检索结果-内蒙古大学图书馆

A Coarse-to-Fine Ensembling Framework for Head and Neck Tumor and Lymph Segmentation in CT and PET images 1

3rd 3D Head and Neck Tumor Segmentation in PET/CT Challenge, HECKTOR 2022, held in Conjunction with the 25th International Conference on Medical image Computing and Computer Assisted Intervention, MICCAI 2022

作者： Sun, Xiao An, Chengyang Wang, Lisheng Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031274206

ISBN: (纸本)9783031274190

Head and neck (H &N) cancer is one of the most prevalent cancers [1]. In its treatment and prognosis analysis, tumors and metastatic lymph nodes may play an important role but their manual segmentations are time-consuming and laborious. In this paper, we propose a coarse-to-fine ensembling framework to segment the H &N tumor and metastatic lymph nodes automatically from Positron Emission Tomography (PET) and Computed Tomography (CT) images. The framework consists of three steps. The first step is to locate the head region in CT images. The second step is a coarse segmentation, to locate the tumor and lymph region of interest (ROI) from the head region. The last step is a fine segmentation, to get the final precise predictions of tumors and metastatic lymph nodes, where we proposed a ensembling refinement model. This framework is evaluated quantitatively with aggregated Dice Similarity Coefficient (DSC) of 0.77782 in the task 1 of the HECKTOR 2022 challenge[2, 3] as team SJTU426. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Visual tracking based on weighted subspace reconstruction error

Visual tracking based on weighted subspace reconstruction er...

引用

作者： Zhou, Tao Zhang, Junhao Xie, Kai Yang, Jie He, Xiangjian Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Faculty of Engineering and Information Technology University of Technology Sydney Australia

ISBN: (纸本)9781479957514

It is a challenging task to develop an effective and robust visual tracking method due to factors such as pose variation, illumination change, occlusion, and motion blur. In this paper, a novel tracking algorithm based on weighted subspace reconstruction error is proposed. We first compute the discriminative weights by sparse construction error with template dictionary consisted of positive and negative samples, and then confidence map for candidates is computed through subspace reconstruction error. Finally, the location of the target object is estimated by maximizing the decision map which is combined discriminative weights and subspace reconstruction error. Furthermore, we use the new evaluation criterion to verify the robustness of the current tracking result, which can reduce the accumulated error effectively. Experimental results on some challenging video sequences show that the proposed algorithm performs favorably against seven state-of-the-art methods in terms of accuracy and robustness. © 2014 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Dynamic Frame Interpolation in Wavelet Domain

引用

IEEE Transactions on image processing 2023年 32卷 5296-5309页

作者： Kong, Lingtong Jiang, Boyuan Luo, Donghao Chu, Wenqing Tai, Ying Wang, Chengjie Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Department of Automation Shanghai200240 China Tencent Youtu Laboratory Shanghai200233 China Nanjing University School of Intelligence Science and Technology Suzhou215163 China

Video frame interpolation is an important low-level vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. However, the spatial redundancy when synthesizing the target frame has not been fully explored, that can result in lots of inefficient computation. On the other hand, the computation compression degree in frame interpolation is highly dependent on both texture distribution and scene motion, which demands to understand the spatial-temporal information of each input frame pair for a better compression degree selection. In this work, we propose a novel two-stage frame interpolation framework termed WaveletVFI to address above problems. It first estimates intermediate optical flow with a lightweight motion perception network, and then a wavelet synthesis network uses flow aligned context features to predict multi-scale wavelet coefficients with sparse convolution for efficient target frame reconstruction, where the sparse valid masks that control computation in each scale are determined by a crucial threshold ratio. Instead of setting a fixed value like previous methods, we find that embedding a classifier in the motion perception network to learn a dynamic threshold for each sample can achieve more computation reduction with almost no loss of accuracy. On the common high resolution and animation frame interpolation benchmarks, proposed WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts. © 1992-2012 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Graph-based text segmentation using a selected channel image

Graph-based text segmentation using a selected channel image

引用

International Conference on Digital image Computing: Techniques and Applications, DICTA 2010

作者： Zeng, Chao Jia, Wenjing He, Xiangjian Yang, Jie iNEXT FEIT University of Technology Sydney Sydney Australia Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9780769542713

This paper proposes a graph-based method for segmentation of a text image using a selected colour-channel image. The text colour information usually presents a two-polarity trend. According to the observation that the histogram distributions of the respective colour channel images are usually different from each other, we select the colour channel image with the histogram having the biggest distance between the two main peaks, which represents the main foreground colour strength and background colour strength respectively. The peak distance is estimated by the mean-shift procedure performed on each individual channel image. Then, a graph model is constructed on a selected channel image to segment the text image into foreground and background. The proposed method is tested on a public database, and its effectiveness is demonstrated by the experimental results. © 2010 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

A REVIEW ON ARTERY WALL SEGMENTATION TECHNIQUES AND INTIMA-MEDIA THICKNESS MEASUREMENT FOR CAROTID ULTRASOUND imageS

引用

Journal of Innovative Optical Health Sciences 2012年第1期5卷 75-84页

作者： XIN YANG WANJI HE KAITONG LI JIAOYING JIN XUMING ZHANG MING YUCHI MINGYUE DING State Key Laboratory for Multi-Spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence(IPRAI)Huazhong University of Science and Technology Wuhan 430074HubeiChina Image Processing and Intelligence Control Key Laboratory of Education Ministry of China School of Life Science and Technology Huazhong University of Science and Technology Wuhan 430074HubeiChina

Stroke and heart attack,which could be led by a kind of cerebrovascular and cardiovascular disease named as atherosclerosis,would seriously cause human morbidity and *** is important for the early stage diagnosis and monitoring medical intervention of the *** stenosis is a classical atherosclerotic lesion with vessel wall narrowing down and accumulating plaques *** carotid artery of intima-media thickness(IMT)is a key indicator to the *** the development of computer assisted diagnosis technology,the imaging techniques,segmentation algorithms,measurement methods,and evaluation tools have made considerable *** imaging,being real-time,economic,reliable,and safe,now seems to become a standard in vascular assessment methodology especially for the measurement of *** review firstly attempts to discuss the clinical relevance of measurements in clinical practice at first,and then followed by the challenges that one has to face when approaching the segmentation of ultrasound ***,the commonly used methods for the IMT segmentation and measurement are ***,discussion and evaluation of different segmentation techniques are *** overview of summary and future perspectives is given finally.

关键词： Ultrasound(US)images carotid artery intima-media thickness(IMT) atherosclerosis image segmentation computer assisted diagnosis(CAD)

来源：评论

学校读者我要写书评

暂无评论

Application of an Improved Focal Loss in Vehicle Detection 19th

Application of an Improved Focal Loss in Vehicle Detection

引用

19th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2020

作者： He, Xuanlin Yang, Jie Kasabov, Nikola Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Auckland University of Technology Auckland New Zealand

ISBN: (纸本)9783030614003

Object detection is an important and fundamental task in computer vision. Recently, the emergence of deep neural network has made considerable progress in object detection. Deep neural network object detectors can be grouped in two broad categories: the two-stage detector and the one-stage detector. One-stage detectors are faster than two-stage detectors. However, they suffer from a severe foreground-backg-round class imbalance during training that causes a low accuracy performance. RetinaNet is a one-stage detector with a novel loss function named Focal Loss which can reduce the class imbalance effect. Thereby RetinaNet outperforms all the two-stage and one-stage detectors in term of accuracy. The main idea of focal loss is to add a modulating factor to rectify the cross-entropy loss, which down-weights the loss of easy examples during training and thus focuses on the hard examples. However, cross-entropy loss only focuses on the loss of the ground-truth classes and thus it can’t gain the loss feedback from the false classes. Thereby cross-entropy loss does not achieve the best convergence. In this paper, we proposed a new loss function named Dual Cross-Entropy Focal Loss, which improves on the focal loss. Dual cross-entropy focal loss adds a modulating factor to rectify the dual cross-entropy loss towards focusing on the hard samples. Dual cross-entropy loss is an improved variant of cross-entropy loss, which gains the loss feedback from both the ground-truth classes and the false classes. We changed the loss function of RetinaNet from focal loss to our dual cross-entropy focal loss and performed some experiments on a small vehicle dataset. The experimental results show that our new loss function improves the vehicle detection performance. © 2020, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

QEA-based threshold for fast and robust portrait segmentation

QEA-based threshold for fast and robust portrait segmentatio...

引用

2005 International Conference on Imaging Science, Systems, and technology: Computer Graphics, CISST'05

作者： Heng, Liu Jingqi, Yan Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200030 China Southwest University of Science and Technology Sichuan 621000 China

ISBN: (纸本)9781932415643

image segmentation is a key technology to image analysis and processing. How to segment portrait fast and robust from the background is a difficult problem. With revising histogram segmentation by threshold in blue tone space, we present an adaptable quantum evolution threshold-searching algorithm to segment portrait fast and robust. Experiments and detail comparison analysis are provided to demonstrate effects.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Tracking moving objects in video using enhanced mean shift and region-based motion field

Tracking moving objects in video using enhanced mean shift a...

引用

15th European Signal processing Conference, EUSIPCO 2007

作者： Wang, Tiesheng Gu, Irene Y.H. Viberg, Mats Cao, Zhongping Song, Nuan Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Department of Signals and Systems Chalmers University of Technology Sweden

ISBN: (纸本)9788392134022

In this paper, we propose a scheme for moving object tracking from videos by combining mean shift and motion field statistics. For mean shift, we employ an enhanced spatial-range mean shift that enables a reduced number of over-segmentation. For motion statistics, we combine the optical flow and high-order moment to generate motion regions that are associated with moving objects (or object parts). Experiments have been conducted on several indoor and outdoor (color/gray-scale) image sequences ranging from simple to median complexity. To evaluate the performance, three objective criteria are applied in addition to the visual inspection. The results show that the proposed method is promising for moving object tracking in video, with an averaging detection rate of 95%. Further, the proposed scheme is compared with that using the conventional mean shift for the tracking, indicating a significantly reduction in false alarm (≈ 30%). © 2007 EURASIP.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

Real-time infrared object tracking based on mean shift

引用

9th Iberoamerican Congress on pattern recognition, CIARP 2004

作者： Jian, Cheng Jie, Yang Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai200030 China

ISBN: (纸本)3540235272

The mean shift algorithm is an efficient method for tracking object in the color image sequence. However, in the infrared object-tracking scenario, there is a singular feature space, i.e. the grey space, for representing the infrared object. Due to the lack of the information for the object representation, the object tracking based on the mean shift algorithm may be lost in the infrared sequence. To overcome this disadvantage, we propose a new scheme that is to construct a cascade grey space. The experimental results performed on two different infrared image sequences show our new scheme is efficient and robust for the infrared object tracking. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Unsupervised color-texture segmentation 1

引用

International Conference on image Analysis and recognition, ICIAR 2004

作者： Wang, Yuzhong Yang, Jie Zhou, Yue Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai200030 China

ISBN: (数字)9783540301257

ISBN: (纸本)3540232230

An improved approach for JSEG is presented for unsupervisedcolor image segmentation. Instead of color quantization, an automaticclassification method based on adaptive mean shift (AMS) basedclustering is used for nonparametric clustering of image data set. Theclustering results are used to construct Gaussian mixture modelling ofimage data set for the calculation of soft J value. The region growingalgorithm used in JSEG is then applied in segmenting the image basedon the multiscale soft J-images. Experiments show that the synergismof JSEG and the soft classification based on GMM overcomes thelimitations of JSEG successfully and is more robust. © Springer-Verlag Berlin Heidelberg 2004.

关键词： image segmentation

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：