检索结果-内蒙古大学图书馆

CATIRI:An Efficient Method for Content-and-Text Based Image Retrieval

Journal of Computer Science & Technology 2019年第2期34卷 287-304页

作者： Mengqi Zeng Bin Yao Zhi-Jie Wang Yanyan Shen Feifei Li Jianfeng Zhang Hao Lin Minyi Guo Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Data and Computer Science Sun Yat-sen University Guangzhou 510006 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou 510006 China National Engineering Laboratory for Big Data Analysis and Applications Beijing 100871 China School of Computing University of Utah Salt Lake City 84112 U.S.A. Alibaba Group Hangzhou 311121 China

The combination of visual and textual information in image retrieval remarkably alleviates the semantic gap of traditional image retrieval methods,and thus it has attracted much attention *** retrieval based on such a combination is usually called the content-and-text based image retrieval(CTBIR).Nevertheless,existing studies in CTBIR mainly make efforts on improving the retrieval *** the best of our knowledge,little attention has been focused on how to enhance the retrieval ***,image data is widespread and expanding rapidly in our daily ***,it is important and interesting to investigate the retrieval *** this end,this paper presents an efficient image retrieval method named CATIRI(content-and-text based image retrieval using indexing).CATIRI follows a three-phase solution framework that develops a new indexing structure called *** MHIM-tree seamlessly integrates several elements including Manhattan Hashing,Inverted index,and *** use our MHIM-tree wisely in the query,we present a set of important metrics and reveal their inherent *** on them,we develop a top-k query algorithm for *** results based on benchmark image datasets demonstrate that CATIRI outperforms the competitors by an order of magnitude.

关键词： image retrieval text-and-visual feature indexing top-k

来源：评论

学校读者我要写书评

暂无评论

Classification of Thoracic Bone Scintigraphic Images Using ResNet with Attention Modules 2

Classification of Thoracic Bone Scintigraphic Images Using R...

引用

2nd International Conference on Signal Image Processing and Communication, ICSIPC 2022

作者： Cao, Xu Cao, Yongchun Lin, Qiang Man, Zhengxing Wang, Yubo Key Laboratory of China’s Ethnic Languages and Information Technology of Ministry of Education Northwest Minzu University China School of Mathematics and Computer Science Northwest Minzu University China Key Laboratory of Streaming Data Computing Technologies and Application Northwest Minzu University China

ISBN: (纸本)9781510657694

Whole-body bone scan is an effective tool for diagnosing bone metastasis from malignant tumors, including lung cancer. However, due to the low spatial resolution of Scintigraphic images, manual analysis of the images is very difficult. In order to accurately diagnose bone metastases, a self-defined convolutional neural network is studied and constructed in this paper for detecting lung cancer-Caused skeletal metastasis in bone scan images Firstly, since thoracic regions such as ribs and spine are the most frequent areas of bone metastases, we preprocessed the collected SPECT whole-body bone imaging data to extract the thoracic regions. Then based on the feature that ResNet can alleviate the vanishing gradient problem caused by increasing depth in deep neural networks and the feature that attention can focus on important information to improve network expression. A deep SPECT image classification network Att-ResNet24 with residual module and hybrid attention mechanism is developed for classification of these images, including bone metastases and non-bone metastases. Experiments on a set of real SPETC whole-body bone images show that self-defined classification networks can be effectively used for the detection of bone metastases, obtaining the best scores 0.737, 0.744, 0.736, and 0.735 for accuracy, precision, recall, and F-1 score, respectively. © 2022 SPIE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Multi-disease classification of whole-body scintigraphy images based on deep learning 7

Multi-disease classification of whole-body scintigraphy imag...

引用

7th International Conference on Intelligent computing and Signal Processing, ICSP 2022

作者： Liu, Liangxia Cao, Yongchun Lin, Qiang Man, Zhengxing Wang, Weiqiong Key Laboratory of China's Ethnic Languages and Information Technology Ministry of Education Northwest Minzu University China School of Mathematics and Computer Science Northwest Minzu University China Key Laboratory of Streaming Data Computing Technologies and Application Northwest Minzu University China

ISBN: (纸本)9781665478571

Bone scan images has important clinical application value for the early diagnosis and treatment of skeletal lesions in the whole-body. In order to realize classification of multiple diseases (i.e., normal, bone metastases, arthritis, and thyroid cancer) in whole-body bone scintigraphy images, In this paper, the multi-disease classification method based on convolutional neural network was studied on bone scan images, and a self-defined classification model was proposed, which was named SPNT9. The model consists of nine convolutional layers, five pooling layers, two fully connected layers and one softmax layer. Finally, the model was validated with real SPECT images collected. By comparing with VGGNet, ResNet and DenseNet models, The SPNT9 model obtained the best classification performance in the test samples, with Accuracy, Precision, Recall and F-1 of 0.8814, 0.7806, 0.7900 and 0.7899, respectively. The results show that the proposed model can be used to accurately classify multiple diseases in SPECT images. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Automated Classification of SPECT Bone Scan Images

CNN-Based Automated Classification of SPECT Bone Scan Images

引用

2022 International Conference on Neural Networks, Information, and Communication Engineering, NNICE 2022

作者： Man, Zhengxing Lin, Qiang Cao, Yongchun School of Mathematics and Computer Science Northwest Minzu University Gansu Lanzhou730124 China Key Laboratory of Streaming Data Computing Technologies and Application Northwest Minzu University Gansu Lanzhou730030 China

ISBN: (纸本)9781510655171

Functional medicine imaging has been successfully applied to capture functional changes in pathological tissues of the body in recent years. SPECT nuclear medicine functional imaging has the potential to acquire information about areas of concern (e.g., lesions and organs) in a non-invasive manner, enabling semi-automated or automated decision-making for the purposes of disease diagnosis, treatment, evaluation, and prediction. To reliably identify that whether or not at least one hotspot or lesion presents in a whole-body SPECT image, in this work, we develop a group of CNN-based classifiers. Specifically, we first propose a preprocessing method that transforms each original SPECT file into the required form by deep learning model, including normalization, 3-channel construction, rotation and scaling, size standardization, and size adapting. Second, six different classifiers are constructed by fine-tuning parameters of the standard VGG-16 model. Last, a group of real-world SPECT whole-body bone scan files were utilized to evaluate the developed classifiers. Experiment results shows that our classifiers are workable for the 2-class classification of SPECT images, achieving a best value of 0.7641, 0.6678, 1.000, and 0.6574 for defined evaluation metrics Acc, Pre, Rec, and AUC, respectively. © 2022 SPIE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

On Star Coloring of Mycielski's Graphs for Special Graphs

On Star Coloring of Mycielski's Graphs for Special Graphs

引用

Computer Science and Management Technology (ICCSMT), International Conference on

作者： Cai Jin Shuangliang Tian Zhuomo An School of Mathematics and Computer Science Northwest for Minzu University Key Laboratory of Streaming Data Computing Technologies and Applications Northwest Minzu University Lanzhou China

ISBN: (纸本)9781728186696

Let G be a simple graph with vertex set V (G) and edge set E (G). A vertex coloring of G is called a star coloring of G if any path of 4 order is bicolored. The minimum number of colors required for a star coloring of G is denoted by χ s (G). Let G is a simple graph with vertex set V (G) = V and edge set E (G) = E, if the vertex set is V ∪ V' ∪ {w} where V' = {X' : x ∈ V} and the edge set is EU{xy' : xy∈V} U {y'w : y'∈V'}, then G is a Mycielski's graph. This paper mainly studies star coloring of Mycielski's graph for some special graphs, the specific results are as follows: if n = 2,3 , then χ s (M (P n )) = 4, otherwise, χ s (M (P n )) = 6 ; if n = 5, then χ s (M(C n )) = 8, otherwise, χ s (M(C n )) = 6 ; χ s (M(S n )) = 4 ; χ s (M (K n )) = n + 2.

关键词： Computer science Color

来源：评论

学校读者我要写书评

暂无评论

The acyclic coloring of the Corona product and Edge corona product of special graphs

The acyclic coloring of the Corona product and Edge corona p...

引用

Computer Science and Management Technology (ICCSMT), International Conference on

作者： Qiqi Lu Shuangliang Tian Lizhen Peng School of Mathematics and Computer Science Northwest for Minzu University Key Laboratory of Streaming Data Computing Technologies and Applications Northwest Minzu University Lanzhou China

An acyclic coloring of a graph is a proper vertex coloring such that there are no bichromatic cycles. The acyclic chromatic number of G, denoted a(G), is the minimum number of colors required for acyclic coloring of a graph G. We study the acyclic coloring of the corona product, edge corona product of paths or circles and any simple graph, and the corresponding acyclic chromatic number are determined.

关键词： Computer science Color Corona

来源：评论

学校读者我要写书评

暂无评论

Adjacent vertex distinguishing incidence coloring of semi-strong product of paths

Adjacent vertex distinguishing incidence coloring of semi-st...

引用

Computer Science and Management Technology (ICCSMT), International Conference on

作者： Lizhen Peng Shuangliang Tian Qiqi Lu School of Mathematics and Computer Science Northwest for Minzu University Key Laboratory of Streaming Data Computing Technologies and Applications Northwest Minzu University Lanzhou China

ISBN: (纸本)9781728186696

Adjacent vertex distinguishing incidence coloring of graph G is an incidence coloring that satisfies that adjacent vertices have different color sets, and the minimum color number is called the adjacent vertex distinguishing incidence coloring number of graph G, which is denoted as χ ai (G). In this paper, we study the adjacent vertex distinguishing incidence coloring of semi-strong products and strong products of paths of different orders, and obtain the exact values of the corresponding coloring numbers.

关键词： Computer science Color

来源：评论

学校读者我要写书评

暂无评论

SPECT bone imaging thyroid lesion segmentation

SPECT bone imaging thyroid lesion segmentation

引用

2021 International Conference on Big data and Intelligent Algorithms, BDIA 2021

作者： Mingyang-Luo Qiang-Lin Tongtong-Li Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Lanzhou730030 China School of Mathematics and Computer Science Northwest Minzu University Lanzhou730030 China Key Laboratory of Streaming Data Computing and Application Northwest Minzu University Lanzhou730124 China

Nuclear medicine SPECT is the main functional imaging modality, which plays an important role in the diagnosis and treatment of thyroid diseases. Hyperthyroidism is a common thyroid disease with symptoms such as exophthalmos, eyelid edema, and vision loss. In order to accurately segment thyroid lesions from SPECT thyroid data, a U-net-based thyroid lesion segmentation model was constructed. First, mirror, rotate, and translate the existing data. At the same time, use the generative adversarial network to expand the data. Then build a segmentation model based on U-net. Finally, perform experimental evaluation and analysis based on a set of real SPECT thyroid data. The results show that: in the traditional data expansion, the IoU value of the improved RS-U-net model is 66.83. © Published under licence by IOP Publishing Ltd.

关键词： Nuclear medicine

来源：评论

学校读者我要写书评

暂无评论

X-ray Classification of Tuberculosis Based on Convolutional Networks

X-ray Classification of Tuberculosis Based on Convolutional ...

引用

2021 IEEE International Conference on Artificial Intelligence and Industrial Design, AIID 2021

作者： Cao, Kai Zhang, Jingyi Huang, Mengge Deng, Tao Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Northwest Minzu University Gansu Lanzhou730000 China Key Laboratory of Streaming Data Computing Technologies and Application School of Mathematics and Computer Science Northwest Minzu University Gansu Lanzhou730000 China

ISBN: (纸本)9780738110837

Tuberculosis is a chronic infectious disease caused by Mycobacterium tuberculosis, which can invade many organs, and pulmonary tuberculosis is the most common infection. It is the key to treat tuberculosis to detect and diagnose the disease in the early stage. The existing computer-aided detection system has made preliminary progress in the diagnosis of pulmonary tuberculosis based on chest X-ray, but there is still a lack of further research on the classification of image signs of tuberculosis. In recent years, with the in-depth research and development in the field of deep learning, convolutional networks have emerged. Convolutional networks have achieved the best current results in image recognition, image classification, image segmentation, and other fields. Therefore, this paper applies the convolutional network to tuberculosis CT images and uses different convolutional network models to study the classification of tuberculosis CT images. Experiments show that the DenseNet121 model has higher performance than VGGNet16, VGGNet19, and ResNet152 models. As a result of classification, the accuracy rate is over 90%. © 2021 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Structured information extraction for bone scan image report texts 4

Structured information extraction for bone scan image report...

引用

2021 4th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2021

作者： Huang, Mengge Zhang, Jingyi Deng, Tao Man, Zhengxing Lin, Qiang Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Northwest Minzu University Lanzhou730030 China Key Laboratory of Streaming Data Computing Technologies and Application Northwest Minzu University Lanzhou730030 China School of Mathematics and Computer Science Northwest Minzu University Lanzhou730030 China

Extracting structured information from the bone scan image report text plays a crucial role in supporting clinical analysis and research. This study summarized the structure and characteristics of 3608 bone scan image report text using dictionary-based information extraction method, including data cleaning, entity recognition, building dictionary and extraction rules. This method was used to obtain the structured data of bone scan image report text required for clinical research, and the effect evaluation was carried out on 1000 randomly selected report texts, with the precision rate and recall rate higher than 90%. The method proposed in this study is practical and could have good effect on structured results for bone scan imaging report text. © Published under licence by IOP Publishing Ltd.

关键词： Clinical research

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：