Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing最新文献

筛选
英文 中文
Automatic Detection of Blood Vessels and Classification in Retinal Images for Diabetic Retinopathy Diagnosis with Application of Convolution Neural Network 基于卷积神经网络的糖尿病视网膜病变视网膜图像血管自动检测与分类
N. S. P. Kazakh-British, A. Pak, D. Abdullina
{"title":"Automatic Detection of Blood Vessels and Classification in Retinal Images for Diabetic Retinopathy Diagnosis with Application of Convolution Neural Network","authors":"N. S. P. Kazakh-British, A. Pak, D. Abdullina","doi":"10.1145/3290589.3290596","DOIUrl":"https://doi.org/10.1145/3290589.3290596","url":null,"abstract":"Described for the first time by MacKenzie (1879), diabetic retinopathy (DR) and today is the most common cause of blindness among persons of working age in most countries of the world. Prevention of DR is the early detection of a violation of morphology and a deterioration in the light sensitivity of the retina associated with this disease. To do this, highly informative methods of non-invasive retinal research are needed, with predictive capabilities. In this article, we propose an autonomous algorithm for such diagnostics, based on the training of the Artificial Neural Network (ANN) and the preprocessing of the image by an anisotropic diffusion filter. It allows not only to detect pathologies moreover to provide them with probabilistic evaluation of a possible variant of the disease.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134456369","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: 4
A New Fast Multi-Context Method for Lossless Image Coding 一种新的快速多上下文无损图像编码方法
G. Ulacha, R. Stasinski
{"title":"A New Fast Multi-Context Method for Lossless Image Coding","authors":"G. Ulacha, R. Stasinski","doi":"10.1145/3290589.3290600","DOIUrl":"https://doi.org/10.1145/3290589.3290600","url":null,"abstract":"A new efficient and fast context lossless image coding method is presented in the paper, named Multi-ctx. High performance is obtained due to the fact that predictors are chosen from a very large database. On the other hand, simple rules determining contexts result in low computational complexity of the method. The technique can be easily adapted to specific class of applications, as the algorithm can be trained on a set of exemplary images. For the purpose of proving its potential it has been trained on a set of 45 images of various type, then its performance compared to that of some widely used fast techniques. Indeed, the new method appears to be the best, even better than CALIC approach.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134494902","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
Pedestrian Detection based on Reduced High-Dimensional Distinctive Feature using Deep Neural Network 基于深度神经网络的降维高维显著特征行人检测
H. Song, K. Choi
{"title":"Pedestrian Detection based on Reduced High-Dimensional Distinctive Feature using Deep Neural Network","authors":"H. Song, K. Choi","doi":"10.1145/3290589.3290601","DOIUrl":"https://doi.org/10.1145/3290589.3290601","url":null,"abstract":"Pedestrian detection is an essential and significant research topic due to its diverse applications in the area of safety systems. The distinctiveness is detected by the following three steps. Firstly, images are represented by their respective co-occurrence matrices, which are vectorized by using the bag of visual words (BoVW) framework. Secondly, their weights are calculated from the histograms of visual words of each class. Finally, computed weights are applied to the testing image set as the distinctiveness of visual words. The fully connected Multi-Layer Perceptron (MLP) is used as classification method in our system, which has limited performance. This paper introduces a combination of principle component analysis (PCA), guided filtering, deeplearning architecture into visual data classification. In detail, as a mature dimension reduction architecture, PCA is capable of reducing the redundancy of multi-dimensional information. The proposed method is compared with the MLP using the Caltech 256 datasets, with the following classes: pedestrians, cars, motorbikes and airplanes. The experimental results show that the proposed method outperforms current methods in predicting pedestrians and transportation objects. It yields an average accuracy of 96.50%, which is approximately 8.5% more than the compared state-of-the-art.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131680488","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
Facial-based Intrusion Detection System with Deep Learning in Embedded Devices 嵌入式设备中基于人脸的深度学习入侵检测系统
G. Amato, F. Carrara, F. Falchi, C. Gennaro, C. Vairo
{"title":"Facial-based Intrusion Detection System with Deep Learning in Embedded Devices","authors":"G. Amato, F. Carrara, F. Falchi, C. Gennaro, C. Vairo","doi":"10.1145/3290589.3290598","DOIUrl":"https://doi.org/10.1145/3290589.3290598","url":null,"abstract":"With the advent of deep learning based methods, facial recognition algorithms have become more effective and efficient. However, these algorithms have usually the disadvantage of requiring the use of dedicated hardware devices, such as graphical processing units (GPUs), which pose restrictions on their usage on embedded devices with limited computational power. In this paper, we present an approach that allows building an intrusion detection system, based on face recognition, running on embedded devices. It relies on deep learning techniques and does not exploit the GPUs. Face recognition is performed using a knn classifier on features extracted from a 50-layers Residual Network (ResNet-50) trained on the VGGFace2 dataset. In our experiment, we determined the optimal confidence threshold that allows distinguishing legitimate users from intruders. In order to validate the proposed system, we created a ground truth composed of 15,393 images of faces and 44 identities, captured by two smart cameras placed in two different offices, in a test period of six months. We show that the obtained results are good both from the efficiency and effectiveness perspective.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123466012","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
Enhanced Stereovision Processing for Improved 3D Object Reconstruction 增强立体视觉处理改进三维物体重建
Antony Mansi, Walid B. Hussein
{"title":"Enhanced Stereovision Processing for Improved 3D Object Reconstruction","authors":"Antony Mansi, Walid B. Hussein","doi":"10.1145/3290589.3290604","DOIUrl":"https://doi.org/10.1145/3290589.3290604","url":null,"abstract":"Whenever there is photogrammetry or computer vision, image processing techniques take place; since both of sciences depend on extract information from an image. Moreover, it is essential to apply these image processing techniques to obtain the depth information of the scene objects and then construct their 3D view. Researchers have been working in the stereovision technique to reconstruct a 3D object with different approaches, some were for specific applications, and others were improvements in the method itself. In this paper, an enhanced stereo imaging technique is proposed to increase the accuracy in the 3D object construction. Starting from the image acquisition to the rectification process, then passing through stereo matcher between the two stereo images to produce a robust disparity map which is put into a refinement process for improvements. Finally, the depth view is constructed with a superior accuracy in comparison to the commonly applied stereo imaging approaches.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125650973","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
Autonomous Vehicle: The Architecture Aspect of Self Driving Car 自动驾驶汽车:自动驾驶汽车的架构方面
Farzeen Munir, Shoaib Azam, M. Hussain, Ahmed Muqeem Sheri, M. Jeon
{"title":"Autonomous Vehicle: The Architecture Aspect of Self Driving Car","authors":"Farzeen Munir, Shoaib Azam, M. Hussain, Ahmed Muqeem Sheri, M. Jeon","doi":"10.1145/3290589.3290599","DOIUrl":"https://doi.org/10.1145/3290589.3290599","url":null,"abstract":"Self-driving cars have received a lot of attention in recent years and many stakeholders like Google, Uber, Tesla, and so forth have invested a lot in this area and developed their own autonomous driving car platforms. The challenge to make an autonomous car is not only the stringent performance but also the safety of the passengers and pedestrians. Even with the development of technologies, autonomous driving is still an active research area and still requires a lot of experimentations and making architecture entirely autonomous. The intriguing area of self-driving car motivates us to build an autonomous driving platform. In this paper, we discuss the architecture of the self-driving car and its software components that include localization, detection, motion planning and mission planning. We also highlight the hardware modules that are responsible for controlling the car. The autonomous driving is running state-of-the-art algorithms used in localization, detection, mission and motion planning.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121222958","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: 29
Multi-mode Emotion Recognition Based on Generalized Discriminative Canonical Correlation Analysis 基于广义判别典型相关分析的多模式情绪识别
Lijiang Chen, Wentao Dou, Xia Mao
{"title":"Multi-mode Emotion Recognition Based on Generalized Discriminative Canonical Correlation Analysis","authors":"Lijiang Chen, Wentao Dou, Xia Mao","doi":"10.1145/3290589.3290590","DOIUrl":"https://doi.org/10.1145/3290589.3290590","url":null,"abstract":"In recent years, emotion recognition encounters difficulties: accuracy and robustness. In order to improve performance of the emotion recognition system, here we present a novel multimode emotion recognition system, including visual and audio information. Meanwhile, a feature fusion algorithm named Generalized discriminative canonical correlation analysis (GDCCA) is proposed and utilized in this system. First, we extract video image features through 2D Gabor wavelet and obtain the statistical and annotation features of audio. Then the above features are fused by GDCCA to be a fusion feature which is fed into SVM classifier to get the recognition results. Finally, the novel emotion recognition system is applied on the database of BUBE (Beihang University Biomodal Emotion Database) and the experiments provide extensive illustrations of the systems performance.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117035817","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
Constrained Attribute Selection for Stress Detection Based on Physiological Signals 基于生理信号的应力检测约束属性选择
V. Anzova, T. Ganchev
{"title":"Constrained Attribute Selection for Stress Detection Based on Physiological Signals","authors":"V. Anzova, T. Ganchev","doi":"10.1145/3290589.3290597","DOIUrl":"https://doi.org/10.1145/3290589.3290597","url":null,"abstract":"We present a constrained attribute selection method that makes use of feature assessment based on the Fisher's separation criterion followed by variety reduction post-processing. The post-processing incorporates task-specific constrain into the feature selection process, as this is expected to facilitate the subsequent data modeling and classification stages. Here we validate the proposed method in an experimental setup oriented towards acute stress detection based on physiological signals. The experimental results support that the proposed method brings advantage, when compared to three other cases: (i) the full set of features, (ii) a subset selected based on prior knowledge, (iii) and a subset selected based solely on Fisher's separation criterion.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"1 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113932795","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: 7
Design of FIR Filter Based on FPGA 基于FPGA的FIR滤波器设计
Cai-hong Liu, Shuang-liang Tian, Zi-long Liu
{"title":"Design of FIR Filter Based on FPGA","authors":"Cai-hong Liu, Shuang-liang Tian, Zi-long Liu","doi":"10.1145/3290589.3290602","DOIUrl":"https://doi.org/10.1145/3290589.3290602","url":null,"abstract":"The filter has become an important device when people use for communication and deal with all kinds of signals. FPGA is very suitable for digital signal processing. And it is very good for designing digital filter by using FPGA. A FIR digital filter is designed based on FPGA in this paper, It can assure arbitrary amplitude-frequency characteristic. The hardware design is from Altera company. AD and DA is used in the system because the input and output of this system is digital signal. In order to achieve a high transmission speed, the design was simulated using the System Generator for FPGA. The use of simulation can greatly reduce the cost of the experiment.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130165134","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: 4
Query Tree with Knowledge-based Splitting for RFID Tag Identification 基于知识分割的RFID标签识别查询树
Y. Lai, R. Jayadi, Sheng-Chi Huang, Yen-Hung Chen
{"title":"Query Tree with Knowledge-based Splitting for RFID Tag Identification","authors":"Y. Lai, R. Jayadi, Sheng-Chi Huang, Yen-Hung Chen","doi":"10.1145/3290589.3290592","DOIUrl":"https://doi.org/10.1145/3290589.3290592","url":null,"abstract":"In Radio Frequency Identification (RFID) systems, the reader identifies tags through communication over a shared wireless channel. When multiple tags transmit their IDs simultaneously, their signals collide, prolonging the identification delay. Currently, there are many anti-collision protocols and one important approach of them is Query Tree (QT) protocol. In general applications, an RFID system has a database, which owns all tag IDs that possibly appear. Thus, considering the case that the RFID system has this knowledge, we propose a Query Tree with Knowledge-based Splitting (QTKS) protocol. From the known database, QTKS constructs a knowledge-based query tree, which stores queries that can more quickly identify appearing tags, which belong to possible tags in the database. The simulation results show that QTKS significantly outperforms related previous work. Compared to QT, QTKS can reduce its identification delay by 52%.","PeriodicalId":353605,"journal":{"name":"Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125133481","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: 4
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
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