检索结果-内蒙古大学图书馆

Object scale selection of hierarchical image segmentation with deep seeds

IET image processing 2021年第1期15卷 191-205页

作者： Al-Huda, Zaid Peng, Bo Yang, Yan Algburi, Riyadh Nazar Ali Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu Sichuan Peoples R China Southwest Jiaotong Univ Natl Engn Lab Integrated Transportat Big Data App Chengdu Sichuan Peoples R China Southwest Jiaotong Univ Sch Mech Engn Chengdu Sichuan Peoples R China

Hierarchical image segmentation is a prevalent technique in the literature for improving segmentation quality, where the segmentation result needs to be searched at different scales of the hierarchy to identify objects represented from various scales. In this paper, a novel framework for improving the quality of object segmentation is presented. To this end, the authors first select the optimal segments among several hierarchical scales of the input image using simple mid-level features and dynamic programming. Simultaneously, deep seeds are localised on the input image for the foreground and background classes using a deep classification network and a saliency network, respectively. Then, a graphical model is constructed as a set of nodes that jointly propagate information from deep seeds to unmarked regions to obtain the final object segmentation. Comprehensive experiments are performed on different datasets for popular hierarchical image segmentation algorithms. The experimental results show that the proposed framework can significantly improve the quality of object segmentation at low computational costs and without training any segmentation network.

关键词： Optical, image and video signal processing Optimisation techniques computer vision and image processing techniques Optimisation techniques

来源：评论

学校读者我要写书评

暂无评论

A dual-attention V-network for pulmonary lobe segmentation in CT scans

引用

IET image processing 2021年第8期15卷 1644-1654页

作者： Zheng, Shaohua Nie, Weiyu Pan, Lin Zheng, Bin Shen, Zhiqiang Huang, Liqin Pei, Chenhao She, Yuhang Chen, Liuqing Fuzhou Univ Coll Phys & Informat Engn 2 Xueyuan Rd Fuzhou 350108 Fujian Peoples R China Fujian Med Univ Thorac Dept Union Hosp Fuzhou Peoples R China Fuzhou Univ Coll Mech Engn & Automat Fuzhou Peoples R China

The reliable and automatic segmentation of pulmonary lobes in computed tomography scans is an important pre-condition for the diagnosis, assessment, and treatment of lung diseases. However, due to the incomplete lobar structures and morphological changes caused by diseases, the lobe segmentation still encounters great challenges. Recently, convolution neural network has exerted a tremendous impact on medical image analysis. Nevertheless, the basic convolution operations mainly obtain local features that are insufficient for accurate lobe segmentation. The idea that the global features are equally crucial especially when lesions appear is considered. Here, a dual-attention V-network named DAV-Net for pulmonary lobe segmentation is proposed. First, a novel dual-attention module to capture global contextual information and model the semantic dependencies in spatial and channel dimensions is introduced. Second, a progressive output scheme is used to avoid the vanishing gradient phenomenon and obtain relatively effective features in hidden layers. Finally, an improved combo loss is devised to address input and output lobe imbalance problem during training and inference. In the evaluation using the LUNA16 dataset and our in-house dataset, the proposed DAV-Net obtains Dice similarity coefficients of 0.947 and 0.934, respectively;these values are superior to those obtained by existing methods.

关键词： Optical, image and video signal processing X-ray techniques: radiography and computed tomography (biomedical imaging/measurement) computer vision and image processing techniques X-rays and particle beams (medical uses) Patient diagnostic methods and instrumentation Biology and medical computing Neural nets

来源：评论

学校读者我要写书评

暂无评论

A robust sperm cell tracking algorithm using uneven lighting image fixing and improved branch and bound algorithm

引用

IET image processing 2021年第9期15卷 2068-2079页

作者： Alhaj Alabdulla, Ahmad Hasiloglu, Abdulsamet Hicazi Aksu, Emrah Ataturk Univ Fac Engn Dept Comp Engn Erzurum Turkey Ataturk Univ Fac Vet Med Dept Reprod & Artificial Inseminat Erzurum Turkey

An accurate and robust sperm cells tracking algorithm that is able to detect and track sperm cells in videos with high accuracy and efficiency is presented. It is fast enough to process approximately 30 frames per second. It can find the correct path and measure motility parameters for each sperm. It can also adapt with different types of images coming from different cameras and bad recording conditions. Specifically, a new way is offered to optimize uneven lighting images to improve sperm cells detection which gives us the ability to get more accurate tracking results. The shape of each detected object is used to specify collided sperms and utilized dynamic gates which become bigger and smaller according to the sperm cell's speed. For assigning tracks to the detected sperm cells positions an improved version of branch and bound algorithm which is faster than the normal one is offered. This sperm cells tracking algorithm outperforms many of the previous algorithms as it has lower error rate in both sperm detection and tracking. It is compared with six other algorithms, and it gives lower tracking error rates. This method will allow doctors and researchers to obtain sperm motility data instantly and accurately.

关键词： Biological transport cellular and subcellular transmembrane physics Optical, image and video signal processing computer vision and image processing techniques Other topics in statistics Other topics in statistics Optical and laser radiation (medical uses) Patient diagnostic methods and instrumentation Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

Reversible and high-capacity data hiding in medical images

引用

IET image processing 2011年第2期5卷 190-197页

作者： Fallahpour, M. Megias, D. Ghanbari, M. Univ Oberta Catalunya Barcelona Spain Univ Essex Sch Comp Sci & Elect Engn Colchester CO4 3SQ Essex England

In this study, the authors introduce a highly efficient reversible data hiding system. It is based on dividing the image into tiles and shifting the histograms of each image tile between its minimum and maximum frequency. Data are then inserted at the pixel level with the largest frequency to maximise data hiding capacity. It exploits the special properties of medical images, where the histogram of their non-overlapping image tiles mostly peak around some grey values and the rest of the spectrum is mainly empty. The zeros (or minima) and peaks (maxima) of the histograms of the image tiles are then relocated to embed the data. The grey values of some pixels are therefore modified. High capacity, high fidelity, reversibility and multiple data insertions are the key requirements of data hiding in medical images. The authors show how histograms of image tiles of medical images can be exploited to achieve these requirements. Compared to the data hiding method applied to the whole image, the authors' scheme can result in 30-200% capacity improvement and still with better image quality, depending on the medical image content. Additional advantages of the proposed method include hiding data in the regions of non-interest and better exploitation of spatial masking.

关键词： health physics image quality Patient diagnostic methods and instrumentation medical image content spatial masking nonoverlapping image tiles Biology and medical computing computer vision and image processing techniques data encapsulation Data handling techniques Optical, image and video signal processing high-capacity data hiding grey values reversible data hiding medical image processing Biomedical measurement and imaging histograms Medical and biomedical uses of fields, radiations, and radioactivity grey systems

来源：评论

学校读者我要写书评

暂无评论

Fractal indexing with the joint statistical properties and its application in texture image retrieval

引用

IET image processing 2008年第4期2卷 218-230页

作者： Pi, M. Li, H. Univ Alberta Dept Comp Sci Edmonton AB T6G 2E8 Canada Univ Lethbridge Dept Math & Comp Sci Lethbridge AB T1K 3M4 Canada

Fractal image coding is a block-based scheme that exploits the self-similarity hiding within an image. Fractal parameters generated by the block-based scheme are quantitative measurements of self-similarity, and therefore they can be used to construct image signatures. By combining fractal parameters and collage error, a set of new statistical fractal signatures, such as histogram of collage error (HE), joint histogram of contrast scaling and collage error (JHSE), and joint histogram of range block mean and contrast scaling and collage error (JHMSE) is proposed. These fractal signatures effectively extract and reflect the statistical properties intrinsic in texture images. Hence, they provide new statistical features for use in texture image retrieval and identification. Furthermore, in order to reduce computational complexity of the JHMSE signature, the JHMSE signature is simplified to HM (histogram of range block mean) +JHSE and HM + HS (histogram of contrast scaling) +HE, based on the independence and distance equivalence. Mathematical analysis of the simplification scheme is also carried out. The proposed fractal signatures are compared with the existing fractal signatures. Experimental results show that the proposed signatures, HM + JHSE and HM + HS + HE, achieve a higher retrieval rate with a lower computational complexity.

关键词： indexing joint histogram of contrast scaling and collage error contrast scaling histogram range block mean histogram image signatures statistical analysis computer vision and image processing techniques texture image retrieval Other topics in statistics fractal indexing Information retrieval techniques image texture JHSE joint statistical properties image retrieval fractal image coding self-similarity hiding block-based scheme

来源：评论

学校读者我要写书评

暂无评论

TSDCN: Traffic safety state deep clustering network for real-time traffic crash-prediction

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2021年第1期15卷 132-146页

作者： Li, Haitao Bai, Qiaowen Zhao, Yonghua Qu, Zhaowei Xin, Wang Jilin Univ Coll Transportat Changchun Jilin Peoples R China Jilin Univ Publ Comp Educ & Res Ctr Changchun Jilin Peoples R China

Traffic safety state clustering has always been the focus of traffic safety research and the foundation of real-time crash potential prediction. How to mine effective latent crash risk information and improve clustering effect are the goals and difficulties of traffic safety state clustering task. The conventional methods adopt independent feature extraction and clustering processing, which leads to mismatch problems and decrease clustering effect. To deal with the problems, a novel traffic safety state deep clustering network (TSDCN) is proposed. TSDCN integrates the feature extraction and clustering into an end-to-end deep hybrid network. A custom autoencoder is constructed to extract expressive risk feature and iteratively optimize clustering effects and feature extraction using a deep clustering layer. The three-stage multitask strategy is designed to joint-adjust shared network parameters and ensure convergence at different stages. The comparative experiments show the TSDCN achieves more outstanding cluster performance than those existing models. Moreover, the traffic safety state cluster results are statistically analysed and the crash risk level is quantified for each safety state. The risk-quantized results are consistent with the real road crash situation and this confirms the safety state clustering effectiveness of TSDCN.

关键词： Optimisation techniques computer vision and image processing techniques Data handling techniques Traffic engineering computing Other topics in statistics Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

New method for generating site-specific clutter map for land-based radar by using multimodal remote-sensing images and digital terrain data

引用

IET RADAR SONAR AND NAVIGATION 2011年第3期5卷 374-388页

作者： Kurekin, A. Radford, D. Lever, K. Marshall, D. Shark, L. -K. Plymouth Marine Lab Plymouth PL1 3DH Devon England Gen Dynam UK Oakdale NP12 4AA Blackwood Wales Cardiff Univ Commun Res Ctr Cardiff CF24 0YF S Glam Wales Cardiff Univ Dept Comp Sci Cardiff CF24 3AA S Glam Wales Univ Cent Lancashire ADSIP Res Ctr Preston PR1 2HE Lancs England

By using multimodal remote-sensing images and digital terrain data of the environment, this study presents a new method for generating the clutter map specific to the selected land radar site and the radar's operating parameters. In the proposed method, the estimation of backscattering from the environment involves extrapolation of the airborne radar remote-sensing image to provide the baseline values, classification of multispectral remote-sensing satellite images to provide a detailed description of terrain types, use of digital terrain elevation data with the land radar position and height to provide local grazing angles and a terrain visibility map and use of the digital topographic map to provide the geometric reference for all data sets. Using actual remote-sensing images and digital terrain data acquired from a real environment with various terrain features, the clutter map generated by the proposed method for land-based radar is compared with that generated by the competitive modelling method. The accuracy of the proposed method is demonstrated based on the differences with respect to the actual clutter measurements using a different airborne radar-sensing configuration.

关键词： computer vision and image processing techniques Geophysical techniques and equipment Geography and cartography computing comprehensive modelling method site-specific clutter map Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research radar imaging local grazing angles backscattering estimation multimodal remote-sensing images Optical, image and video signal processing digital topographic map terrain mapping Radar equipment, systems and applications multispectral remote-sensing satellite image classification clutter measurements remote sensing by radar terrain visibility map backscatter land radar position land-based radar radar clutter digital terrain data airborne radar

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition using a combination of enhanced local binary pattern and pyramid histogram of oriented gradients features extraction

引用

IET image processing 2021年第2期15卷 468-478页

作者： Sharifnejad, Maede Shahbahrami, Asadollah Akoushideh, Alireza Hassanpour, Reza Zare Univ Guilan Dept Comp Engn Rasht Iran Tech & Vocat Univ TVU Fac Shahid Chamran Guilan Branch Dept Elect Engn Rasht Iran Erasmus Univ Dept Technol & Operat Management Rotterdam Netherlands

Automatic facial expression recognition, which has many applications such as drivers, patients, and criminals' emotions recognition, is a challenging task. This is due to the variety of individuals and facial expression variability in different conditions, for instance, gender, race, colour and changing illumination. In addition, there are many regions in a face image such as forehead, mouth, eyes, eyebrows, nose, cheeks and chin, and extracting features of all these regions are expensive in terms of computational time. Each of the six basic emotions of anger, disgust, fear, happiness, sadness and surprise affect some regions more than the other regions. The goal of this study is to evaluate the performance of enhanced local binary pattern, pyramid histogram of oriented gradients feature-extraction algorithms and their combination in terms of recognition accuracy, feature vector length and computational time on one, two and three combined regions of a face image. Our experimental results show that the combination of both feature-extraction algorithms yields an average recognition accuracy of 95.33% using three regions, that is, the mouth, nose and eyes on Cohn-Kanade dataset. Besides, the mouth region is the most important part in terms of accuracy in comparison to eyes, nose and combination of both eyes and nose regions.

关键词： image recognition computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Pornographic image screening by integrating recognition module and image black-list/white-list subsystem

引用

IET image processing 2010年第2期4卷 103-113页

作者： Sun, H. -M. Kainan Univ Dept Comp Sci & Informat Engn Luchu 33857 Taoyuan County Taiwan

A number of pornographic image detection techniques have been studied in the literature but the online error-correction method is rarely discussed. As some of the pornographic images on the Internet are duplicated, the online error-correction capability can prevent repeated misclassification occurring on the same image. An image black-list/white-list subsystem is presented to correct the classification errors of the recognition module. This subsystem uses the wavelet transform to extract the colour and texture features from images. However, images can be lossily compressed and the image features will be shifted. To be able to identify lossily compressed images, a support vector machine serves as a classifier to determine whether two image feature vectors represent the same image. The experimental result demonstrates that the proposed subsystem can remedy the errors of the recognition module and increase the recognition accuracy.

关键词： support vector machine Internet support vector machines wavelet transform classification errors image features computer vision and image processing techniques image classification image black-list/white-list subsystem online error-correction capability feature extraction image compression pornographic image screening Optical, image and video signal processing computer communications recognition module

来源：评论

学校读者我要写书评

暂无评论

A new recognition algorithm for high-voltage lines based on improved LSD and convolutional neural networks

引用

IET image processing 2021年第1期15卷 260-268页

作者： Luo, Yanhong Yu, Xue Yang, Dongsheng Northeastern Univ Dept Elect Engn Shenyang 110004 Peoples R China

With the development of high-voltage transmission and artificial intelligence technology, unmanned line inspection has become the inevitable trend of current electric power inspection. A new recognition algorithm for high-voltage lines is proposed based on colour (Red, Green, Blue) RGB image to support the unmanned line inspection. Firstly, in order to solve the problem of missing weak edges in image edge detection, an improved Canny algorithm is proposed. Fourier transform Gaussian filter is introduced to enhance the high-frequency signal of the image, which makes the extracted edge information more complete. At the same time, an improved line segment detector (LSD) algorithm is developed to extract the high-voltage line. The complementary edge information of the three channels of the colour RGB image is analyzed, and the calculation formula of the horizontal line angle is improved, which greatly reduces the possibility of false detection and missed detection in the high-voltage line extraction. In addition, the convolution neural network (CNN) is used to accurately recognize the extracted high-voltage lines, which reduces the interference of non-high-voltage lines. Simulation results show that the proposed algorithm has high recognition accuracy and strong robustness in the complex environment.

关键词： Optical, image and video signal processing image recognition computer vision and image processing techniques Integral transforms Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：