2013 18th International Conference on Digital Signal Processing (DSP)最新文献_第9页

Multi-model AAM framework for face image modeling 人脸图像建模的多模型AAM框架

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622752

M. A. Khan, C. Xydeas, Hassan Ahmed

引用次数: 6

Grammar-assisted audio-video equation recognition 语法辅助音频-视频方程识别

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622671

Smita Vemulapalli, M. Hayes

{"title":"Grammar-assisted audio-video equation recognition","authors":"Smita Vemulapalli, M. Hayes","doi":"10.1109/ICDSP.2013.6622671","DOIUrl":"https://doi.org/10.1109/ICDSP.2013.6622671","url":null,"abstract":"In this paper, we consider the problem of recognizing handwritten mathematical content from classroom videos. Since the handwritten text and the accompanying audio refer to the same mathematical characters and symbols, a combination of video and audio based recognizers has the potential to significantly increase the recognition accuracy compared to that of the individual recognizers. In this paper, we propose a novel multi-step technique for combining the output of the video and the audio based recognizers. Initial recognition results from a video based recognizer and a speech recognizer, operating independently on the handwritten and the spoken content from a classroom video, are combined with a base mathematical speech grammar to arrive at a constrained speech grammar that is specific to the content being recognized. The constrained speech grammar is then used by the speech recognizer to generate the final character recognition results. A subsequent layout analysis step, which makes used of audio cues and X-Y cuts based method, is used to arrive at the final recognized content. Experiments conducted using videos recorded in a classroom like environment are used to demonstrate the significant improvement in recognition accuracy that can be achieved using our technique.","PeriodicalId":180360,"journal":{"name":"2013 18th International Conference on Digital Signal Processing (DSP)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127420303","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

Modeling of readback signal generated by scanning PCM surfaces 扫描PCM表面产生的读回信号的建模

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622699

I. Zacharias, T. Antonakopoulos

{"title":"Modeling of readback signal generated by scanning PCM surfaces","authors":"I. Zacharias, T. Antonakopoulos","doi":"10.1109/ICDSP.2013.6622699","DOIUrl":"https://doi.org/10.1109/ICDSP.2013.6622699","url":null,"abstract":"Micro-electro-mechanical systems (MEMS) based on Scanning Probe Methods (SPM) are an emerging technology for sensor based applications and data storage. Atomic Force Microscope (AFM) techniques with conductive tips, using phase-change materials to record data as amorphous or crystalline marks, have been demonstrated experimentally. Storing data patterns on the Phase Change Medium (PCM) is achieved by the write process, which determines the final shape and size of the mark based on complex electrical, thermal and phase transition phenomena. The read process relies on measuring the electrical resistivity at different positions of the respective mark. In this paper, we present the model of the readback signal that is generated when a data pattern stored in a PCM surface is scanned with constant velocity. The presented two-dimensional model is based on Finite Element Method (FEM) analysis that has been used to simulate such a physical mechanism. The main objective of this work is to derive and analyze the basic waveform of the readback signal from an amorphous mark, for different geometric and physical configurations of the storage system.","PeriodicalId":180360,"journal":{"name":"2013 18th International Conference on Digital Signal Processing (DSP)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127880992","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

Evaluation of low-complexity visual feature detectors and descriptors 评估低复杂度的视觉特征检测器和描述符

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622757

A. Canclini, M. Cesana, A. Redondi, M. Tagliasacchi, J. Ascenso, Rodrigo Cilla

引用次数: 80

A convex optimization approach for image resolution enhancement from compressed representations 从压缩表示增强图像分辨率的凸优化方法

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622842

R. Gaetano, B. Pesquet-Popescu, C. Chaux

{"title":"A convex optimization approach for image resolution enhancement from compressed representations","authors":"R. Gaetano, B. Pesquet-Popescu, C. Chaux","doi":"10.1109/ICDSP.2013.6622842","DOIUrl":"https://doi.org/10.1109/ICDSP.2013.6622842","url":null,"abstract":"Quality of experience in future home devices is foreseen to drastically increase, with the increase in image resolution. Displays with a horizontal resolution of 4K pixels are already appearing, and 8K Super-HiVision has already been demonstrated. Currently, only spatial upsampling of conventional HD format is performed to match the resolution of such displays. In this paper, we propose a novel method for high-quality up-conversion of legacy visual content in order to fit the screen resolution. More precisely, by assuming that we have various versions of the same image at standard resolution, encoded with different parameters, we try to reconstruct the high resolution image with higher quality than a simple interpolation. To this end, we adopt a variational formulation of the problem and construct a convex constrained criterion that incorporates both a fidelity term (linked to the acquisition process) and some a priori information. A recent primal-dual proximal algorithm is used to solve the associated minimization problem and simulation results show the good performance and behavior of the proposed approach.","PeriodicalId":180360,"journal":{"name":"2013 18th International Conference on Digital Signal Processing (DSP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123909681","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

RAAT - The reverie avatar authoring tool RAAT -幻想头像创作工具

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622788

K. C. Apostolakis, P. Daras

{"title":"RAAT - The reverie avatar authoring tool","authors":"K. C. Apostolakis, P. Daras","doi":"10.1109/ICDSP.2013.6622788","DOIUrl":"https://doi.org/10.1109/ICDSP.2013.6622788","url":null,"abstract":"Avatar embodiment within the World Wide Web has gained a lot of popularity in recent years thanks to the introduction of networked virtual environments created for socialization and entertainment purposes. As each of these virtual worlds generates a unique set of user requirements concerning representation preferences based on the environment's context, it becomes clear that every attempt at creating such virtual worlds should encourage the development of the appropriate avatar authoring tools, being based on a thorough study of avatar desirable features. The Reverie Avatar Authoring Tool (RAAT) introduced in this paper helps developers address these ever-emerging avatar feature requirements, allowing them to easily set up and design online character creation applications, tailored to the virtual environment specifications. Summarizing the design process to a simple task of documenting the application interface within a single script, RAAT encapsulates the demanding tasks of character creation within simple function calls, while also offering a web-based real-time solution for photorealistic integration of user physical appearance onto the character mesh.","PeriodicalId":180360,"journal":{"name":"2013 18th International Conference on Digital Signal Processing (DSP)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123920639","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: 17

Unsupervised music segmentation via multi-scale processing of compressive features' representation 基于多尺度压缩特征表示的无监督音乐分割

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622772

Ilias Theodorakopoulos, G. Economou, S. Fotopoulos

引用次数: 4

Sparsity-based classification using texture and depth 基于稀疏的分类使用纹理和深度

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622771

Tsampikos Kounalakis, N. Boulgouris

引用次数: 4

Improving the detection and localization of duplicated regions in copy-move image forgery 改进复制-移动图像伪造中重复区域的检测和定位

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622700

Maryam Jaberi, G. Bebis, M. Hussain, Muhammad Ghulam

{"title":"Improving the detection and localization of duplicated regions in copy-move image forgery","authors":"Maryam Jaberi, G. Bebis, M. Hussain, Muhammad Ghulam","doi":"10.1109/ICDSP.2013.6622700","DOIUrl":"https://doi.org/10.1109/ICDSP.2013.6622700","url":null,"abstract":"Using keypoint-based features, such as SIFT features, for detecting copy-move image forgeries has yielded promising results. In this paper, our emphasis is on improving the detection and localization of duplicated regions using more powerful keypoint-based features. In this context, we have adopted a more powerful set of keypoint-based features, called MIFT, which share the properties of SIFT features but also are invariant to mirror reflection transformations. To improve localization, we propose estimating the parameters of the affine transformation between copied and pasted regions more accurately using an iterative scheme which finds additional keypoint matches incrementally. To reduce the number of false positives and negatives, we propose using “dense” MIFT features, instead of standard pixel correlation, along with hystereresis thresholding and morphological operations. The proposed approach has been evaluated and compared with competitive approaches through a comprehensive set of experiments using a large dataset of real images. Our results indicate that our method can detect duplicated regions in copy-move image forgery with higher accuracy, especially when the size of the duplicated region is small.","PeriodicalId":180360,"journal":{"name":"2013 18th International Conference on Digital Signal Processing (DSP)","volume":"357 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115939582","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: 22

HDR image watermarking based on bracketing decomposition 基于括号法分解的HDR图像水印

2013 18th International Conference on Digital Signal Processing (DSP) Pub Date : 2013-07-01 DOI: 10.1109/ICDSP.2013.6622687

V. Solachidis, E. Maiorana, P. Campisi, F. Banterle

引用次数: 23