发布求助
文献互助 智能选刊 最新文献

2017 IEEE International Conference on Imaging Systems and Techniques (IST)最新文献

筛选
英文 中文
Multi-classification of skin diseases for dermoscopy images using deep learning 基于深度学习的皮肤镜图像皮肤病多分类
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261543
Hangning Zhou, Feng-ying Xie, Zhi-guo Jiang, Jie Liu, Shiqi Wang, Chen-yu Zhu
{"title":"Multi-classification of skin diseases for dermoscopy images using deep learning","authors":"Hangning Zhou, Feng-ying Xie, Zhi-guo Jiang, Jie Liu, Shiqi Wang, Chen-yu Zhu","doi":"10.1109/IST.2017.8261543","DOIUrl":"https://doi.org/10.1109/IST.2017.8261543","url":null,"abstract":"Skin diseases are very common in our daily life. Due to the similar appearance of skin diseases, automatic classification through lesion images is quite a challenging task. In this paper, a novel multi-classification method based on convolutional neural network (CNN) is proposed for dermoscopy images. A CNN network with nested residual structure is designed first, which can learn more information than the original residual structure. Then, the designed network are trained through transfer learning. With the trained network, 6 kinds of lesion diseases are classified, including nevus, seborrheic keratosis, psoriasis, seborrheic dermatitis, eczema and basal cell carcinoma. The experiments are conducted on six-classification and two-classification tasks, and with the accuracies of 65.8% and 90% respectively, our method greatly outperforms other 4 state-of-the-art networks and the average of 149 professional dermatologists.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126817265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 19
Modelling of electrical capacitance array for water leakage imaging inside porous slab 多孔板内漏水成像的电容阵列建模
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261466
L. Rui, Lihui Peng
{"title":"Modelling of electrical capacitance array for water leakage imaging inside porous slab","authors":"L. Rui, Lihui Peng","doi":"10.1109/IST.2017.8261466","DOIUrl":"https://doi.org/10.1109/IST.2017.8261466","url":null,"abstract":"The paper presents a capacitance sensor array for water leakage imaging inside porous slab. The modelling of the proposed capacitance sensor array is investigated, including the sensitivity map and electrical potential distribution inside the sensor. The simulation data based preliminary image reconstruction results by using the linear back projection (LBP), the projected Landweber iteration, and the total variation regularization, are presented and demonstrates that the proposed the capacitance sensor array is feasible for imaging of water leakage inside porous slab.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116070186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Wavelet domain based directional dictionaries for single image super-resolution 基于小波域的单幅图像超分辨率定向字典
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261523
Junaid Ahmed, B. Gao, G. Tian
{"title":"Wavelet domain based directional dictionaries for single image super-resolution","authors":"Junaid Ahmed, B. Gao, G. Tian","doi":"10.1109/IST.2017.8261523","DOIUrl":"https://doi.org/10.1109/IST.2017.8261523","url":null,"abstract":"This paper introduces wavelet domain-based multiple dictionary learning for single image super-resolution. A coupled dictionary learning mechanism is employed using sparsity with the desirable properties of the wavelet transform, such as directionality, analysis at many resolution levels, and persistence across scales. This approach ensures that coupling between signal features (at two consecutive levels) becomes more prominent. We design six pairs of coupled, low and high resolution wavelet sub-band dictionaries. The dictionaries are compact and directional. Super-resolution is achieved by using these low and high resolution dictionaries. Compared to state of the art algorithms, results show significant improvements for the reconstruction of low-resolution images.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128099615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Fast vehicle detection based on evolving convolutional neural network 基于进化卷积神经网络的快速车辆检测
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261505
Fengbin Zhu, Youfei Lu, Na Ying, G. Giakos
{"title":"Fast vehicle detection based on evolving convolutional neural network","authors":"Fengbin Zhu, Youfei Lu, Na Ying, G. Giakos","doi":"10.1109/IST.2017.8261505","DOIUrl":"https://doi.org/10.1109/IST.2017.8261505","url":null,"abstract":"With the rapid development of pattern recognition, computer vision and artificial intelligence technology, vehicle detection, traffic, and public safety, are core areas to extract direct benefits. To identify and locate a fast-moving vehicle, with high positional accuracy an evolving algorithm, based on convolutional neural networks, is proposed. Enhanced feature extraction is achieved by embedding our framework with a computationally cost-efficient proposal network to generate initial anchor boxes as well as to discard unlikely regions; feature fusion technology was used to extract hyper features, refine the identification and locate the vehicle, as well as improve the quality and accuracy of vehicle detection. Finally, we evaluated our network performance against the recent DETRAC benchmark [1] as well as using vehicle data sets collected by ourselves. The outcome of this study indicates a significant improvement over the state-of-the-art Faster RCNN by 9.61%, which fully highlights the effectiveness of the proposed algorithm.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132842139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 11
Localize car door handles with image segmentation and saliency detection 利用图像分割和显著性检测对车门把手进行定位
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261539
Fan Zhang, Mengchao Hao, Muyang Liu, Jinyu Yang
{"title":"Localize car door handles with image segmentation and saliency detection","authors":"Fan Zhang, Mengchao Hao, Muyang Liu, Jinyu Yang","doi":"10.1109/IST.2017.8261539","DOIUrl":"https://doi.org/10.1109/IST.2017.8261539","url":null,"abstract":"Importance of little objects in cars such as door handles is obvious, both in daily lives and in industrial manufacture. However, since the lack of the distinctive appearance and feature, obtaining the location of them is still remaining a challenge. This paper proposes an effective approach for the detection of the door handles of cars. The method innovatively combines frequency and spatial domains' algorithms to detect the location of little objects of cars in a relatively large image. To illustrate the method more concisely, our method localizes door handles through image segmentation and visual saliency detection. First, by segmenting the image we can remove the unnecessary area to improve the speed and accuracy of our approach. After finding the region of interest, our approach uses a visual saliency detection algorithm named Spectral Residual Approach which can get the location of door handles accurately. At last, the approach is tested by different kinds of images of vehicles. The results of the experiments show that our approach is obvious and practical.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133736675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Alzheimer's disease classification based on combination of multi-model convolutional networks 基于多模型卷积网络组合的阿尔茨海默病分类
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261566
Fan Li, D. Cheng, Manhua Liu
{"title":"Alzheimer's disease classification based on combination of multi-model convolutional networks","authors":"Fan Li, D. Cheng, Manhua Liu","doi":"10.1109/IST.2017.8261566","DOIUrl":"https://doi.org/10.1109/IST.2017.8261566","url":null,"abstract":"Alzheimer's disease (AD) is an irreversible neurodegenerative disorder with progressive impairment of memory and cognitive functions. It brings increasingly troubling in today's society. Its early diagnosis and warning are particularly important. Structural magnetic resonance images (MRI) play an important role to help understand the brain anatomical changes related to AD. Traditional methods are usually based on extraction of handcrafted features and training a classifier to distinguish AD from other groups. Motivated by the success of deep learning in image classification, this paper proposes a classification method based on combination of multimodel 3D convolutional networks to learn the various features from MR brain images. First, a deep 3D convolutional neural network (3D CNN) is built to hierarchically transform the MR image into more compact high-level features. Second, the multiscale 3D convolutional autoencoders (3D CAEs) are constructed to extract features from MR brain images. The features learned by these models are combined with the upper fully connected layers for image classification in AD diagnosis. The proposed method can automatically learn the generic features from the imaging data for classification without segmentations of brain tissues and regions. Our method is evaluated using T1-weighted MR brain images on 428 subjects including 199 AD patients and 229 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an accuracy of 88.31% for AD classification and an AUC (area under the ROC curve) of 92.73%, demonstrating the promising classification performances.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131913456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 49
An improved image processing method for particle measurement 一种改进的粒子测量图像处理方法
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261471
Yang Cai, M. Su
{"title":"An improved image processing method for particle measurement","authors":"Yang Cai, M. Su","doi":"10.1109/IST.2017.8261471","DOIUrl":"https://doi.org/10.1109/IST.2017.8261471","url":null,"abstract":"For the particle measurement under the condition of uneven illumination, defocus blur as well as consisting of touching particles, an effective analysis method was proposed in this paper. Firstly, through analyzing and determining the optimal imaging plane of particles, the level of defocus blur can be reduced, and then the influence of uneven illumination can also be eliminated by using an adaptive thresholding method, finally, with the aid of image reconstruction method to modify the Euclidean distance transform result of binary image and combined with the watershed transform, touching particles can be efficiently segmented, besides, which can also help to reduce the error rate during the segments of peanut-shaped particles. According to the experimental analysis, this proposed method can effectively reduce the analytical error of particle characteristics when compared with the conventional method.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124893392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Influence of ray-tracing step on aero-optics imaging deviation computation 射线跟踪步长对航空光学成像偏差计算的影响
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261482
Liang Xu, Deting Xue, X. Lv
{"title":"Influence of ray-tracing step on aero-optics imaging deviation computation","authors":"Liang Xu, Deting Xue, X. Lv","doi":"10.1109/IST.2017.8261482","DOIUrl":"https://doi.org/10.1109/IST.2017.8261482","url":null,"abstract":"Ray tracing is required in aero-optical imaging deviation computation, and the tracing step size is an influencing factor. In this paper, the Runge-Kutta method is used to complete the tracing. During the tracing process, the quadrilateral mesh interpolation is used. Based on the typical velocity Mach number 3 and attack angle 0 degree, the influence of tracing step size on imaging deviation is analyzed, and a series of typical data about different line-of-sight angles for different height are given. The results show that the smaller the step size is, the higher the ray-tracing accuracy well be, and a smaller step will cause an increase in tracing computations.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134621653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Correcting ionospheric and orbital errors in spacebome SAR differential interferograms 空间合成孔径雷达差分干涉图中电离层和轨道误差的校正
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261533
K. Hasni, Jie Chen, Guo Wei
{"title":"Correcting ionospheric and orbital errors in spacebome SAR differential interferograms","authors":"K. Hasni, Jie Chen, Guo Wei","doi":"10.1109/IST.2017.8261533","DOIUrl":"https://doi.org/10.1109/IST.2017.8261533","url":null,"abstract":"Ionospheric phase delay and orbital errors, are major limitations for precise deformation measurement in low frequencies SAR systems. The dispersive nature of the ionosphere introduces a shift in SAR images that is translated to differential interferograms. Orbital errors are basically a result of inaccurate baseline estimation, due the estimation model or non precise orbits. In this work, we present a combined method for correcting ionospheric and orbital errors in DInSAR, using the Split-Spectrum algorithm for ionospheric phase delay estimation and compensation. The orbital noise is modeled as non linear contribution taking into account the residual topography related to the used Digital Elevation Model (DEM). The methodology is applied on real data case to test its ability to compensate for these errors.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134460751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
A new regularization method for electrical impedance tomography 电阻抗层析成像的一种新的正则化方法
2017 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2017-10-01 DOI: 10.1109/IST.2017.8261554
B. Han, Yanbin Xu, F. Dong
{"title":"A new regularization method for electrical impedance tomography","authors":"B. Han, Yanbin Xu, F. Dong","doi":"10.1109/IST.2017.8261554","DOIUrl":"https://doi.org/10.1109/IST.2017.8261554","url":null,"abstract":"Regularization methods are good ways to address the ill-posed problem of the inverse problem of electrical impedance tomography (EIT). Common regularization methods such as Tikhonov, L1 norm and total variation (TV) regularization methods have their own inescapable problems, such as the over smoothness of reconstructed edges and the unstable solution due to measurement noise. In this paper, a new regularization method was proposed, which utilizes the total differences of conductivities of neighbored pixels (TDN) as penalty term. This method performed strong robustness against the boundary measurement noise, good ability to reserve the sharp edges as well as special capacity to reconstruct the accurate shape of square objects.","PeriodicalId":187213,"journal":{"name":"2017 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133541242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书