首页 > 最新文献

2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)最新文献

英文 中文
Facial expression invariant 3D face reconstruction from a single image using Deformable Generic Elastic Models 使用可变形的通用弹性模型从单个图像重建面部表情不变的三维人脸
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6779940
A. Moeini, K. Faez, Hosein Moeini
In this paper, we propose an efficient method to reconstructing the 3D models of a human face from a single 2D face image robustness under a variety facial expressions using the Deformable Generic Elastic Model (D-GEM). We extended the Generic Elastic Model (GEM) approach and combined it with statistical information of the human face and deformed generic depth models by computing the distance around face lips. Particularly, we demonstrate that D-GEM can approximate the 3D shape of the input face image more accurately, achieving a better and higher quality of 3D face modeling and reconstruction robustness under a variety of facial expressions compared to the original GEM and Gender and Ethnicity-GEM (GE-GEM) approach. It has been tested on an available 3D face database, demonstrating its accuracy and robustness compared to the GEM and GE-GEM approach under a variety of imaging conditions, including facial expressions, gender and ethnicity.
本文提出了一种利用可变形通用弹性模型(D-GEM)在多种面部表情下从单个二维人脸图像鲁棒重建人脸三维模型的有效方法。我们扩展了通用弹性模型(GEM)方法,将其与人脸统计信息和变形的通用深度模型相结合,通过计算人脸嘴唇周围的距离。特别是,我们证明了D-GEM可以更准确地近似输入人脸图像的三维形状,与原始GEM和Gender and Ethnicity-GEM (GE-GEM)方法相比,在各种面部表情下实现了更好和更高质量的三维人脸建模和重建鲁棒性。它已经在一个可用的3D人脸数据库上进行了测试,与GEM和GE-GEM方法相比,在各种成像条件下,包括面部表情、性别和种族,证明了它的准确性和稳健性。
{"title":"Facial expression invariant 3D face reconstruction from a single image using Deformable Generic Elastic Models","authors":"A. Moeini, K. Faez, Hosein Moeini","doi":"10.1109/IRANIANMVIP.2013.6779940","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6779940","url":null,"abstract":"In this paper, we propose an efficient method to reconstructing the 3D models of a human face from a single 2D face image robustness under a variety facial expressions using the Deformable Generic Elastic Model (D-GEM). We extended the Generic Elastic Model (GEM) approach and combined it with statistical information of the human face and deformed generic depth models by computing the distance around face lips. Particularly, we demonstrate that D-GEM can approximate the 3D shape of the input face image more accurately, achieving a better and higher quality of 3D face modeling and reconstruction robustness under a variety of facial expressions compared to the original GEM and Gender and Ethnicity-GEM (GE-GEM) approach. It has been tested on an available 3D face database, demonstrating its accuracy and robustness compared to the GEM and GE-GEM approach under a variety of imaging conditions, including facial expressions, gender and ethnicity.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116670544","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: 5
Warped document restoration by recovering shape of the surface 通过恢复表面形状来恢复扭曲的文档
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6779991
Maryam Shamqoli, H. Khosravi
Document images produced by scanner or digital camera, usually suffer from two main distortions: geometric and photometric. Both of them deteriorate the performance of OCR systems. In this paper, we present a novel method to compensate for undesirable geometric distortions aiming to improve OCR results. Our methodology is based on low cost transformation which addresses the projection of curve line to 2-D rectangular area combined with finding text lines. Experimental results on several document images, indicate the effectiveness of the proposed method.
由扫描仪或数码相机产生的文件图像通常有两种主要的畸变:几何畸变和光度畸变。两者都会降低OCR系统的性能。在本文中,我们提出了一种新的方法来补偿不良的几何畸变,旨在提高OCR的结果。我们的方法是基于低成本的转换,解决了曲线到二维矩形区域的投影,并结合了查找文本线。在多幅文档图像上的实验结果表明了该方法的有效性。
{"title":"Warped document restoration by recovering shape of the surface","authors":"Maryam Shamqoli, H. Khosravi","doi":"10.1109/IRANIANMVIP.2013.6779991","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6779991","url":null,"abstract":"Document images produced by scanner or digital camera, usually suffer from two main distortions: geometric and photometric. Both of them deteriorate the performance of OCR systems. In this paper, we present a novel method to compensate for undesirable geometric distortions aiming to improve OCR results. Our methodology is based on low cost transformation which addresses the projection of curve line to 2-D rectangular area combined with finding text lines. Experimental results on several document images, indicate the effectiveness of the proposed method.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125906259","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: 5
Calibrate kinect to use in computer vision, simplified and precise 校准kinect用于计算机视觉,简化和精确
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6780001
M. Davoodianidaliki, M. Saadatseresht
Visual sensors, active or passive, play an important role in computer vision and in visual sensors, calibration is of utmost importance. Kinect as a new developed sensor for use as a Natural User Interface is being utilized in different fields especially CV. This integrated system beside other sensors, contains two visual sensors of active and passive that demands a process of calibration. Among different methods of calibration, image-based calibration for data-fusion purposes, has lowest computational cost and can be quite simple and precise. In this study, 2 different methods, consisting of a physical interior distortion model and an eight parameters registration equation have been proposed. Besides computed parameters and their precision, a table of distortion values is introduced that can be used in registration level. Finally to evaluate chosen proposed method, a simple registration of processed data is utilized and results are discussed.
无论是主动式还是被动式视觉传感器,在计算机视觉中都扮演着重要的角色,而在视觉传感器中,校准是至关重要的。Kinect作为一种新开发的传感器,用于自然用户界面,正被应用于不同的领域,尤其是CV。除了其他传感器外,该集成系统还包含两个需要校准过程的主动和被动视觉传感器。在各种标定方法中,以数据融合为目的的基于图像的标定计算成本最低,且简单、精确。本文提出了两种不同的方法,即物理内部畸变模型和八参数配准方程。除了计算出的参数及其精度外,还介绍了可用于配准级的失真值表。最后对所选择的方法进行评价,对处理后的数据进行简单的配准,并对结果进行了讨论。
{"title":"Calibrate kinect to use in computer vision, simplified and precise","authors":"M. Davoodianidaliki, M. Saadatseresht","doi":"10.1109/IRANIANMVIP.2013.6780001","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6780001","url":null,"abstract":"Visual sensors, active or passive, play an important role in computer vision and in visual sensors, calibration is of utmost importance. Kinect as a new developed sensor for use as a Natural User Interface is being utilized in different fields especially CV. This integrated system beside other sensors, contains two visual sensors of active and passive that demands a process of calibration. Among different methods of calibration, image-based calibration for data-fusion purposes, has lowest computational cost and can be quite simple and precise. In this study, 2 different methods, consisting of a physical interior distortion model and an eight parameters registration equation have been proposed. Besides computed parameters and their precision, a table of distortion values is introduced that can be used in registration level. Finally to evaluate chosen proposed method, a simple registration of processed data is utilized and results are discussed.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128286439","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 rank based ensemble classifier for image classification using color and texture features 一种基于秩的集成分类器,利用颜色和纹理特征进行图像分类
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6780008
F. Ahmadi, M. Sigari, M. Shiri
This paper presents a color image classification method using rank based ensemble classifier. In this paper, we use color histogram in different color spaces and Gabor wavelet to extract color and texture features respectively. These features are classified by two classifiers: Nearest Neighbor (NN) and Multi Layer Perceptron (MLP). In the proposed approach, each set of features are classified by each classifier to generate a rank list of length three. Therefore, we have some rank list for different combination of feature sets and classifiers. The generated rank lists present an ordered list of class labels that the classifier believes the input image is related to those classes in order of priority. To combine the outputs (rank list) of each classifier, simple and weighted majority vote are used. Experiments show the proposed system with weighted majority vote achieves a recall and precision of 86.2 % and 86.16% respectively. Our proposed system has higher efficiency in comparison of other systems.
提出了一种基于秩的集成分类器的彩色图像分类方法。在本文中,我们分别使用不同颜色空间的颜色直方图和Gabor小波来提取颜色和纹理特征。这些特征通过两种分类器进行分类:最近邻(NN)和多层感知器(MLP)。在该方法中,每个分类器对每组特征进行分类,生成长度为3的秩表。因此,对于不同的特征集和分类器组合,我们有一些排序表。生成的秩列表呈现一个有序的类标签列表,分类器认为输入图像按优先级顺序与这些类相关。为了组合每个分类器的输出(排名列表),使用简单和加权多数投票。实验表明,采用加权多数投票方法的系统的查全率和查准率分别达到86.2%和86.16%。与其他系统相比,我们提出的系统具有更高的效率。
{"title":"A rank based ensemble classifier for image classification using color and texture features","authors":"F. Ahmadi, M. Sigari, M. Shiri","doi":"10.1109/IRANIANMVIP.2013.6780008","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6780008","url":null,"abstract":"This paper presents a color image classification method using rank based ensemble classifier. In this paper, we use color histogram in different color spaces and Gabor wavelet to extract color and texture features respectively. These features are classified by two classifiers: Nearest Neighbor (NN) and Multi Layer Perceptron (MLP). In the proposed approach, each set of features are classified by each classifier to generate a rank list of length three. Therefore, we have some rank list for different combination of feature sets and classifiers. The generated rank lists present an ordered list of class labels that the classifier believes the input image is related to those classes in order of priority. To combine the outputs (rank list) of each classifier, simple and weighted majority vote are used. Experiments show the proposed system with weighted majority vote achieves a recall and precision of 86.2 % and 86.16% respectively. Our proposed system has higher efficiency in comparison of other systems.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128800179","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
3D pooling on local space-time features for human action recognition 基于局部时空特征的三维池化人体动作识别
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6779992
Najme Hadibarhaghtalab, Z. Azimifar
Successful approaches use local space-time features for human action recognition task including hand designed features or learned features. However these methods need a wise technique to encode local features to make a global representation for video. For this, some methods use K-means vector quantization to histogram each video as a bag of word. Pooling is a way used for global representation of an image. This method pools the local image feature over some image neighborhood. In this paper we extend pooling method called 3D pooling for global representation of video. 3D pooling represents each video by concatenating pooled feature vectors achieved from 8 equal regions of video. We also applied stacked convolutional ISA as local feature extractor. We evaluated our method on KTH data set and got our best result using max pooling. It improves the performance of highly demanded earlier methods.
成功的方法利用局部时空特征来完成人类动作识别任务,包括手工设计特征或学习特征。然而,这些方法需要一种明智的技术来对局部特征进行编码,以便对视频进行全局表示。为此,一些方法使用k均值矢量量化来将每个视频作为一个词包进行直方图。池化是一种用于图像全局表示的方法。该方法将局部图像特征集中在一些图像邻域上。本文将池化方法扩展为3D池化,用于视频的全局表示。3D池化通过连接从8个相等的视频区域获得的池化特征向量来表示每个视频。我们还应用了堆叠卷积ISA作为局部特征提取器。我们在KTH数据集上评估了我们的方法,并使用max pooling获得了最好的结果。它提高了高要求的早期方法的性能。
{"title":"3D pooling on local space-time features for human action recognition","authors":"Najme Hadibarhaghtalab, Z. Azimifar","doi":"10.1109/IRANIANMVIP.2013.6779992","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6779992","url":null,"abstract":"Successful approaches use local space-time features for human action recognition task including hand designed features or learned features. However these methods need a wise technique to encode local features to make a global representation for video. For this, some methods use K-means vector quantization to histogram each video as a bag of word. Pooling is a way used for global representation of an image. This method pools the local image feature over some image neighborhood. In this paper we extend pooling method called 3D pooling for global representation of video. 3D pooling represents each video by concatenating pooled feature vectors achieved from 8 equal regions of video. We also applied stacked convolutional ISA as local feature extractor. We evaluated our method on KTH data set and got our best result using max pooling. It improves the performance of highly demanded earlier methods.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128493258","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
An optimal prediction based reversible image watermarking in Hadamard domain 基于最优预测的Hadamard域可逆图像水印
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6780020
Zahra Pakdaman, S. Saryazdi
This paper presents a reversible watermarking scheme based on a reversible Hadamarh Transform. In the proposed method, the watermark is embedded using the prediction error of Hadamard coefficients. To achieve a more accurate prediction, a Gravitational Search Algorithm (GSA) is used to optimize the prediction coefficients. The proposed method does not need any location map. This property leads to increase the capacity as well as the quality of the watermarked image. To evaluate the performance of the proposed method, a comparative experiment with some well-known reversible methods is performed. The obtained results confirm the efficiency of the proposed method.
提出了一种基于可逆Hadamarh变换的可逆水印方案。该方法利用Hadamard系数的预测误差嵌入水印。为了获得更准确的预测结果,采用重力搜索算法(GSA)对预测系数进行优化。该方法不需要任何位置地图。这一特性不仅提高了水印图像的容量,而且提高了水印图像的质量。为了评估该方法的性能,与一些已知的可逆方法进行了对比实验。所得结果证实了该方法的有效性。
{"title":"An optimal prediction based reversible image watermarking in Hadamard domain","authors":"Zahra Pakdaman, S. Saryazdi","doi":"10.1109/IRANIANMVIP.2013.6780020","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6780020","url":null,"abstract":"This paper presents a reversible watermarking scheme based on a reversible Hadamarh Transform. In the proposed method, the watermark is embedded using the prediction error of Hadamard coefficients. To achieve a more accurate prediction, a Gravitational Search Algorithm (GSA) is used to optimize the prediction coefficients. The proposed method does not need any location map. This property leads to increase the capacity as well as the quality of the watermarked image. To evaluate the performance of the proposed method, a comparative experiment with some well-known reversible methods is performed. The obtained results confirm the efficiency of the proposed method.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124530145","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
A novel steganography approach for 3D polygonal meshes using Surfacelet Transform 一种基于曲面小波变换的三维多边形网格隐写方法
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6780000
H. Kaveh, M. Moin, F. Razzazi
Steganography is the science and art of communicating secret data in an appropriate multimedia cover. Three-dimensional (3D) meshes have been used more and more in industrial, medical, and entertainment applications during the last decades. In This Paper, a high-capacity and very low-distortion 3D-Mesh steganography scheme based on novel directional N-dimensional Surfacelet Transform, is proposed. Experimental results show that the cover model distortion is very small. This novel approach can provide much higher hiding capacity and lower distortion than existing approaches in transform domain, while obeying the main Steganographical factors on 3-D models.
隐写术是在适当的多媒体封面上传输秘密数据的科学和艺术。在过去的几十年里,三维(3D)网格在工业、医疗和娱乐应用中得到越来越多的应用。本文提出了一种基于新型定向n维曲面小波变换的高容量、极低失真的三维网格隐写方案。实验结果表明,覆盖模型畸变很小。该方法在满足三维模型主要隐写因素的前提下,在变换域具有更高的隐写能力和更低的失真。
{"title":"A novel steganography approach for 3D polygonal meshes using Surfacelet Transform","authors":"H. Kaveh, M. Moin, F. Razzazi","doi":"10.1109/IRANIANMVIP.2013.6780000","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6780000","url":null,"abstract":"Steganography is the science and art of communicating secret data in an appropriate multimedia cover. Three-dimensional (3D) meshes have been used more and more in industrial, medical, and entertainment applications during the last decades. In This Paper, a high-capacity and very low-distortion 3D-Mesh steganography scheme based on novel directional N-dimensional Surfacelet Transform, is proposed. Experimental results show that the cover model distortion is very small. This novel approach can provide much higher hiding capacity and lower distortion than existing approaches in transform domain, while obeying the main Steganographical factors on 3-D models.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124534741","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
Finding text Stroke width variety in city maps 查找文字笔画宽度变化在城市地图
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6779994
Ali Ghafari-Beranghar, E. Kabir, Kaveh Kangarloo
The Stroke width is an important and stable feature to describe the texts in the document images. In this paper, we propose a method for finding stroke width variety in city map images. Since in city maps the graphics lines and text labels are usually overlap with each other, it is difficult to find the stroke width in such images. On the other hand, texts are printed in a variety of widths. Knowing the major text stroke width is a prior knowledge before map processing like text extraction from graphics lines. In the proposed method, we find the candidate connected components that have significant stroke-width information. Then we locally assign a minimum stroke width to each pixel. For each candidate component, stroke width is determined. By clustering stroke width of components, we find major stroke widths. The experimental results on several varieties of city maps are reported and shown to be promising.
笔画宽度是描述文档图像中文字的一个重要而稳定的特征。本文提出了一种寻找城市地图图像中笔画宽度变化的方法。由于在城市地图中,图形线和文本标签通常相互重叠,因此很难在此类图像中找到笔画宽度。另一方面,文本以各种宽度印刷。在从图形线提取文本等地图处理之前,知道主要文本笔画宽度是一个先验知识。在该方法中,我们找到具有显著笔画宽度信息的候选连接分量。然后我们在局部为每个像素分配最小描边宽度。对于每个候选组件,确定笔画宽度。通过对组件的行程宽度进行聚类,找到主行程宽度。本文报道了在几种不同的城市地图上的实验结果,并显示出了良好的前景。
{"title":"Finding text Stroke width variety in city maps","authors":"Ali Ghafari-Beranghar, E. Kabir, Kaveh Kangarloo","doi":"10.1109/IRANIANMVIP.2013.6779994","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6779994","url":null,"abstract":"The Stroke width is an important and stable feature to describe the texts in the document images. In this paper, we propose a method for finding stroke width variety in city map images. Since in city maps the graphics lines and text labels are usually overlap with each other, it is difficult to find the stroke width in such images. On the other hand, texts are printed in a variety of widths. Knowing the major text stroke width is a prior knowledge before map processing like text extraction from graphics lines. In the proposed method, we find the candidate connected components that have significant stroke-width information. Then we locally assign a minimum stroke width to each pixel. For each candidate component, stroke width is determined. By clustering stroke width of components, we find major stroke widths. The experimental results on several varieties of city maps are reported and shown to be promising.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127641046","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
Transparent watermarking based on psychovisual properties using neural networks 基于心理视觉属性的神经网络透明水印
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6779945
Maryam Karimi, Majid Mohrekesh, Shekoofeh Azizi, S. Samavi
The extreme growth of using digital media has created a need for techniques that can be used to protect the copyrights of digital contents. One approach for copyright protection is to embed an invisible signal, known as a digital watermark, in the image. One of the most important features of an effective watermarking scheme is transparency. A good watermarking method should be invisible such that human eye could not distinguish the dissimilarities between the watermarked image and the original one. On the other hand, a watermarked image should be robust against intentional and unintentional attacks. There is an inherent tradeoff between transparency and robustness. It is desired to keep both properties as high as possible In this paper we propose the use of artificial neural networks (ANN) to predict the most suitable areas of an image for embedding. This ANN is trained based on the human visual system (HVS) model. Only blocks which produce least amount of perceivable changes are selected by this method. This block selection method can aid many of the existing embedding techniques. We have implemented our block selection method in addition to a simple watermarking method. Our results show a noticeable improvement of imperceptibility in our approach compared to other methods.
数字媒体使用的急剧增长产生了对可用于保护数字内容版权的技术的需求。保护版权的一种方法是在图像中嵌入一个不可见的信号,即数字水印。一个有效的水印方案的最重要的特征之一是透明度。好的水印方法应该是不可见的,使人眼无法分辨出水印图像与原始图像的不同之处。另一方面,水印图像对有意和无意攻击的鲁棒性。透明度和稳健性之间存在着内在的权衡。在本文中,我们建议使用人工神经网络(ANN)来预测图像中最适合嵌入的区域。该人工神经网络是基于人类视觉系统(HVS)模型进行训练的。这种方法只选择产生最少可感知变化的块。这种块选择方法可以帮助许多现有的嵌入技术。除了简单的水印方法外,我们还实现了我们的块选择方法。我们的结果表明,与其他方法相比,我们的方法在不可感知性方面有明显的改善。
{"title":"Transparent watermarking based on psychovisual properties using neural networks","authors":"Maryam Karimi, Majid Mohrekesh, Shekoofeh Azizi, S. Samavi","doi":"10.1109/IRANIANMVIP.2013.6779945","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6779945","url":null,"abstract":"The extreme growth of using digital media has created a need for techniques that can be used to protect the copyrights of digital contents. One approach for copyright protection is to embed an invisible signal, known as a digital watermark, in the image. One of the most important features of an effective watermarking scheme is transparency. A good watermarking method should be invisible such that human eye could not distinguish the dissimilarities between the watermarked image and the original one. On the other hand, a watermarked image should be robust against intentional and unintentional attacks. There is an inherent tradeoff between transparency and robustness. It is desired to keep both properties as high as possible In this paper we propose the use of artificial neural networks (ANN) to predict the most suitable areas of an image for embedding. This ANN is trained based on the human visual system (HVS) model. Only blocks which produce least amount of perceivable changes are selected by this method. This block selection method can aid many of the existing embedding techniques. We have implemented our block selection method in addition to a simple watermarking method. Our results show a noticeable improvement of imperceptibility in our approach compared to other methods.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"328 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125449405","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
Long distance iris recognition 远距离虹膜识别
Pub Date : 2013-09-01 DOI: 10.1109/IRANIANMVIP.2013.6779971
R. Amandi, Mitra Bayat, Kobra Minakhani, Hamidreza Mirloo, M. Bazarghan
In this paper we introduce an algorithm to analyze the human iris, long-range iris recognition software has been developed to be more user-friendliness and create an economic way to the identification. Our algorithm centralized on pupil detection, and by using estimated ranges we omit the other regions to create more efficient search space. The final decision on iris region detection provides by Hough Transform. We use the Gaussian method to create a refined mask which has an important rule of the matching process. To extract efficient features of iris regions and matching we used SIFT algorithm, Results on CASIAV4-at Distance shows %93 as verification Rate.
本文介绍了一种对人体虹膜进行分析的算法,开发了远程虹膜识别软件,使虹膜识别更加人性化,为虹膜识别提供了一种经济可行的方法。我们的算法集中于瞳孔检测,并通过使用估计范围来忽略其他区域,以创造更有效的搜索空间。虹膜区域检测的最终决策由霍夫变换提供。我们使用高斯方法创建了一个精细的蒙版,它具有匹配过程的重要规则。为了有效提取虹膜区域特征并进行匹配,我们采用SIFT算法,在CASIAV4-at Distance上的验证率为%93。
{"title":"Long distance iris recognition","authors":"R. Amandi, Mitra Bayat, Kobra Minakhani, Hamidreza Mirloo, M. Bazarghan","doi":"10.1109/IRANIANMVIP.2013.6779971","DOIUrl":"https://doi.org/10.1109/IRANIANMVIP.2013.6779971","url":null,"abstract":"In this paper we introduce an algorithm to analyze the human iris, long-range iris recognition software has been developed to be more user-friendliness and create an economic way to the identification. Our algorithm centralized on pupil detection, and by using estimated ranges we omit the other regions to create more efficient search space. The final decision on iris region detection provides by Hough Transform. We use the Gaussian method to create a refined mask which has an important rule of the matching process. To extract efficient features of iris regions and matching we used SIFT algorithm, Results on CASIAV4-at Distance shows %93 as verification Rate.","PeriodicalId":297204,"journal":{"name":"2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134355525","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
期刊
2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
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
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1