碎片图像字符特征提取方法研究

字符特征提取是含文字碎片图像拼接的关键环节,直接影响拼接效果。提出了一种包含文字信息的碎片图像特征提取方法 ,首先,对原始碎片图像进行预处理,分别得到字符和碎片背景的二值图像;然后,利用边缘检测算子提取字符和碎片背景的单像素边缘;最后,利用结构算子检测碎片图像中字符与碎片背景边缘的交叉点,并根据交叉点的信息提取字体边缘方向特征。仿真实验结果表明本文提出的碎片图像字符特征提取方法思路合理,能够快速、准确地提取出碎片图像中的字符特征,为后续的匹配拼接奠定基础。     

基于连通域的图像中场景文本定位

提出了一种基于连通域的自动定位图像中场景文本的方法.该方法充分利用了场景文本的两类特征--字符特征和文本区域特征,同时对一些字符特征进行组合,组合得到的新字符特征能够对字符的大小、字体等有很好的不变性.该方法利用级联弱分类器将所有的特征组合到一个框架中,提高了处理速度.实验结果显示,该方法对字符的大小、颜色、语言等具有很好的鲁棒性,并具有较高的召回率.     

局部高亮干扰文本图像的二值化方法研究

本文提出一种新的基于Curvelet变换的文本图像二值化处理方法,以消除文本图像中局部高亮度区域对二值化图像质量的影响.首先对具有局部高亮度区域干扰的原始文本图像进行Curvelet变换,得到图像在曲波域的Curvelet系数集；然后根据各Curvelet系数所表征的图像特征,对Curvelet系数进行非线性增强,以优化文本图像的直方图分布；对增强的Curvelet系数集进行反变换,得到直方图优化后的时域图像,进而应用Otsu方法实现文本图像二值化.应用本文方法对具有带状及点状局部高亮度区域的文本图像进行二值化处理,并采用ABBYYFineReaderl0对二值图像进行OCR识别.实验结果表明,通过本文提出的处理方法所得到的二值化图像,其字符的OCR识别准确率最高可达94.81％,优于其他四种典型的图像二值化处理方法.     

模糊理论与BP网络在目标识别中的应用

针对利用神经网络进行目标识别时特征向量选取中存在的一些问题：如特征向量选取不当，导致不同目标特征向量值可区分性差；相同目标由于大小、平移、旋转角度的不同，导致特征向量值具有较大差异等，首先对样本图像边缘提取，然后对已有的隶属函数进行改造，提出了一种基于模糊理论的阈值分割法，把图像二值化处理，提取出样本图像中目标的边缘轮廓，对其取不变矩．并归一化不变矩．为了避免不变矩数值过小，对其取对数，以此作为BP网络的输入特征向量，进行训练和识别．试验表明该方法能快速有效地识别出目标．     

基于Canny算子的图像边缘检测实现

图像边缘信息是重要的图像信息,本文详细介绍了canny算子边缘提取的原理和算法,然后利Matlab编程实现Canny算子对灰度图像的边缘检测。实验表明,Canny算子提取图像边缘具有很好的效果。     

基于线奇异性分析的图像边缘检测方法

针对基于图像像素点分析的边缘提取方法存在无法同时满足高抑噪性、连续性,定位性等问题,本文提出了方向Beamle变换(DBT)方法,在定义图像线奇异性的理论基础上,利用DBT对图像进行线奇异性分析,依据Beamlet变换具有的线段提取能力,将图像边缘检测问题转化为方向Beamlet变换系数矩阵中奇异点的检测问题,以降低噪声点对边缘检测结果的影响.通过对人工图像以及SAR图像的实验,与经典边缘检测算子相比较,验证了本方法具有较强的抗噪性,特别是针对直线边缘,在抑制噪声影响的同时保证了线状边缘的直线连接性,抗噪性较强.     

LabVIEW平台的文本图像倾斜校正方法

文本图像扫描过程中会出现倾斜的情况,这给后期的图像处理和分析带来了困难,因此对文本图像进行检测和倾斜校正具有十分重要的意义.为解决这个问题,提出了一种基于文本图像边缘特征的方法,通过提取文本图像边缘的像素点,利用最小二乘法对这些像素点进行直线拟合,从而计算得到倾斜角.在LabVIEW平台上,利用LabVIEW视觉库IMAQ中强大的图像处理函数,实现倾斜角度检测方法,进而通过旋转变换对倾斜的图像进行校正.结果表明,该方法对图像校正的效果较好,并且能够快速实现.     

基于字符基元视觉短语的图像关键字识别

提出了一种利用字符基元视觉短语进行图像关键字识别的方法.该方法通过提取图像关键字的最大稳定极值区域,并进行归一化后得到字符基元.由于通常情况下每个关键字由若干字符基元构成,因此通过采用利用邻接的字符基元构造的视觉短语来提高图像关键字特征描述的可区分性;由于不同的字符基元组合结构可能构成不同的图像关键字,因此基于字符基元相邻关系判断短语几何结构的相似性.此方法不需要对图像进行二值化、布局分析和文本区域定位等预处理操作,具有更好的灵活性和鲁棒性.实验结果表明,此方法对于不同语言的图像关键字识别都具有较高的准确性.     

基于机器视觉的线束连接器字符检测

针对线束连接器上印刷字符检测智能化程度不高的情况,提出了一种基于机器视觉的检测方法.首先,利用一阶导数获得印刷字符边缘点,并将边缘点拟合为线,由此定位字符的位置,并对字符的角度和位置进行比较;然后,对合格的字符分割、归一化,并以整个字符图像作为输入特征;最后,基于字符的特征,建立了用于印刷字符识别的BP神经网络,并对其进行了改进.实验证明:基于机器视觉的连接器印刷字符单个字符识别准确率为99.1%,检测时间为95ms,具有较高的识别准确率和速度.     

基于BP神经网络的字符图像识别方法

字符图像识别是数字图像处理技术中的重要应用,本文研究了一种基于BP神经网络的字符图像识别方法。首先对图像进行预处理,包括临域法去杂及灰度、二值化处理;然后采用垂直投影法进行图像分割,对字符进行网格及交点特征的提取;最后利用经过训练的BP神经网络进行字符识别。     

Image edge detection and enhancement by an inversion operation

Edge extraction is an essential part of image processing. In digital image processing there are several optical methods for properly obtaining image edges. We propose a method of image edge extraction and enhancement by using a lens-based optical setup, the image, and its inverted form. The inverted and the noninverted images help here to obtain the image edges.     

A robust zero-watermarking algorithm for copyright protection of text documents

The widespread use of Internet and other communication technologies has brought about ease in reproducing, disclosing and distributing digital content. In addition to getting the benefits of information exchange, the digital community is confronted with authentication, forgery and copyright protection issues. Text is the most frequently used medium travelling over the Internet, along with images, audio and video. Majority of the content of books, newspapers, web pages, advertisements, research papers, legal documents and many other documents is basically, plain text. Therefore, copyright protection of plain text is a most important issue. In this article, we propose a robust zero-watermarking algorithm based on prepositions and double letters for copyright protection of plain text. The embedding algorithm uses occurrences of prepositions and double letters in the text to generate a key based on watermark. The extraction algorithm extracts the watermark from the noisy text to identify the original owner. Experimental results illustrate the effectiveness of the proposed algorithm on text encountering combined insertion, deletion and re-ordering attacks, both in the dispersed and localized forms. The results are also compared to a recent work on text watermarking.     

PCB导线上下线宽检测算法研究

针对PCB导线的上下线宽的测量,提出了快速而且精确的边缘提取算法。由于采集的显微图像中有很强噪声,一般常用除噪方法很容易破坏图像的边缘信息。采用P-M模型进行除噪,这种方法最大的优点是能够在除噪的同时保护甚至增强图像的边缘;利用Canny算子对降噪图像提取边缘点;最后进行Hough直线拟合。实验证明该方法不仅有很强的抗噪声能力,能够保持边缘信息和测量的精度,并且满足工程测量的实际要求。     

Multimodal medical image fusion based on discrete Tchebichef moments and pulse coupled neural network

Multimodal medical image fusion plays a vital role in clinical diagnoses and treatment planning. In many image fusion methods‐based pulse coupled neural network (PCNN), normalized coefficients are used to motivate the PCNN, and this makes the fused image blur, detail loss, and decreases contrast. Moreover, they are limited in dealing with medical images with different modalities. In this article, we present a new multimodal medical image fusion method based on discrete Tchebichef moments and pulse coupled neural network to overcome the aforementioned problems. First, medical images are divided into equal‐size blocks and the Tchebichef moments are calculated to characterize image shape, and energy of blocks is computed as the sum of squared non‐DC moment values. Then to retain edges and textures, the energy of Tchebichef moments for blocks is introduced to motivate the PCNN with adaptive linking strength. Finally, large firing times are selected as coefficients of the fused image. Experimental results show that the proposed scheme outperforms state‐of‐the‐art methods and it is more effective in processing medical images with different modalities. © 2017 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 27, 57–65, 2017     

Text Detection and Recognition for Natural Scene Images Using Deep Convolutional Neural Networks

Words are the most indispensable information in human life. It is very important to analyze and understand the meaning of words. Compared with the general visual elements, the text conveys rich and high-level moral information, which enables the computer to better understand the semantic content of the text. With the rapid development of computer technology, great achievements have been made in text information detection and recognition. However, when dealing with text characters in natural scene images, there are still some limitations in the detection and recognition of natural scene images. Because natural scene image has more interference and complexity than text, these factors make the detection and recognition of natural scene image text face many challenges. To solve this problem, a new text detection and recognition method based on depth convolution neural network is proposed for natural scene image in this paper. In text detection, this method obtains high-level visual features from the bottom pixels by ResNet network, and extracts the context features from character sequences by BLSTM layer, then introduce to the idea of faster R-CNN vertical anchor point to find the bounding box of the detected text, which effectively improves the effect of text object detection. In addition, in text recognition task, DenseNet model is used to construct character recognition based on Kares. Finally, the output of Softmax is used to classify each character. Our method can replace the artificially defined features with automatic learning and context-based features. It improves the efficiency and accuracy of recognition, and realizes text detection and recognition of natural scene images. And on the PAC2018 competition platform, the experimental results have achieved good results.     

Extraction of text lines and text blocks on document images based on statistical modeling

In this article, we developed a Bayesian model to characterize text line and text block structures on document images using the text word bounding boxes. We posed the extraction problem as finding the text lines and text blocks that maximize the Bayesian probability of the text lines and text blocks given the text word bounding boxes. In particular, we derived the so-called probabilistic linear displacement model (PLDM) to model the text line structures from text word bounding boxes. We also developed an augmented PLDM model to characterize the text block structures from text line bounding boxes. By systematically gathering statistics from a large population of document images, we are able to validate our models through experiments and determine the proper model parameters. We designed and implemented an iterative algorithm that used these probabilistic models to extract the text lines and text blocks. The quantitative performances of the algorithm in terms of the rates of miss, false, correct, splitting, merging, and spurious detections of the text lines and text blocks are reported. © 1996 John Wiley & Sons, Inc.     

Fractional M-band dual tree complex wavelet transform for digital watermarking

In this paper, a novel digital watermarking scheme using fractional M-band dual tree complex wavelet transform (Fr-M-band-DT-CWT) is proposed. High frequency channels have wide bandwidth and low frequency channels have narrow bandwidth. These characteristics are suitable for analysing low frequency signal, but not for relatively high frequency signal. The images often contain many edges, which may cause rich middle and high frequency components in the 2-band wavelet domain. Therefore, the ordinary 2-band dual tree complex wavelet transform (DT-CWT) is not well-suited for analysing the image. So, the M-band DT-CWT with the FrFT called Fr-M-band-DT-CWT is proposed in this paper to address this problem. Further, we integrate the Fr-M-Band-DT-CWT with singular value decomposition (SVD) in order to enhance the performance. Experimental results of the proposed watermarking scheme are compared with the previously available watermarking algorithms, fractional Fourier transform (FrFT), fractional wavelet transform (FrWT). Further, the proposed watermark extraction scheme is also tested on different attacks. The results of the present investigations show that the proposed watermarking scheme is superior as compared to other existing watermarking schemes.     

Curvelet Transform Based on Edge Preserving Filter for Retinal Blood Vessel Segmentation

Segmentation of vessel in retinal fundus images is a primary step for the clinical identification for specific eye diseases. Effective diagnosis of vascular pathologies from angiographic images is thus a vital aspect and generally depends on segmentation of vascular structure. Although various approaches for retinal vessel segmentation are extensively utilized, however, the responses are lower at vessel's edges. The curvelet transform signifies edges better than wavelets, and hence convenient for multiscale edge enhancement. The bilateral filter is a nonlinear filter that is capable of providing effective smoothing while preserving strong edges. Fast bilateral filter is an advanced version of bilateral filter that regulates the contrast while preserving the edges. Therefore, in this paper a fusion algorithm is recommended by fusing fast bilateral filter that can effectively preserve the edge details and curvelet transform that has better capability to detect the edge direction feature and better investigation and tracking of significant characteristics of the image. Afterwards C mean thresholding is used for the extraction of vessel. The recommended fusion approach is assessed on DRIVE dataset. Experimental results illustrate that the fusion algorithm preserved the advantages of the both and provides better result. The results demonstrate that the recommended method outperforms the traditional approaches.     

基于PCNN区域分割的图像邻域去噪算法

针对小波图像去噪方法中使用的NeighShrink方法,本文提出了一种有效的保护图像边缘的图像去噪算法.主要改进了NeighShrink方法中固定的邻域范围,根据图像自身的性质,自适应分割成不同的邻域对图像进行去噪处理;并进一步结合小波层内相关性,对各个不规则邻域加上固定的窗口,选择了几何距离更为接近且在同一不规则邻域内的系数,以完善NeighShrink方法.该算法采取平稳小波对含噪图像进行分解,以保持相位不变性,并对低频子带利用脉冲耦合神经网络模型进行图像分割,按照一定的规则将性质相似的像素点相接,得到原图像分割后的信息.在处理过程中利用得到的分割信息对边缘予以保护.实验结果表明,该方法在降低了图像噪声的同时又尽可能地保留了图像的边缘信息,是一种有效的去噪方法.