发布求助
文献互助 智能选刊 最新文献

2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)最新文献

筛选
英文 中文
Optimized fast Walsh-Hadamard transform on OpenCL-GPU and OpenCL-CPU 优化了OpenCL-GPU和OpenCL-CPU上的快速Walsh-Hadamard变换
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7820984
Pedro M. M. Pereira, Patrício Domingues, Nuno M. M. Rodrigues, S. Faria, G. Falcão
{"title":"Optimized fast Walsh-Hadamard transform on OpenCL-GPU and OpenCL-CPU","authors":"Pedro M. M. Pereira, Patrício Domingues, Nuno M. M. Rodrigues, S. Faria, G. Falcão","doi":"10.1109/IPTA.2016.7820984","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7820984","url":null,"abstract":"The Walsh-Hadamard transform plays a major role in many image and video coding algorithms. In one hand, its intensive use in these algorithms makes its acceleration a challenge, in order to speed-up the algorithm execution. On the other hand, the available fast implementations are not efficient across different platforms. In this work, a parallel-based implementation of the WHT is proposed for CPU and GPU platforms using the OpenCL standard. OpenCL achieves portability at code level, but its performance suffers when the same code is used for CPUs and GPUs. To achieve top performance, we propose two WHT versions: OpenCL-GPU for GPUs and OpenCL-CPU for CPUs. Broadly, OpenCL-GPU executed on a GPU runs faster than OpenCL-CPU executed on a multicore CPU, with speedups that range from 120.87 to 1016.35. However, OpenCL-GPU performance drops substantially when ran on a multicore CPU machine, where OpenCL-CPU achieves higher performance, as it exploits the OpenCL support for SIMD instructions.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130203931","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
A perceptual-based rate control for HEVC 基于感知的HEVC速率控制
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7820958
Aisheng Yang, H. Zeng, Lin Ma, J. Chen, C. Cai, K. Ma
{"title":"A perceptual-based rate control for HEVC","authors":"Aisheng Yang, H. Zeng, Lin Ma, J. Chen, C. Cai, K. Ma","doi":"10.1109/IPTA.2016.7820958","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7820958","url":null,"abstract":"In this paper, a perceptual-based rate control algorithm for the high efficiency video coding (HEVC) is proposed. Since the human visual system (HVS) is highly sensitive to edge information inherited in image and video contents, gradient magnitude is considered a very effective attribute on the computation of the spatial perceptual characteristics (SPC) and the temporal perceptual characteristic (TPC). The latter is further computed based on the gradient magnitude similarity deviation (GMSD). The combined perceptual characteristic of SPC and TPC is then used to guide the bit allocation process for each CTU. Experimental results have clearly shown that the proposed perceptual rate control scheme can achieve superior perceptual coding performance, compared with the original R-A rate control adopted in the HEVC.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124940861","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: 8
Score thresholding for accurate instance classification in multiple instance learning 多实例学习中用于准确实例分类的分数阈值
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7821026
M. Carbonneau, Eric Granger, G. Gagnon
{"title":"Score thresholding for accurate instance classification in multiple instance learning","authors":"M. Carbonneau, Eric Granger, G. Gagnon","doi":"10.1109/IPTA.2016.7821026","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7821026","url":null,"abstract":"Multiple instance learning (MIL) is a form of weakly supervised learning for problems in which training instances are arranged into bags, and a label is provided for whole bags but not for individual instances. Most proposed MIL algorithms focus on bag classification, but more recently, the classification of individual instances has attracted the attention of the pattern recognition community. While these two tasks are similar, there are important differences in the consequences of instance misclassification. In this paper, the scoring function learned by MIL classifiers for the bag classification task is exploited for instance classification by adjusting the decision threshold. A new criterion for the threshold adjustment is proposed and validated using 7 reference MIL algorithms on 3 real-world data sets from different application domains. Experiments show considerable improvements in accuracy over these algorithms for instance classification. In some applications, the unweighted average recall increases by as much as 18%, while the Fi-score increases by 12%.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121951399","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
On the use of skin texture features for gender recognition: An experimental evaluation 利用皮肤纹理特征进行性别识别:一项实验评估
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7821018
F. Bianconi, F. Smeraldi, M. Abdollahyan, P. Xiao
{"title":"On the use of skin texture features for gender recognition: An experimental evaluation","authors":"F. Bianconi, F. Smeraldi, M. Abdollahyan, P. Xiao","doi":"10.1109/IPTA.2016.7821018","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7821018","url":null,"abstract":"Skin appearance is almost universally the object of gender-related expectations and stereotypes. This not with standing, remarkably little work has been done on establishing quantitatively whether skin texture can be used for gender discrimination. We present a detailed analysis of the skin texture of 43 subjects based on two complementary imaging modalities afforded by a visible-light dermoscope and the recently developed Epsilon sensor for capacitive imaging. We consider an array of established texture features in combination with two supervised classification techniques (1-NN and SVM) and a state-of-the-art unsupervised approach (t-SNE). A statistical analysis of the results suggests that skin microtexture carries very little information on gender.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121227256","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: 10
Fast HEVC CU/PU mode decision based on ANN and texture analysis 基于神经网络和纹理分析的HEVC CU/PU模式快速决策
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7821003
Shuaihu Zhou, Zuochang Ye, Yan Wang
{"title":"Fast HEVC CU/PU mode decision based on ANN and texture analysis","authors":"Shuaihu Zhou, Zuochang Ye, Yan Wang","doi":"10.1109/IPTA.2016.7821003","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7821003","url":null,"abstract":"HEVC (high efficiency video coding), as the latest video coding standard, is more efficient than H.264/AVC, nevertheless it also brings in a very high computational complexity. To reduce the time of CU (coding unit) splitting or PU (prediction unit) mode deciding, a fast algorithm based on ANN (artificial neural network) and texture analysis is proposed in this paper. First, we acquire and then label the CUs of the training set with “split” and “unsplit” according to the quad-tree CU depth. Second, the texture features of “split” and “unsplit” CUs are quantified and compiled, based on which we can set the texture thresholds to judge whether or not to split the current CU or which prediction mode should be taken preliminarily. Finally, in terms of the CUs we can't judge from texture, we use ANN or the original algorithm of HM (HEVC test model) software to decide. Compared to HM15.0, the proposed algorithm can save 51.85% encoding time on average with negligible coding efficiency loss.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115187570","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
Improving curve skeletons of tubular volumes 改善管状体积的曲线骨架
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7820965
Florent Grélard, F. Baldacci, A. Vialard, J. Domenger
{"title":"Improving curve skeletons of tubular volumes","authors":"Florent Grélard, F. Baldacci, A. Vialard, J. Domenger","doi":"10.1109/IPTA.2016.7820965","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7820965","url":null,"abstract":"Curve-skeletons encode both geometrical and topological information of 3D volumes (sets of voxels), and are key to many applications. However, due to the complexity and variability of the shapes, there is a variety of algorithms yielding skeletons suitable for certain objects, but inappropriate for others. In this article, we are interested in filtering skeletons of digital tubular objects with varying-diameter and junctions, resulting from the segmentation of organs (airway-trees, vessels). Existing skeletons might not be centered or contain faulty branches. For medical applications such as virtual endoscopy or cross-section estimation, post-processing steps are applied in order to prune the spurious branches and smooth the skeleton. State-of-the-art methods for pruning are insufficient with respect to varying-diameter tubes. We propose a new approach to prune irrelevant skeleton branches, and to recenter the skeleton inside the shape.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128517299","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
Multi-modal subspace learning with dropout regularization for cross-modal recognition and retrieval 基于dropout正则化的多模态子空间学习跨模态识别与检索
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7821032
G. Cao, Muhammad-Adeel Waris, Alexandros Iosifidis, M. Gabbouj
{"title":"Multi-modal subspace learning with dropout regularization for cross-modal recognition and retrieval","authors":"G. Cao, Muhammad-Adeel Waris, Alexandros Iosifidis, M. Gabbouj","doi":"10.1109/IPTA.2016.7821032","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7821032","url":null,"abstract":"There has been a surge of efforts in cross-modal recognition and retrieval in recent multimedia research. Towards this goal, we investigate a multi-modal subspace learning algorithm together with the Dropout regularizer. Inspired by the regularization for neural networks, we propose to aritificially remove the effect of certain amount of feature bins using the probabilistic approach to prevent the linear subspace learning from over-fitting. The novel regularizer is well integrated into the multi-modal learning algorithm which maximizes the between-class scatter while minimizing the within-class scatter in the projected latent space. The new objective function can be solved efficiently as the generalized eigenvalue problem. Experimental results have shown that superior performance can be obtained in both face-sketch recognition and cross-modal retrieval applications.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121466184","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
De-identifying people in videos using neural art 用神经艺术去识别视频中的人
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7820987
K. Brkić, I. Sikirić, T. Hrkać, Z. Kalafatić
{"title":"De-identifying people in videos using neural art","authors":"K. Brkić, I. Sikirić, T. Hrkać, Z. Kalafatić","doi":"10.1109/IPTA.2016.7820987","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7820987","url":null,"abstract":"We propose a computer vision-based de-identification pipeline that enables automated segmentation of humans in videos and effective protection of their identities. Due to the ubiquity of video surveillance, many jurisdictions implement strict regulations for the protection of personal data in publicly collected video sequences, requiring the data to be de-identified. However, soft biometric and non-biometric features like clothing, hair color, personal items, skin marks, etc., are often overlooked in the process. Assuming a surveillance scenario, we combine GMM-based background subtraction with an improved version of the GrabCut algorithm to find and segment pedestrians. We use the responses of a deep neural network to de-identify soft and non-biometric features through style mixing with images of other pedestrians. Our method produces de-identified versions of the input frames while preserving the naturalness and utility of the de-identified data.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134331509","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
Automatic modeling and classification of vitreomacular traction pathology stages 玻璃体黄斑牵引病理分期的自动建模与分类
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7821004
Agnieszka Stankiewicz, T. Marciniak, A. Dabrowski, M. Stopa, Piotr Rakowicz, Elzbieta Marciniak
{"title":"Automatic modeling and classification of vitreomacular traction pathology stages","authors":"Agnieszka Stankiewicz, T. Marciniak, A. Dabrowski, M. Stopa, Piotr Rakowicz, Elzbieta Marciniak","doi":"10.1109/IPTA.2016.7821004","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7821004","url":null,"abstract":"Retinal pathologies that are detected too late and/or left untreated can seriously damage eyesight. It is important to monitor the retina and react to any pathological changes. A fast, accurate, non-invasive, and even three-dimensional retina examination is the optical coherence tomography (OCT). In this paper we propose a new automated classification method for evaluation of vitreomacular interface (VRI) in human eyes. We present an approach for modelling changes in retina structure during the progression of vitreomacular traction (VMT) pathology. Presented experiments were performed on volumetric data acquired from adult patients with the use of Avanti RTvue device. Advanced digital image processing algorithms were subsequently applied to each OCT cross-section (B-scan) for image denoising and flattening, as well as retina layers segmentation. The proposed solution has a good accuracy and almost all subjects were successfully classified into one of 4 groups corresponding to various stages of VMT. The developed models of VMT stages show a high potential of the proposed method to support ophthalmologists in making appropriate clinical decisions.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131799906","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
Segmentation of retinal vessels in adaptive optics images for assessment of vasculitis 自适应光学图像中视网膜血管的分割用于血管炎的评估
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) Pub Date : 2016-12-01 DOI: 10.1109/IPTA.2016.7821037
Marthe Lagarrigue-Charbonnier, F. Rossant, I. Bloch, M. Errera, M. Pâques
{"title":"Segmentation of retinal vessels in adaptive optics images for assessment of vasculitis","authors":"Marthe Lagarrigue-Charbonnier, F. Rossant, I. Bloch, M. Errera, M. Pâques","doi":"10.1109/IPTA.2016.7821037","DOIUrl":"https://doi.org/10.1109/IPTA.2016.7821037","url":null,"abstract":"In this paper we propose a new method for segmenting retinal vessels in adaptive optics images. This method is particularly dedicated for segmenting vessels with significant morphological alterations due to vasculitis, but it is also accurate for vessels with moderate or without alteration. It relies on a pre-segmentation step which is crucial for the robustness and accuracy of the results. This step is based on a specific morphological processing of isolines of the original image: they constitute of good basis for the segmentation because they are disposed along the wall borders of the vessels. Regularization is then performed using active contour model embedding a parallelism constraint. This novel model allows precise segmenting inner and outer walls of the vessel. In particular it is more accurate in the case of vasculitis than the existing methods. This is the only method that allows quantification. The results and the runtime make it suitable for clinical use.","PeriodicalId":123429,"journal":{"name":"2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124798269","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