改进的模糊阈值图像分割方法

提出了一种自适应的模糊阈值图像分割方法,通过预分割和直方图信息相结合的方法,解决了传统的模糊闽值图像分割法难以自动获取窗宽的困难;并针对模糊闽值图像分割方法不能适用于直方图呈单峰分布的图像的缺陷,提出了一个新的平滑迭代公式。该平滑迭代公式利用像素点的邻域信息使图像增强,再使用自适应的模糊阈值图像分割方法进行分割,可以拓宽模糊阈值图像分割方法的适用范围。实验结果表明,使用该方法的目标分割正确率达97.3％,显示了较高的分割精度和较强的鲁棒性。     

An adaptive framework for saliency detection

At present, people are inclined to use one saliency detection method to cover all the pixels in an image. However, every method has its own limitations. A single method may not yield a good performance at all image scenes. In this article, we propose a new adaptive framework to detect salient objects. For each pixel in an image, it adaptively selects an appropriate method according to the pixel context relationship. In our framework, an image is characterized by a set of binary maps, which are generated by randomly thresholding the image's initial saliency map. And then, we utilize the surroundedness cue, which are obtained by a series of operations on the binary maps, to classify all the pixels in an image. Furthermore, based on the classes, we choose methods to detect salient objects. Extensive experimental results on three benchmark datasets demonstrate that our method performs favorable against 11 state-of-the-art methods.     

An adaptive image denoising method based on local parameters optimization

In image denoising algorithms, the noise is handled by either modifying term-by-term, i.e., individual pixels or block-by-block, i.e., group of pixels, using suitable shrinkage factor and threshold function. The shrinkage factor is generally a function of threshold and some other characteristics of the neighbouring pixels of the pixel to be thresholded (denoised). The threshold is determined in terms of the noise variance present in the image and its size. The VisuShrink, SureShrink, and NeighShrink methods are important denoising methods that provide good results. The first two, i.e., VisuShrink and SureShrink methods follow term-by-term approach, i.e., modify the individual pixel and the third one, i.e., NeighShrink and its variants: ModiNeighShrink, IIDMWD, and IAWDMBMC, follow block-by-block approach, i.e., modify the pixels in groups, in order to remove the noise. The VisuShrink, SureShrink, and NeighShrink methods however do not give very good visual quality because they remove too many coefficients due to their high threshold values. In this paper, we propose an image denoising method that uses the local parameters of the neighbouring coefficients of the pixel to be denoised in the noisy image. In our method, we propose two new shrinkage factors and the threshold at each decomposition level, which lead to better visual quality. We also establish the relationship between both the shrinkage factors. We compare the performance of our method with that of the VisuShrink and NeighShrink including various variants. Simulation results show that our proposed method has high peak signal-to-noise ratio and good visual quality of the image as compared to the traditional methods: Weiner filter, VisuShrink, SureShrink, NeighBlock, NeighShrink, ModiNeighShrink, LAWML, IIDMWT, and IAWDMBNC methods.     

Computer generation of binary Fresnel holography

Binarization of Fresnel holograms by direct thresholding based on the polarity of the fringe pattern is studied. It is found that if the hologram is binarized (i.e., for black and white hologram pixels) in this manner, only the edges of the object are preserved in the reconstructed image. To alleviate the errors caused by binarization, the use of error diffusion has been routinely employed. However, the reconstructed image using such standard technique is heavily contaminated with random noise. In this paper, we propose a novel noniterative method for generating Fresnel holograms that are suitable for binarization. Our method is capable of preserving good visual quality on the reconstructed images.     

非下采样Contourlet变换域统计模型红外图像去噪

对红外图像进行非下采样Contourlet变换,分析其系数的统计特征,采用广义高斯分布来模拟系数的概率分布。根据非下采样Contourlet变换的带通子带各方向能量不同的特点,提出修正的贝叶斯阈值公式,为了克服软、硬阈值函数的缺点,又提出一种具有可调节自适应性的新阈值函数,最后利用新阈值函数估计出不含噪声的变换系数,并通过非下采样Contourlet逆变换得到去噪后的红外图像。仿真实验表明,文中方法在峰值信噪比及视觉效果上均优于经典的小波阈值去噪算法。     

Visual Relationship Detection with Contextual Information

Understanding an image goes beyond recognizing and locating the objects in it, the relationships between objects also very important in image understanding. Most previous methods have focused on recognizing local predictions of the relationships. But real-world image relationships often determined by the surrounding objects and other contextual information. In this work, we employ this insight to propose a novel framework to deal with the problem of visual relationship detection. The core of the framework is a relationship inference network, which is a recurrent structure designed for combining the global contextual information of the object to infer the relationship of the image. Experimental results on Stanford VRD and Visual Genome demonstrate that the proposed method achieves a good performance both in efficiency and accuracy. Finally, we demonstrate the value of visual relationship on two computer vision tasks: image retrieval and scene graph generation.     

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.     

视觉自适应行人计数

基于视觉的行人计数技术因其广阔的应用前景逐步成为智能视觉监控领域的一个研究热点。本文提出了一种基于虚拟门上前景像素点个数的行人计数方法。该方法分为学习和计数两个过程。在学习过程中,本方法采用基于行人检测的方法获取场景中的若干行人模型,并利用线性拟合为虚拟门上的点赋予权重。在计数过程中,本方法在考虑虚拟门上前景像素的权重、运动矢量的大小和方向等信息的基础上,逐帧统计虚拟门上前景点个数,通过特定时间内累计的前景点数量来确定通过虚拟门的行人数量。实验表明,该方法能够在保证计数精度的前提下,有较好的实时性能。     

Automatic segmentation system for liver tumors based on the multilevel thresholding and electromagnetism optimization algorithm

In this article, we propose an automated segmentation system for liver tumors using magnetic resonance imaging and computed tomography. The proposed system is based on the algorithm of multilevel thresholding with electromagnetism optimization (EMO). The system starts with visualizing a patient's digital communication in medicine (DICOM) abdominal data set in three views. Two-stage active contour segmentation methods that integrate region-based local and global techniques using the active geodesic contour technique are proposed to segment the liver. To increase the accuracy and speed of segmentation for liver images, we identify the optimal threshold of the image segmentation method based on EMO with Otsu and Kapur algorithms. EMO offers interesting search capabilities while keeping a low computational cost. The proposed system was tested using a set of five DICOM data sets. All images were of the same size and stored in JPEG format (512 × 512 pixels). Experimental results illustrate that the proposed system outperforms state-of-the-art methods such as the watershed algorithm. The average sensitivity, specificity, and accuracy of the segmented liver using the active contour model were 97.05%, 99.88%, and 98.47%, respectively. Moreover, the average sensitivity, specificity, and accuracy of the segmented liver tumor results were 94.15%, 99.57%, and 96.86%, respectively.     

基于方块编码的图像特征提取及检索算法

提出了一种基于方块编码的图像检索算法.首先将图像分成互不重叠的子图像块,根据图像块中各像素间的色差,利用方块编码的思想对这些子图像进行编码,然后根据人眼的视觉特性来定义图像的关键块,最后借助于基于关键字的文本检索技术进行图像检索.同时,考虑到不同类型的关键块在表征图像内容时重要程度的不同而赋予其不同的权值.实验结果表明本文算法在图像的相似性检索时是有效的,并具有较高的检索效率.     

Improving performance of wavelet-based image de-noising algorithm using complex diffusion process

Abstract

Image enhancement and de-noising is an essential pre-processing step in many image processing algorithms. In any image de-noising algorithm, the main concern is to keep the interesting structures of the image. Such interesting structures often correspond to the discontinuities (edges). In this paper, we present a new algorithm for image noise reduction based on the combination of complex diffusion process and wavelet thresholding. In the existing wavelet thresholding methods, the noise reduction is limited, because the approximate coefficients containing the main information of the image are kept unchanged. Since noise affects both the approximate and detail coefficients, the proposed algorithm for noise reduction applies the complex diffusion process on the approximation band in order to alleviate the deficiency of the existing wavelet thresholding methods. The algorithm has been examined using a variety of standard images and its performance has been compared against several de-noising algorithms known from the prior art. Experimental results show that the proposed algorithm preserves the edges better and in most cases, improves the measured visual quality of the de-noised images in comparison to the existing methods known from the literature. The improvement is obtained without excessive computational cost, and the algorithm works well on a wide range of different types of noise.     

采用图像融合技术的多模式人脸识别

利用图像融合技术实现了基于可见光图像和红外热图像相结合的多模式人脸识别,研究了两种图像在像素级和特征级的融合方法.在像素级,提出了基于小波分解的图像融合方法,实现了两种图像的有效融合.在特征级,采用分别提取两种识别方法中具有较好分类效果的前50%的特征进行特征级的融合.实验表明,经像素级和特征级融合后,识别准确率都较单一图像有很大程度的提高,并且特征级的融合效果明显优于像素级的融合.因此,基于图像融合技术的多模式人脸识别,有效的增加了图像的信息量,是提高人脸识别准确率的有效途径之一.     

基于最优色空间和视觉掩蔽的彩色图像评价算法

目的针对当前色差算法在评价彩色图像时未考虑图像中像素之间颜色在视觉上的空间效应,提出基于最优色空间和视觉掩蔽效应的彩色图像质量评价算法。方法通过分析色空间通道间的相关性,选取最优正交、对立空间作为评价的工作色空间,在此基础上,利用色空间各颜色通道的掩蔽函数,去除图像颜色与颜色之间在视觉上的空间关联性,最后构建图像颜色差别公式,以评价彩色图像质量。结果在验证实验中,通过利用Pearson相关系数、Spearman等级相关系数以及Kendall等级相关系数,分析各算法评价与图像主观评价之间的关系发现,该算法评价与主观评价的Pearson相关系数、Spearman等级相关系数和Kendall等级相关系数分别可达到0.3948,0.5840和0.4814,且分别大于现有其他色差算法评价与主观评价的相关系数。结论该算法评价结果与人眼视觉主观评价相对一致。     

基于二维EMD和小波阈值的掌纹图像去噪

为有效抑制掌纹图像中含有的噪声、提高特征提取的精度,提出一种基于二维经验模式分解和小波阈值去噪相结合的掌纹图像去噪新方法。首先,对含有噪声的掌纹图像进行二维EMD分解,得到不同特征尺度的本征模函数子图像;然后对中高频成分的IMF进行小波多阈值去噪;最后将去噪处理后的各IMF与残差图像通过加和进行重构。实验结果表明,该方法与单独的二维EMD滤波及小波阈值去噪相比,去噪效果更明显,提取的主线和细节特征更清晰,因而均方误差最小、峰值信噪比最高。     

Data hiding based on two-stage referencing for two-colour images

Abstract

Data hiding in two-colour images is difficult since 1 pixel requires only 1 bit representation and it is easy to detect for pixel distortion. In this paper, we describe a new data hiding method for two-colour images by two-stage referencing. The cover image is partitioned into n×n non-overlapping sub-blocks, and we calculate difference values by two stages for all pixels to find the suitable replacement pixel. The two-stage referencing is to obtain difference values that are different with the current pixel value for neighbouring pixels with n×n and (n+2)×(n+2). These two difference values are used to embed a secret bit on the sub-block. The experimental results show that the proposed method achieves a good visual quality for the stego-image.     

Better Visual Image Super-Resolution with Laplacian Pyramid of Generative Adversarial Networks

Although there has been a great breakthrough in the accuracy and speed of super-resolution (SR) reconstruction of a single image by using a convolutional neural network, an important problem remains unresolved: how to restore finer texture details during image super-resolution reconstruction? This paper proposes an Enhanced Laplacian Pyramid Generative Adversarial Network (ELSRGAN), based on the Laplacian pyramid to capture the high-frequency details of the image. By combining Laplacian pyramids and generative adversarial networks, progressive reconstruction of super-resolution images can be made, making model applications more flexible. In order to solve the problem of gradient disappearance, we introduce the Residual-in-Residual Dense Block (RRDB) as the basic network unit. Network capacity benefits more from dense connections, is able to capture more visual features with better reconstruction effects, and removes BN layers to increase calculation speed and reduce calculation complexity. In addition, a loss of content driven by perceived similarity is used instead of content loss driven by spatial similarity, thereby enhancing the visual effect of the superresolution image, making it more consistent with human visual perception. Extensive qualitative and quantitative evaluation of the baseline datasets shows that the proposed algorithm has higher mean-sort-score (MSS) than any state-of-the-art method and has better visual perception.     

基于图像配准的STN-LCD外观缺陷检测

提出了一种基于图像配准的超扭曲向列液晶显示器件(STN-LCD)的外观缺陷自动检测方法.该方法首先对标准模板图像做不均匀光照消除、二值化以及区域信息提取;然后通过控制点检测和仿射变换实现待检测图像和模板图像之间的配准;并利用各图形区域的灰度平均值和标准方差等统计信息,检测缺段、针孔等各类缺陷.为提高图像配准精度,进一步提出了有效控制点筛选方案以及混合插值方法.实验结果表明,该方法设计思路合理,缺陷检测正确率达到98.3%,可代替人眼实现对STN-LCD多种外观缺陷的快速、自动检测,满足实际应用需求.     

Fusion of MRI and CT images using guided image filter and image statistics

In medical imaging using different modalities such as MRI and CT, complementary information of a targeted organ will be captured. All the necessary information from these two modalities has to be integrated into a single image for better diagnosis and treatment of a patient. Image fusion is a process of combining useful or complementary information from multiple images into a single image. In this article, we present a new weighted average fusion algorithm to fuse MRI and CT images of a brain based on guided image filter and the image statistics. The proposed algorithm is as follows: detail layers are extracted from each source image by using guided image filter. Weights corresponding to each source image are calculated from the detail layers with help of image statistics. Then a weighted average fusion strategy is implemented to integrate source image information into a single image. Fusion performance is assessed both qualitatively and quantitatively. Proposed method is compared with the traditional and recent image fusion methods. Results showed that our algorithm yields superior performance.     

An Adaptive Image Calibration Algorithm for Steganalysis

In this paper, a new adaptive calibration algorithm for image steganalysis is proposed. Steganography disturbs the dependence between neighboring pixels and decreases the neighborhood node degree. Firstly, we analyzed the effect of steganography on the neighborhood node degree of cover images. Then, the calibratable pixels are marked by the analysis of neighborhood node degree. Finally, the strong correlation calibration image is constructed by revising the calibratable pixels. Experimental results reveal that compared with secondary steganography the image calibration method significantly increased the detection accuracy for LSB matching steganography on low embedding ratio. The proposed method also has a better performance against spatial steganography.     

IGM‐based perceptual multimodal medical image fusion using free energy motivated adaptive PCNN

Multimodal medical image fusion merges two medical images to produce a visual enhanced fused image, to provide more accurate comprehensive pathological information to doctors for better diagnosis and treatment. In this article, we present a perceptual multimodal medical image fusion method with free energy (FE) motivated adaptive pulse coupled neural network (PCNN) by employing Internal Generative Mechanism (IGM). First, source images are divided into predicted layers and detail layers with Bayesian prediction model. Then to retain human visual system inspired features, FE is used to motivate the PCNN for processing detail layers, and large firing times are selected as coefficients. The predicted layers are fused with the averaging strategy as activity level measurement. Finally, the fused image is reconstructed by merging coefficients in both fused layers. Experimental results visually and quantitatively show that the proposed fusion strategy is superior to the state‐of‐the‐art methods.