Implementation of Texture Based Image Retrieval Using M-band Wavelet Transform

Wavelet transform has attracted attention because it is a very useful tool for signal analyzing. As a fundamental characteristic of an image, texture traits play an important role in the human vision system for recognition and interpretation of images. The paper presents an approach to implement texture-based image retrieval using M-band wavelet transform. Firstly the traditional 2-band wavelet is extended to M-band wavelet transform. Then the wavelet moments are computed by M-band wavelet coefficients in the wavelet domain. The set of wavelet moments forms the feature vector related to the texture distribution of each wavelet images. The distances between the feature vectors describe the similarities of different images. The experimental result shows that the M-band wavelet moment features of the images are effective for image indexing. The retrieval method has lower computational complexity, yet it is capable of giving better retrieval performance for a given medical image database.

No-reference image quality assessment based on AdaBoost_BP neural network in wavelet domain

Considering the relatively poor robustness of quality scores for different types of distortion and the lack of mechanism for determining distortion types, a no-reference image quality assessment(NR-IQA) method based on the Ada Boost BP neural network in the wavelet domain(WABNN) is proposed. A 36-dimensional image feature vector is constructed by extracting natural scene statistics(NSS) features and local information entropy features of the distorted image wavelet sub-band coefficients in three scales. The ABNN classifier is obtained by learning the relationship between image features and distortion types. The ABNN scorer is obtained by learning the relationship between image features and image quality scores. A series of contrast experiments are carried out in the laboratory of image and video engineering(LIVE) database and TID2013 database. Experimental results show the high accuracy of the distinguishing distortion type, the high consistency with subjective scores and the high robustness of the method for distorted images. Experiment results also show the independence of the database and the relatively high operation efficiency of this method.

A New Content Based Image Retrieval Model Based on Wavelet Transform

Searching interested images based on visual properties of images is a challenging problem and it has received considerable attention from researchers in the fields like image processing, computer vision and multimedia systems in the last 20 years. While the importance and the effect of the image features like color, texture and shape have been taken into account in many papers, there have not been many studies on the importance of the color spaces on the performance of Content Based Image Retrieval (CBIR) systems. In this paper we first experimentally study the effect of choosing color space on the performance of content based image retrieval using Wavelet decomposition of each color channel. To this end, the retrieval results of different color spaces like RGB, YUV, HSV, YCbCr and Lab are analyzed. Then as a result a new Content Based Retrieval model using Wavelet Transform in Lab color space and Color Moments is proposed. In order to increase the efficiency of the proposed model some division schemes are taken into account which improves the performance of the proposed model. The proposed model tackles one of the important restrictions in content based image retrieval, namely, the challenge between the accuracy of retrieval and its time complexity. The experimental results on two databases [19] [24] demonstrate the superiority of the proposed model compared to existing models.

An Overview on Wavelet Software Packages

Wavelet analysis provides very powerful problem\|solving tools for analyzing, encoding, compressing, reconstructing, and modeling signals and images. The amount of wavelets\|related software has been constantly multiplying. Many wavelet analysis tools are widely available. This overview represents a significant survey for many currently available packages. It will be of great benefit to engineers and researchers for using the toolkits and developing new software. The beginner to learning wavelets can also get a great help from the review. If you browse around at some of the Internet sites listed in the reference of this paper, you may find more plentiful wavelet resources.

Wavelet Moment Invariants Extraction of Underwater Laser Vision Image

Wavelet moment invariants are constructed for object recognition based on the global feature and local feature of target, which are brought for the simple background of the underwater objects, complex structure, similar form etc. These invariant features realize the multi-dimension feature extraction of local topology and in- variant transform. Considering translation and scale invariant characteristics were ignored by conventional wavelet moments, some improvements were done in this paper. The cubic B-spline wavelets which are optimally localized in space-frequency and close to the forms of Li's(or Zernike's) polynomial moments were applied for calculating the wavelet moments. To testify superiority of the wavelet moments mentioned in this paper, generalized regres- sion neural network(GRNN) was used to calculate the recognition rates based on wavelet invariant moments and conventional invariant moments respectively. Wavelet moments obtained 100% recognition rate for every object and the conventional moments obtained less classification rate. The result shows that wavelet moment has the ability to identify many types of objects and is suitable for laser image recognition.

Medical ultrasound image segmentation by modified local histogram range image method

Fast and satisfied medical ultrasound segmentation is known to be difficult due to speckle noises and other artificial effects. Since speckle noise is formed from random signals which are emitted by an ultrasound system, we can’t encounter the same way as other image noises. Lack of information in ultrasound images is another problem. Thus, segmentation results may not be accurate enough by means of customary image segmentation methods. Those methods that can specify undesirable effects and segment them by eliminating artificial effects, should be chosen. It seems to be a complicated work with high computational load. The current study presents a different approach to ultrasound image segmentation that relies mainly on local evaluation, named as local histogram range image method which is modified by means of discrete wavelet transform. Thus, a significant decrease in computational load is then achieved. The results show that it is possible for tissues to be segmented correctly.

Robust Image Watermarking Using LWT and Stochastic Gradient Firefly Algorithm

Watermarking of digital images is required in diversified applicationsranging from medical imaging to commercial images used over the web.Usually, the copyright information is embossed over the image in the form ofa logo at the corner or diagonal text in the background. However, this formof visible watermarking is not suitable for a large class of applications. In allsuch cases, a hidden watermark is embedded inside the original image as proofof ownership. A large number of techniques and algorithms are proposedby researchers for invisible watermarking. In this paper, we focus on issuesthat are critical for security aspects in the most common domains like digitalphotography copyrighting, online image stores, etc. The requirements of thisclass of application include robustness (resistance to attack), blindness (directextraction without original image), high embedding capacity, high Peak Signalto Noise Ratio (PSNR), and high Structural Similarity Matrix (SSIM). Mostof these requirements are conflicting, which means that an attempt to maximizeone requirement harms the other. In this paper, a blind type of imagewatermarking scheme is proposed using Lifting Wavelet Transform (LWT)as the baseline. Using this technique, custom binary watermarks in the formof a binary string can be embedded. Hu’s Invariant moments’ coefficientsare used as a key to extract the watermark. A Stochastic variant of theFirefly algorithm (FA) is used for the optimization of the technique. Undera prespecified size of embedding data, high PSNR and SSIM are obtainedusing the Stochastic Gradient variant of the Firefly technique. The simulationis done using Matrix Laboratory (MATLAB) tool and it is shown that theproposed technique outperforms the benchmark techniques of watermarkingconsidering PSNR and SSIM as quality metrics.

Study on Method of Removing Stripe Noise in CBERS-02 Image

Based on the project of land macroscopical monitoring by CBERS,a remote sensing image of Arongqi in Inner Mongolia was studied by different methods such as histogram matching,principal component analysis,moment matching,low-pass filter and wavelet transform.A qualitative analysis and quantitative assessment was also carried out.The results showed that wavelet transform could effectively remove stripe noise,and also kept its advantages in the details.Moment matching had a better strip removal,but it changed features in its spectrum easily and it was not fit for CBERS-02 image processing.Principal component analysis could not remove stripe noise,but also strengthened it in a certain extent.

Adaptive template filter method for image processing based on immune genetic algorithm

To preserve the original signal as much as possible and filter random noises as many as possible in image processing,a threshold optimization-based adaptive template filtering algorithm was proposed.Unlike conventional filters whose template shapes and coefficients were fixed,multi-templates were defined and the right template for each pixel could be matched adaptively based on local image characteristics in the proposed method.The superiority of this method was verified by former results concerning the matching experiment of actual image with the comparison of conventional filtering methods.The adaptive search ability of immune genetic algorithm with the elitist selection and elitist crossover(IGAE) was used to optimize threshold t of the transformation function,and then combined with wavelet transformation to estimate noise variance.Multi-experiments were performed to test the validity of IGAE.The results show that the filtered result of t obtained by IGAE is superior to that of t obtained by other methods,IGAE has a faster convergence speed and a higher computational efficiency compared with the canonical genetic algorithm with the elitism and the immune algorithm with the information entropy and elitism by multi-experiments.

基于误差函数的复材加筋板概率成像冲击定位

提出了一种复合材料加筋板结构概率成像冲击定位方法。通过在复合材料加筋板结构表面布置稀疏阵列的压电传感器网络接收冲击响应信号,采用复Morlet小波变换提取冲击响应信号特定中心频率的窄带Lamb波信号并计算模值,根据模的峰值获取Lamb波的到达时刻,构建基于波达时间差的误差函数并计算监测区域内各点为冲击源的概率值,将概率值作为像素值对结构进行概率成像冲击定位。在总体尺寸为700 mm×450 mm的碳纤维增强复合材料加筋板结构上对算法进行了验证。实验结果表明,该算法简单有效,成像分辨率和定位精度高,采用较少的传感器数量依然拥有可观的冲击定位精度。

基于非局部均值滤波的结构光图像去噪

采用一种改进的自适应非局部均值滤波结合小波去噪的方法对结构光图像进行滤波处理。首先针对椒盐噪声,采用一种有效的自适应检测窗口确认噪声点,噪声像素被其相邻的三个像素的组合所取代,然后使用基于椒盐噪声特征的非局部均值滤波来重构噪声点的灰度值。进一步地针对高斯噪声,对图像进行小波变换,并对高频部分进行方向性中值滤波,最终经小波逆变换进行重构,得到去噪后的结构光条纹图像。实验结果显示,与传统方法进行比较,改进的方法能够有效地滤除结构光图像中的噪声,并保持了结构光条纹图像的细节信息。

基于SIFT-GMLBP的动态图像视觉信息提取研究

为了精确地提取动态图像特征,为动画设计师提供更全面、更准确的视觉信息,文中提出基于SIFT-GMLBP的动态图像视觉信息提取方法。以关键点为像素中心,采用局部二值模式(LBP),通过比较其与邻域的灰度值获取LBP码,实现动态图像局部纹理特征捕捉;根据网格化LBP(MLBP)进一步将动态图像中的像素邻域划分为多个网格,使每个网格产生一个LBP值,降低特征向量的维数;结合Gabor滤波器,通过多尺度和多方向的纹理分析,提取动态图像在不同频率和方向上的局部结构信息,整合所有Gabor滤波器响应图像的GMLBP特征,形成包含原始动态图像在不同尺度和方向上的丰富纹理信息的特征向量。实验结果表明:该方法提取的关键点数量和分布非常合理,具有较高的稳定性和动态信息捕获能力,且该方法每秒能够处理高达30帧的图像。

应用于PCB缺陷检测系统的图像质量评价法

基于机器视觉的PCB缺陷检测系统易于因图像模糊等失真问题,影响后续缺陷检测的准确性。针对此问题建立了相关模糊图像数据集,并提出一种空频结合的无参考图像质量实时评价方法。方法提取图像的最大局部变化信息作为空域信息。随后对空域信息进行一级小波分解,求出高频分量中水平方向的小波系数,随后利用处理后的小波系数的最大值,得到客观评价值。同时,建立PCB模糊图像数据集(PBID)用于算法的验证。大量实验结果表明,与其它无参考图像质量评价方法相比,该方法与主观评价值具有较高的一致性,在PBID数据集上的皮尔逊线性相关系数(PLCC)达到了0.9835,且运行速度快,仅为每帧0.1302 s,适合对实时性要求较高的应用场合。

图像处理中应用图像降噪算法的研究综述

日常生活中,在发送、存储图像和拍照形成图像的过程中往往会因操作不当而导致图像不清晰,无法反映图像本质。为此采用图像降噪算法将图像中的杂质去除,还原出无噪声的图像,同时还可以使大部分的细节因素保留在图片中,让图片更加清晰。在去噪方法的运用上通常是采用无噪图像和含有噪声的先验信息,但弊端是二者并没有进行有效的结合。为了解决这个问题,采用小波、非局部均值等方式进行去噪,并且在非局部均值去噪中从欧氏距离和权重分配方面进行一些优化。

基于改进SIFT算法的图像匹配

为进一步提高SIFT匹配算法的鲁棒性和正确率,从以下几个方面改进SIFT算法。对图像进行多分辨率小波变换,重建图像近似成分——低频信息参与匹配;采用"回"字形双层方邻窗将特征点邻域区域划分成四部分,建立32维特征点描述符向量;运用欧式距离初步确定匹配点,再用积分图像进一步剔除由于特征点具有空间相似性而出现的误匹配点,从而提高匹配精度。实验表明,本文算法在匹配精度和匹配时间上有明显提高,特别是当图像具有较多局部相似特征时,匹配点数增加,匹配正确率提高。

基于小波多尺度表示的图像匹配研究

根据小波变换系数对信号平移步长的变化规律，提出一种基于小波金字塔结构的、遍历式的图像匹配方法，这种方法消除了由于小波变换对平移的敏感性所引起的误匹配，在匹配策略上，以小波分解高频分量的匹配为主。实验证实，本匹配方法对实时图和参考图的局部灰度反转不敏感，具有一定抗几何失真的能力，优于经典的灰度相关匹配。

图像去噪的自适应非局部均值滤波方法

提出一种自适应的非局部均值滤波算法.针对传统非局部均值滤波算法不能自适应地调节滤波参数的不足,本文统计和分析了不同图像的最优滤波参数与其小波系数能量的关系,并运用最小二乘拟合法建立了最佳滤波器参数值的预测函数,该函数可为待滤波图像选取合适的非局部均值滤波参数,进而实现了自适应的非局部均值滤波.与传统非局部均值滤波时需手动调节参数相比,本文的算法更加灵活.实验结果表明,对于具有不同内容或结构特性的图像,本文算法在峰值信噪比和主观去噪效果方面均优于传统的非局部均值滤波算法.

一种快速、高精度和稳健的影像匹配算法

在遥感影像应用中,匹配是一项很关键技术,它的优劣直接关系到后续成果的质量。而匹配质量本身的优劣又取决于匹配的速度、精度和可靠性。针对这三个方面的因素,本文探讨一种基于小波变换、遗传算法和最小二乘匹配的快速高精度影像匹配组合算法。小波变换用于减少匹配搜索数据,遗传算法用于优化搜索空间,而最小二乘匹配则用于获得子像素匹配精度。同时为提高遗传搜索的稳定性和匹配结果的可靠性,本文探讨一种改进的自适应算子概率遗传算法。该改进的基本原理是杂交概率依选择的两父代染色体间的Hamming距离而自适应的变化,变异概率则依父代个体的适应度而自适应的变化。实验结果表明:与传统方法相比,本文方法具有明显的性能优势。

基于几何形状和小波矩的静脉特征提取与匹配

针对手背静脉识别系统的特征提取与匹配算法研究问题,提出了一种粗匹配与细匹配结合的方法.该方法通过分析图像特征描述符特性,考虑静脉图像的全局信息,确定提取具有平移、旋转、比例和仿射不变性的边界和区域的形状特征进行粗匹配;为了考虑局部特征使形状描述符具有良好的易分辨能力,依据小波矩具有小波多尺度分析和不变矩的优点,确定了基于小波矩的匹配为细匹配的方案,实验结果表明识别率得到了明显提高.