Hence before applying histogram equalization, we modify the input histogram in such a way that it is close to a uniform histogram as well as the original one. Thus, the proposed method can improve the contrast while preserving original image features. The main steps of the new algorithm are adaptive gamma transform, exposure-based histogram splitting, and histogram addition. The object of gamma transform is to restrain histogram spikes to avoid over-enhancement and noise artifacts effect. Histogram splitting is for preserving mean brightness, and histogram addition is used to control histogram pits. Extensive experiments are conducted on 300 test images. The results are evaluated subjectively as well as by DE, PSNR EBCM, GMSD, and MCSD metrics, on which, except for the PSNR, the proposed algorithm has some improvements of 2.89, 9.83, 28.32, and 26.38% over the second best ESIHE algorithm, respectively. That is to say, the overall image quality is better.     

Isolated Mandarin syllable recognition using segmental features

A segment-based speech recognition scheme is proposed. The basic idea is to model explicitly the correlation among successive frames of speech signals by using features representing contours of spectral parameters. The speech signal of an utterance is regarded as a template formed by directly concatenating a sequence of acoustic segments. Each constituent acoustic segment is of variable length in nature and represented by a fixed dimensional feature vector formed by coefficients of discrete orthonormal polynomial expansions for approximating its spectral parameter contours. In the training, an automatic algorithm is proposed to generate several segment-based reference templates for each syllable class. In the testing, a frame-based dynamic programming procedure is employed to calculate the matching score of comparing the test utterance with each reference template. Performance of the proposed scheme was examined by simulations on multi-speaker speech recognition for 408 highly confusing isolated Mandarin base-syllables. A recognition rate of 81.1% was achieved for the case using 5-segment, 8-reference template models with cepstral and delta-cepstral coefficients as the recognition features. It is 4.5% higher than that of a well-modelled 12-state, 5-mixture CHMM method using cepstral, delta cepstral, and delta-delta cepstral coefficients     

基于改进直方图均衡的红外图像对比度增强算法

针对红外图像灰度分布集中、对比度低的特征,提出了一种基于改进直方图均衡的对比度增强算法。首先采用线性对比度增强将原始16位红外图像映射到8位图像A;然后采用改进的平台直方图均衡将原始16位红外图像映射到8位图像B;再根据输入图像的灰度级范围动态确定映射图像A和B的权值;最后以确定的权值将映射图像A和B合并,得到最终对比度增强的图像。该方法克服了传统平台直方图均衡算法噪声过大及亮度突变的缺点,动态结合了传统的灰度变换增强算法,能根据全图目标与背景灰度的分布情况自适应调整对比度。实验表明,该算法在增强目标对比度的同时有效保留了图像的整体信息,改善了视觉效果。     

基于双直方图均衡算法的红外图像增强

为了抑制全局直方图均衡产生的灰度饱和和局部细节丢失的情况,提出了一种双直方图均衡算法。首先对图像的背景和前景进行分割,提出基于直方图的局部最小值和修正的K-Means聚类算法来确定图像的理想分割阈值,然后再对分割的子图分别作全局直方图均衡（Global Histogram Equalization,GHE）。对该算法进行了实验验证,结果表明,相较于GHE算法,经该算法增强后的图像峰值信噪比（Peak Signal to Noise Ratio,PSNR）提高约16.425%,结构相似度（Structural Similarity Index,SSIM）提高约14.85%。同时通过主观分析,基于直方图局部最小值和修正的K-Means聚类算法的图像分割进行双直方图均衡可以有效抑制GHE算法产生的灰度饱和和细节丢失现象。     

Modified Mean and Variance Normalization: Transforming to Utterance-Specific Estimates

Cepstral mean and variance normalization (CMVN) is an efficient noise compensation technique popularly used in many speech applications. CMVN eliminates the mismatch between training and test utterances by transforming them to zero mean and unit variance. In this work, we argue that some amount of useful information is lost during normalization as every utterance is forced to have the same first- and second-order statistics, i.e., zero mean and unit variance. We propose to modify CMVN methodology to retain the useful information and yet compensate for noise. The proposed normalization approach transforms every test utterance to utterance-specific clean mean (i.e., utterance mean if the noise was absent) and clean variance, instead of zero mean and unit variance. We derive expressions to estimate the clean mean and variance from a noisy utterance. The proposed normalization is effective in the recognizing voice commands that are typically short (single words or short phrases), where more advanced methods [such as histogram equalization (HEQ)] are not effective. Recognition results show a relative improvement (RI) of \(21\,\%\) in word error rate over conventional CMVN on the Aurora-2 database and a RI of 20 and \(11\,\%\) over CMVN and HEQ on short utterances of the Aurora-2 database.     

3-D color histogram equalization by principal component analysis

Color histogram equalization is a method for improving visual appearance of images by enhancing image contrast. Color histogram equalization methods are mostly faced with problems like over-enhancement and brightening. In this paper a new color histogram equalization method is proposed which defines a new three dimensional cumulative distribution function based on a one-dimensional histogram. This one-dimensional histogram is calculated by taking into account the correlation between color channels using PCA. Over-enhancement and brightening are solved by this method because of applying the equalization on a transformed image instead of image itself.     

基于直方图均衡化的红外图像伪彩色增强显示

红外成像技术由于具有抗干扰性强和全天候工作等特点而被广泛应用于各个领域.针对红外图像视觉效果模糊的问题,提出了一种基于直方图均衡化的红外图像伪彩色增强显示方法.该方法包括图像增强和伪彩色处理两步：首先,计算图像的均值,并根据均值的大小采用不同的空域变换方法,然后进行直方图均衡化处理;在伪彩色处理中,设计了新的伪彩色编码表,并采用查找表的方式对增强后的图像进行了伪彩色处理与显示.试验结果表明,经过伪彩色增强处理后,图像的显示效果有了明显提高,图像中的动态范围得到了扩大,细节信息也得到了加强.     

Automatic Contrast Enhancement by Transfer Function Modification

In this study, we propose an automatic contrast enhancement method based on transfer function modification (TFM) by histogram equalization. Previous histogram‐based global contrast enhancement techniques employ histogram modification, whereas we propose a direct TFM technique that considers the mean brightness of an image during contrast enhancement. The mean point shifting method using a transfer function is proposed to preserve the mean brightness of an image. In addition, the linearization of transfer function technique, which has a histogram flattening effect, is designed to reduce visual artifacts. An attenuation factor is automatically determined using the maximum value of the probability density function in an image to control its rate of contrast. A new quantitative measurement method called sparsity of a histogram is proposed to obtain a better objective comparison relative to previous global contrast enhancement methods. According to our experimental results, we demonstrated the performance of our proposed method based on generalized measures and the newly proposed measurement.     

基于直方图均衡化的景象匹配导航方法研究

针对基准图与实时图之间灰度分布差异对匹配结果的影响,将直方图调整与灰度相关算法相结合,提出了一种基于直方图均衡化预处理的景象匹配导航方法.首先对基准图与实时图的直方图进行调整,减少二者的灰度分布差异,然后采用积相关算法计算匹配结果.分析了景象匹配主要验证方法的优缺点,提出了一种实用的验证方法.利用该验证方法,在各种干扰...     

Filtering of Filter‐Bank Energies for Robust Speech Recognition

We propose a novel feature processing technique which can provide a cepstral liftering effect in the log‐spectral domain. Cepstral liftering aims at the equalization of variance of cepstral coefficients for the distance‐based speech recognizer, and as a result, provides the robustness for additive noise and speaker variability. However, in the popular hidden Markov model based framework, cepstral liftering has no effect in recognition performance. We derive a filtering method in log‐spectral domain corresponding to the cepstral liftering. The proposed method performs a high‐pass filtering based on the decorrelation of filter‐bank energies. We show that in noisy speech recognition, the proposed method reduces the error rate by 52.7% to conventional feature.     

基于超声测井图像的动态直方图均衡算法研究

超声测井图像低亮度低对比度区域的图像,采用常规直方图均衡算法进行图像增强无法很好的突出局部细节。为了解决这个问题,提出一种动态直方图均衡的图像算法对测井图像进行增强的算法。该算法的直方图是根据被均衡图像数据所在井段位置上下一个局部范围内进行统计,从而保证对每个深度的图像都尽可能均衡到最佳。实验结果证明,该算法较常规直方图均衡算法能更好的局部增强实际测井图像,对测井资料的处理具有很重要实际意义。     

Reconstruction of chaotic signals with application to channel equalization in chaos‐based communication systems

A number of schemes have been proposed for communication using chaos over the past years. Regardless of the exact modulation method used, the transmitted signal must go through a physical channel which undesirably introduces distortion to the signal and adds noise to it. The problem is particularly serious when coherent‐based demodulation is used because the necessary process of chaos synchronization is difficult to implement in practice. This paper addresses the channel distortion problem and proposes a technique for channel equalization in chaos‐based communication systems. The proposed equalization is realized by a modified recurrent neural network (RNN) incorporating a specific training (equalizing) algorithm. Computer simulations are used to demonstrate the performance of the proposed equalizer in chaos‐based communication systems. The Hénon map and Chua's circuit are used to generate chaotic signals. It is shown that the proposed RNN‐based equalizer outperforms conventional equalizers as well as those based on feedforward neural networks for noisy, distorted linear and non‐linear channels. Copyright © 2004 John Wiley & Sons, Ltd.     

Combining Modified LBP and Weighted SRC for Palmprint Recognition

In order to extract invariant features in the palmprint transformation of scale, rotation and affine distortion, a coarse-to-fine palmprint recognition method is proposed by combining the weighted adaptive center symmetric local binary pattern (WACS-LBP) and weighted sparse representation based classification (WSRC). The method consists of coarse and fine stages. In the coarse stage, using the similarity between the test sample and one sample of each training class, most of the training classes could be excluded and a small number of candidate classes of the test sample are reserved. Thus, the original classification problem becomes clear and simple. In the fine stage, the robust rotation invariant weighted histogram feature vector is extracted from each candidate sample and the test sample by WACS-LBP, and the weighted sparse representation optimal problem is constructed by the similarity between the test sample and each candidate training sample, and the test sample is recognized by the minimum residual. The proposed method is tested and compared with the existing algorithms on the PolyU and CASIA database. The experimental results illustrate better performance and rationale interpretation of the proposed method.     

基于生成对抗网络联合训练的语音分离方法

基于深度神经网络的语音分离方法大都在频域上进行训练，并且在训练过程中往往只关注目标语音特征，不考虑干扰语音特征。为此，提出了一种基于生成对抗网络联合训练的语音分离方法。该方法以时域波形作为网络输入，保留了信号时延导致的相位信息。同时，利用对抗机制，使生成模型和判别模型分别训练目标语音和干扰语音的特征，提高了语音分离的有效性。实验中，采用Aishell数据集进行对比测试。结果表明，本文所提方法在三种信噪比条件下都有良好的分离效果，能更好地恢复出目标语音中的高频频段信息。      

基于AR-HMM在线能量调整的语音增强方法

针对单通道语音增强技术对非平稳噪声的跟踪不准确、噪声抑制效果较差的问题,本文提出一种基于在线能量调整的语音增强方法.该方法以归一化临界带能量为特征,采用高斯混合模型对背景噪声进行分类,利用对应类型噪声的自回归隐马尔可夫模型(Auto-Regressive Hidden Markov Model,AR-HMM)和纯净语音的AR-HMM,在最小均方误差准则下估计语音和噪声的功率谱.考虑到非平稳环境中训练集和测试集的差异性,需在线调整语音模型和噪声模型中的能量,语音模型的能量调整采用迭代的期望最大化算法;噪声模型的能量调整则利用的是模型训练过程中的能量重估方法,并以最小值控制的递归平均算法确定噪声能量调整的初始值.在ITU-T G.160标准下对算法进行性能测试,测试结果表明,本文方法对非平稳噪声的跟踪效果较好,对噪声衰减量较大,收敛时间较短.     

一种基于距离变换和遗传算法的遥感图像区配算法

该文提出了一种基于距离变换和遗传算法的遥感图像匹配算法。先对参考图像和目标图像进行直方图处理,以克服不同光照条件下带来的匹配误差,在此基础上对参考图像和目标图像进行距离变换。最后利用遗传算法对距离变换后的图像进行匹配操作。实验结果表明,该算法不仅能满足一定的匹配精度,而且具有较高的匹配效率。     

Histogram equalization and optimal profile compression based approach for colour image enhancement

Many vision based applications depend on images with sufficiently high contrast and colourfulness so that ample amount of information is available to accurately describe objects captured in an image scene. Poor image capturing conditions are often unavoidable but can be compensated. Approaches based on intensity histogram equalization are popular to increase the information content within an image but over-enhancement often results in the production of unwanted artefacts. Furthermore, when constrained to only an intensity-based enhancement, insufficient enrichment on colourfulness and saturation is often observed. In order to address these limitations concurrently, a pipelined approach that incorporates a colour channel stretching process, a histogram equalization step, a magnitude compression procedure, and a saturation maximization stage is proposed. Quantitative and qualitative results obtained from experiments on a wide variety of natural scene images demonstrate the effectiveness of the proposed approach over other methods at reducing artefact while increasing image contrast and colourfulness.