High-quality retinal vessel segmentation using generative adversarial network with a large receptive field

Retinal vessel segmentation is of great significance for assisting doctors in diagnosis of ophthalmological diseases such as diabetic retinopathy, macular degeneration and glaucoma. This article proposes a new retinal vessel segmentation algorithm using generative adversarial learning with a large receptive field. A generative network maps an input retinal fundus image to a realistic vessel image while a discriminative network differentiates between images drawn from the database and the generative network. Firstly, the proposed generative network combines shallow features with the upsampled deep features to assemble a more precise vessel image. Secondly, the residual module in the proposed generative and discriminative networks can effectively help deep nets easy to optimize. Moreover, the dilated convolutions in the proposed generative network effectively enlarge the receptive field without increasing the amount of computations. A number of experiments are conducted on two publicly available datasets (DRIVE and STARE) achieving the segmentation accuracy rates of 95.63% and 96.84%, and the average areas under the ROC curve of 98.12% and 98.53%. Performance results show that the proposed automatic retinal vessel segmentation algorithm outperforms state-of-the-art algorithms in many validation metrics. The proposed algorithm can not only detect small tiny blood vessels but also capture large-scale high-level semantic vessel features.     

拓扑梯度耦合FCMC的全自动图像修复优化算法

目的当前图像修复算法的损坏区域大都是依靠人工来确定,难以自动鉴定损坏区域,使其修复效率较低。此类算法通过利用像素缺失区域的间断边缘来完成填充,导致重构图像视觉间断,且都是依赖随机修复路径,增加了算法时耗。提出拓扑梯度最小重构路径耦合FCMC(Fuzzy C-mean Clustering)的全自动图像修复算法。方法基于图像损坏区域与完好区域之间的性质差异,引入模糊C均值(FCMC),通过损坏区域的聚类中心与各像素之间的距离来计算隶属度函数,设计基于FCMC的损坏区域自动鉴定算法,以自动识别待修复区域;再嵌入拓扑梯度,定义像素缺失区域的关键点选择规则,建立权重距离函数,得到像素缺失区域的连续轮廓,设计最低修复路径成本方案,完成图像重构;以PSNR(Peak Signal to Noise Ratio)为评估指标,构造图像修复反馈机制,优化修复图像。结果仿真结果显示:与当前图像修复算法相比,该算法可自动鉴定图像像素缺失区域,能够提取像素缺失区域的连续轮廓。同时,具有更好的修复视觉效果与更高的修复效率,重构图像不存在模糊与视觉不连通。结论提出的算法能够实现图像的全自动修复,可提高修复图像质量与效率。     

改进的Inceptionv3果蔬识别算法

目的为了提高果蔬农产品识别的准确性,使果蔬农产品分类实现自动化。方法利用深度卷积神经网路强大的特征学习和特征表达能力,来自动学习果蔬种类特征,提出基于位置的柔性注意力算法,对Inceptionv3神经网络进行改进,并结合参数迁移学习方法建立果蔬识别模型;针对果蔬种类繁多,且国内外缺乏完善的果蔬图像数据库这一现状,构建果蔬图像数据集;在此数据集上将文中所提出的果蔬识别算法与其他果蔬识别算法进行对比。结果试验结果表明,在学习率为0.1、迭代次数为5000时,文中提出算法的准确率高达97.89%。结论相较于现有果蔬识别算法,所提出的果蔬识别算法的识别性能最优,鲁棒性最强。     

Deep learning for photoacoustic tomography from sparse data

The development of fast and accurate image reconstruction algorithms is a central aspect of computed tomography. In this paper, we investigate this issue for the sparse data problem in photoacoustic tomography (PAT). We develop a direct and highly efficient reconstruction algorithm based on deep learning. In our approach, image reconstruction is performed with a deep convolutional neural network (CNN), whose weights are adjusted prior to the actual image reconstruction based on a set of training data. The proposed reconstruction approach can be interpreted as a network that uses the PAT filtered backprojection algorithm for the first layer, followed by the U-net architecture for the remaining layers. Actual image reconstruction with deep learning consists in one evaluation of the trained CNN, which does not require time-consuming solution of the forward and adjoint problems. At the same time, our numerical results demonstrate that the proposed deep learning approach reconstructs images with a quality comparable to state of the art iterative approaches for PAT from sparse data.     

An Optimized Approach to Vehicle-Type Classification Using a Convolutional Neural Network

Vehicle type classification is considered a central part of an intelligent traffic system. In recent years, deep learning had a vital role in object detection in many computer vision tasks. To learn high-level deep features and semantics, deep learning offers powerful tools to address problems in traditional architectures of handcrafted feature-extraction techniques. Unlike other algorithms using handcrated visual features, convolutional neural network is able to automatically learn good features of vehicle type classification. This study develops an optimized automatic surveillance and auditing system to detect and classify vehicles of different categories. Transfer learning is used to quickly learn the features by recording a small number of training images from vehicle frontal view images. The proposed system employs extensive data-augmentation techniques for effective training while avoiding the problem of data shortage. In order to capture rich and discriminative information of vehicles, the convolutional neural network is fine-tuned for the classification of vehicle types using the augmented data. The network extracts the feature maps from the entire dataset and generates a label for each object (vehicle) in an image, which can help in vehicle-type detection and classification. Experimental results on a public dataset and our own dataset demonstrated that the proposed method is quite effective in detection and classification of different types of vehicles. The experimental results show that the proposed model achieves 96.04% accuracy on vehicle type classification.     

UFC-Net with Fully-Connected Layers and Hadamard Identity Skip Connection for Image Inpainting

Image inpainting is an interesting technique in computer vision and artificial intelligence for plausibly filling in blank areas of an image by referring to their surrounding areas. Although its performance has been improved significantly using diverse convolutional neural network (CNN)-based models, these models have difficulty filling in some erased areas due to the kernel size of the CNN. If the kernel size is too narrow for the blank area, the models cannot consider the entire surrounding area, only partial areas or none at all. This issue leads to typical problems of inpainting, such as pixel reconstruction failure and unintended filling. To alleviate this, in this paper, we propose a novel inpainting model called UFC-net that reinforces two components in U-net. The first component is the latent networks in the middle of U-net to consider the entire surrounding area. The second component is the Hadamard identity skip connection to improve the attention of the inpainting model on the blank areas and reduce computational cost. We performed extensive comparisons with other inpainting models using the Places2 dataset to evaluate the effectiveness of the proposed scheme. We report some of the results.     

Encoder-Decoder Based LSTM Model to Advance User <i>QoE</i> in 360-Degree Video

The development of multimedia content has resulted in a massive increase in network traffic for video streaming. It demands such types of solutions that can be addressed to obtain the user's Quality-of-Experience (QoE). 360-degree videos have already taken up the user's behavior by storm. However, the users only focus on the part of 360-degree videos, known as a viewport. Despite the immense hype, 360-degree videos convey a loathsome side effect about viewport prediction, making viewers feel uncomfortable because user viewport needs to be pre-fetched in advance. Ideally, we can minimize the bandwidth consumption if we know what the user motion in advance. Looking into the problem definition, we propose an Encoder-Decoder based Long-Short Term Memory (LSTM) model to more accurately capture the non-linear relationship between past and future viewport positions. This model takes the transforming data instead of taking the direct input to predict the future user movement. Then, this prediction model is combined with a rate adaptation approach that assigns the bitrates to various tiles for 360-degree video frames under a given network capacity. Hence, our proposed work aims to facilitate improved system performance when QoE parameters are jointly optimized. Some experiments were carried out and compared with existing work to prove the performance of the proposed model. Last but not least, the experiments implementation of our proposed work provides high user's QoE than its competitors.     

Splitting up panoramic range images into compact 2[1/2]D representations

This article presents a simple technique for splitting up a panoramic range image into a set of 2[1/2]D representations. The proposed technique consists of three stages. First, a spherical discretization map is generated. Second, main surface orientations are extracted together with their corresponding histogram of distances. Each one of these histograms is used to define the position of a projection plane as well as two associated clipping planes. Finally, data points bounded by clipping planes are mapped onto the corresponding projection plane defining a classical 2[1/2]D range image. This last stage—projection—is applied as many times as main orientations in the spherical discretization map. Experimental results with a panoramic range image are presented. © 2006 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 16, 85–91, 2006     

基于深度学习的易拉罐缺陷检测技术

目的 现有的易拉罐缺陷检测系统在高速生产线中存在错检率和漏检率高,检测精度相对较低等问题,为了提高易拉罐缺陷识别的准确性,使易拉罐生产线实现进一步自动化、智能化,基于深度学习技术和迁移学习技术,提出一种适用于易拉罐制造的在线检测的算法。方法 利用深度卷积网络提取易拉罐缺陷特征,通过优化卷积核,减短易拉罐缺陷检测的时间。针对国内外数据集缺乏食品包装制造的缺陷图像,构建易拉罐缺陷数据集,结合预训练网络,通过调整VGG16提升对易拉罐缺陷的识别准确率。结果 对易拉罐数据集在卷积神经网络、迁移学习和调整后的预训练网络进行了易拉罐缺陷检测的性能对比,验证了基于深度学习的易拉罐缺陷检测技术在学习率为0.0005,训练10个迭代后可达到较好的识别效果,最终二分类缺陷识别率为99.7%,算法耗时119 ms。结论 相较于现有的易拉罐检测算法,文中提出的基于深度学习的易拉罐检测算法的识别性能更优,智能化程度更高。同时,该研究有助于制罐企业利用深度学习等AI技术促进智能化生产,减少人力成本,符合国家制造业产业升级的策略,具有一定的实际意义。     

基于深度学习利用特征图加权融合的目标检测方法

为了提高目标检测的准确性,提出了一种基于深度学习利用特征图加权融合实现目标检测的方法。首先,提出将卷积神经网络中的浅层特征图采样后与最深层特征图进行加权融合的思想;其次,根据所提的特征图加权融合思想以及卷积神经网络的具体结构,制定相应的特征图加权融合方案,并由该方案得到新特征图;然后,提出改进的RPN网络,并将新特征图输入到改进的RPN网络得到区域建议;最后,将新特征图和区域建议输入到后续网络层完成目标检测。实验结果表明所提方法取得了更高的目标检测精度以及更好的目标检测效果。     

图像Inpainting技术原理及在包装印刷图像处理中的应用

在包装印刷行业图像修复问题需要有经验的技术人员进行复杂的手工处理,随着计算机图像处理领域对图像自动处理技术的讨论,INPAINTING技术对包装印刷图像处理提供了新的方法和方向.主要介绍了图像自动修复技术的原理、发展,以及在包装印刷行业的应用.     

基于小波神经网络的图像表述

小波神经网络有机地融合了小波分析的时频特性和神经网络自适应优点。本文将小波神经网络应用于图像表述，提出相应的图像表述算法。分别采用两种小波函数作为网络激励函数，以验证图像表述效果。实验结果表明，小波神经网络能够有效地表述图像，其算法具有较强的鲁棒性。     

基于深度学习的界面设计美学评价研究

目的美感已经成为人机交互(HCI)的核心结构之一,对用户的感知和态度具有明显的有益影响。然而界面美观性评价方法仍是设计师及其团队所面临的重要问题。引入深度学习技术来探讨其评价界面设计美感的可能性。方法分别使用基于深度卷积神经网络的闪屏美学分类方法和Google提出的基于深度学习NIMA神经网络,来预测闪屏图像的美学评价分布。结果通过研究发现,使用基于深度学习NIMA神经网络可以得到比传统方法更具体的评价结果,帮助设计师有效而客观地评价界面设计。结论将计算机图像美学评价的研究领域拓展到界面设计领域,验证了深度卷积神经网络在界面设计美学评价领域使用的可行性。未来图像美学评价还可以介入更多的设计相关领域,辅助设计师做出更有效的设计和商业决策。     

Kernel Granulometric Texture Analysis and Light RES-ASPP-UNET Classification for Covid-19 Detection

This research article proposes an automatic frame work for detecting COVID -19 at the early stage using chest X-ray image. It is an undeniable fact that coronovirus is a serious disease but the early detection of the virus present in human bodies can save lives. In recent times, there are so many research solutions that have been presented for early detection, but there is still a lack in need of right and even rich technology for its early detection. The proposed deep learning model analysis the pixels of every image and adjudges the presence of virus. The classifier is designed in such a way so that, it automatically detects the virus present in lungs using chest image. This approach uses an image texture analysis technique called granulometric mathematical model. Selected features are heuristically processed for optimization using novel multi scaling deep learning called light weight residual–atrous spatial pyramid pooling (LightRES-ASPP-Unet) Unet model. The proposed deep LightRES-ASPP-Unet technique has a higher level of contracting solution by extracting major level of image features. Moreover, the corona virus has been detected using high resolution output. In the framework, atrous spatial pyramid pooling (ASPP) method is employed at its bottom level for incorporating the deep multi scale features in to the discriminative mode. The architectural working starts from the selecting the features from the image using granulometric mathematical model and the selected features are optimized using LightRES-ASPP-Unet. ASPP in the analysis of images has performed better than the existing Unet model. The proposed algorithm has achieved 99.6% of accuracy in detecting the virus at its early stage.     

基于纹理特征与最优稀疏表示的图像修复算法

目的解决当前图像修复算法忽略了对修复块后续的优化处理,导致修复图像易出现不连贯效应以及块效应等的不足。方法提出基于纹理特征与稀疏表示的图像修复算法,首先利用像素点对应的数据项,构造了优先权模型。然后,利用像素点在R,G,B分量上对应的像素值来构造纹理特征度量模型,对待修复块中像素点对应的纹理特征进行度量,并根据度量结果,选择其对应样本集的大小。引入SSD型,从样本集中搜索与待修复块最相似的最优样本块,对待修复块进行填充。最后,利用最优样本块函数,构造最优稀疏表示模型,从而实现图像修复。结果仿真结果显示,与当前图像修复算法相比,所提图像修复算法具备更高的复原质量,能有效克服修复图像中出现的不连贯效应以及块效应。结论所提算法具有较高的修复视觉质量,在数字图像处理领域具有较好的应用价值。     

Image Recognition of Citrus Diseases Based on Deep Learning

In recent years, with the development of machine learning and deep learning, it is possible to identify and even control crop diseases by using electronic devices instead of manual observation. In this paper, an image recognition method of citrus diseases based on deep learning is proposed. We built a citrus image dataset including six common citrus diseases. The deep learning network is used to train and learn these images, which can effectively identify and classify crop diseases. In the experiment, we use MobileNetV2 model as the primary network and compare it with other network models in the aspect of speed, model size, accuracy. Results show that our method reduces the prediction time consumption and model size while keeping a good classification accuracy. Finally, we discuss the significance of using MobileNetV2 to identify and classify agricultural diseases in mobile terminal, and put forward relevant suggestions.     

Survey on Segmentation and Classification Techniques of Satellite Images by Deep Learning Algorithm

This survey paper aims to show methods to analyze and classify field satellite images using deep learning and machine learning algorithms. Users of deep learning-based Convolutional Neural Network (CNN) technology to harvest fields from satellite images or generate zones of interest were among the planned application scenarios (ROI). Using machine learning, the satellite image is placed on the input image, segmented, and then tagged. In contemporary categorization, field size ratio, Local Binary Pattern (LBP) histograms, and color data are taken into account. Field satellite image localization has several practical applications, including pest management, scene analysis, and field tracking. The relationship between satellite images in a specific area, or contextual information, is essential to comprehending the field in its whole.     

Cell-type based semantic segmentation of histopathological images using deep convolutional neural networks

Histopathological whole-slide image (WSI) analysis is still one of the most important ways to identify regions of cancer risk. For cancer in which early diagnosis is vital, pathologists are at the center of the decision-making process. Thanks to the widespread use of digital pathology and the development of artificial intelligence methods, automatic histopathological image analysis methods help pathologists in their decision-making process. In this process, rather than producing labels for whole-slide image patches, semantic segmentation is very useful, which facilitates the pathologists’ interpretation. In this study, automatic semantic segmentation based on cell type is proposed for the first time in the literature using novel deep convolutional networks structure (DCNN). We presents semantic information on four classes, including white areas in the whole-slide image, tissue without cells, tissue with normal cells and tissue with cancerous cells. This visual information presented to the pathologist is an easy-to-understand picture of the status of the cells and their implications for the spread of cancerous cells. A new DCNN architecture is created, inspired by the residual network and deconvolution network architecture. Our network is trained end-to-end manner with histopathological image patches for cell structures to be more discriminative. The proposed method not only produces more successful results than other state-of-art semantic segmentation algorithms with 9.2% training error and 88.89% F-score for test, but also has the most important advantage in that it has the ability to generate automatic information about the cancer and also provides information that pathologists can quickly interpret.     

Perceptual image hashing using local entropies and DWT

Abstract

Image hashing is an emerging technology in multimedia security. It uses a short string called image hash to represent an input image and finds applications in image authentication, tamper detection, digital watermark, image indexing, content-based image retrieval and image copy detection. This paper presents a hashing algorithm based on the observation that block entropies are approximately linearly changed after content-preserving manipulations. This is done by converting the input image to a fixed size, dividing the normalised image into non-overlapping blocks, extracting entropies of image blocks and applying a single-level 2D discrete wavelet transform to perform feature compression. Correlation coefficient is exploited to evaluate similarity between hashes. Experimental results show that the proposed algorithm is robust against content-preserving operations, such as JPEG compression, watermark embedding, Gamma correction, Gaussian low-pass filtering, adjustments of brightness and contrast, scaling and small angle rotation. Similarity values between hashes of different images are small, indicating good performances in discriminative capability.     

Robust Multi-Watermarking Algorithm for Medical Images Based on GoogLeNet and Henon Map

The field of medical images has been rapidly evolving since the advent of the digital medical information era. However, medical data is susceptible to leaks and hacks during transmission. This paper proposed a robust multi-watermarking algorithm for medical images based on GoogLeNet transfer learning to protect the privacy of patient data during transmission and storage, as well as to increase the resistance to geometric attacks and the capacity of embedded watermarks of watermarking algorithms. First, a pre-trained GoogLeNet network is used in this paper, based on which the parameters of several previous layers of the network are fixed and the network is fine-tuned for the constructed medical dataset, so that the pre-trained network can further learn the deep convolutional features in the medical dataset, and then the trained network is used to extract the stable feature vectors of medical images. Then, a two-dimensional Henon chaos encryption technique, which is more sensitive to initial values, is used to encrypt multiple different types of watermarked private information. Finally, the feature vector of the image is logically operated with the encrypted multiple watermark information, and the obtained key is stored in a third party, thus achieving zero watermark embedding and blind extraction. The experimental results confirm the robustness of the algorithm from the perspective of multiple types of watermarks, while also demonstrating the successful embedding of multiple watermarks for medical images, and show that the algorithm is more resistant to geometric attacks than some conventional watermarking algorithms.