发布求助
文献互助 智能选刊 最新文献

2011 International Conference on Multimedia and Signal Processing最新文献

筛选
英文 中文
Comparison of Feed-Forward and Recurrent Neural Networks in Active Cancellation of Sound Noise 前馈与递归神经网络在声噪声主动消除中的比较
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.96
M. Salmasi, H. Mahdavi-Nasab, H. Pourghassem
{"title":"Comparison of Feed-Forward and Recurrent Neural Networks in Active Cancellation of Sound Noise","authors":"M. Salmasi, H. Mahdavi-Nasab, H. Pourghassem","doi":"10.1109/CMSP.2011.96","DOIUrl":"https://doi.org/10.1109/CMSP.2011.96","url":null,"abstract":"Passive techniques such as barriers, silencers and isolation are bulky, costly and ineffective at low frequencies. Active cancellation of noise was presented because of these problems. In this paper, we want to investigate the uses of neural networks in active noise control (ANC). Feed-forward and recurrent neural networks are compared for active cancellation of sound noise. In order to compare the two networks the number of layers and neurons are equal in both of the networks. Moreover, training and test samples are similar for networks. The noise signals that are used for training the networks are selected from SPIB database. The results of simulation show the ability of these networks in noise cancellation. As it is seen, recurrent neural network has better performance in noise attenuation than the feed-forward neural network.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130006788","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: 9
A Gray Gradient Based Fast Training Algorithm for Face Detection 基于灰度梯度的人脸检测快速训练算法
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.64
Weimin Chen, Wei Wang, Dongxia Xu
{"title":"A Gray Gradient Based Fast Training Algorithm for Face Detection","authors":"Weimin Chen, Wei Wang, Dongxia Xu","doi":"10.1109/CMSP.2011.64","DOIUrl":"https://doi.org/10.1109/CMSP.2011.64","url":null,"abstract":"This paper describes a fast and simple training method for face detection based on block gradient of the gray level. The gradient orientation is one of the most essential features to describe the image structure. In this paper, the detector is trained just by the positive samples from which the feature values accumulated are regarded as the values' weight to detect. The training set is of 50 faces simples. Each image is divided into three resolutions of 4×4, 8×8 and 16×16 to train the detector for different scales. While the detected value in low resolution is higher than the likelihood threshold, high resolution detector is used for a further detecting. Although the training framework is very simple, the correct detection rate is 91%.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130130581","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
Image Mosaicing Algorithm Based on Salient Region and MVSC 基于显著区域和MVSC的图像拼接算法
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.131
Jinpeng Wang, Yewei Li
{"title":"Image Mosaicing Algorithm Based on Salient Region and MVSC","authors":"Jinpeng Wang, Yewei Li","doi":"10.1109/CMSP.2011.131","DOIUrl":"https://doi.org/10.1109/CMSP.2011.131","url":null,"abstract":"The visual attention model and the Mean Value Seamless Cloning (MVSC) algorithm are combined to propose an image mosaicing algorithm based on salient region and MVSC. The new algorithm uses the visual attention model to extract the salient region, and to use the regional registration technology to achieve the image matching, and MVSC algorithm possess good image fusion character, so the image mosaics were studied. The traditional visual attention is improved, and using the improved visual attention model algorithm to obtain salient region of image repeated. The salient regions of image repeated are matched by the image registration algorithm to determine clone domain of the source and target. Finally, the clone domains of the source and target are fused by the MVSC algorithm, to achieve image mosaicing. Experimental results show that this paper algorithm not only can automatically and accurately obtain salient regions, but also reduce the complexity of the image registration, improve the quality of image mosaicing.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126209005","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
A New Algorithm for Red Blood Cell Characteristics Image Recognition 一种新的红细胞特征图像识别算法
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.67
Z. Ho, Huei-Ju Lee
{"title":"A New Algorithm for Red Blood Cell Characteristics Image Recognition","authors":"Z. Ho, Huei-Ju Lee","doi":"10.1109/CMSP.2011.67","DOIUrl":"https://doi.org/10.1109/CMSP.2011.67","url":null,"abstract":"Blood cells characteristics recognition is an important issue for food nutrition. Food scientists want to know the detailed information of fish red blood cells, such as the major axis of a cell, minor axis of a cell, overlap rate of a cell. It would determine the scale of agglutination of red blood cells. That means the more fatigued a fish, the more agglutination of red blood cells there are. In the animal model, we determine if a medicine significantly outperform control groups via death rate of fishes within a certain number of days. In this study, red cells characteristics levels approach was proposed. It means that the fishes would die at a lower rate than the animal model due to red blood cells image recognition replacing death rate of fishes. Previous researches focused on the shape of red blood cells recognition, most of them did not discuss the cell characteristics, such as the major axis of a cell, minor axis of a cell, overlap rate of cell recognition and computation. Therefore, the main purpose of this research is through red blood cells characteristics recognition to try to replace the traditional animal model approach. This study proposed a new algorithm coded as software to proceed red blood cells characteristics image recognition. After validation, the proposed algorithm successfully recognized the major axis of a cell and minor axis of a cell. The percentage of Hemagglutination rate was successfully calculated. The study would be applied into distribution industries, which transport the live fishes, saving money because due to reducing the fish death rate. In future studies, if some of the assumptions, colored methods or chemical reactions are relaxed or revised, it may recognize different biological photos.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"96 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128939775","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
How Real is Really? A Perceptually Motivated System for Quantifying Visual Realism in Digital Images 真实有多真实?一种量化数字图像视觉真实感的感知激励系统
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.172
N. Wang, W. Doubé
{"title":"How Real is Really? A Perceptually Motivated System for Quantifying Visual Realism in Digital Images","authors":"N. Wang, W. Doubé","doi":"10.1109/CMSP.2011.172","DOIUrl":"https://doi.org/10.1109/CMSP.2011.172","url":null,"abstract":"Contemporary video games are generally designed with the aim of engendering a state of immersion in their players. A sense of 'presence' is considered to be a prerequisite of total immersion, the ultimate level of immersion, and can be directly related to the degree of realism in the simulation presented in a videogame. However, continuously increasing the degree of visual realism in an image could cause adverse effects such as fault amplification and more importantly, emotions like fear and dread of the uncanny. It can also substantially raise the development costs of a game. Consequently, videogame developers would benefit greatly from knowing the threshold beyond which increased realism is counter-productive. This paper details the development of an image processing system that measures the degree of realism of an image using three methods - gradient variance, color variance and shadow softness - derived from existing theories and practices in perceptual psychology, photoforensics and image processing. It then discusses testing of the system on a variety of photographic and video game images.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120979361","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: 18
An Edge Detection Method Based on Lifting Wavelet and Mathematical Morphology 一种基于提升小波和数学形态学的边缘检测方法
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.155
Rong Wang
{"title":"An Edge Detection Method Based on Lifting Wavelet and Mathematical Morphology","authors":"Rong Wang","doi":"10.1109/CMSP.2011.155","DOIUrl":"https://doi.org/10.1109/CMSP.2011.155","url":null,"abstract":"An edge detection method based on lifting wavelet and mathematical morphology is proposed in this paper. Firstly, the original image is decomposed by lifting wavelet transformation; secondly, the edge pixels in low-frequency sub-image are detected by morphological gradient and edge pixels in high-frequency sub-images are detected by the largest value of the module of wavelet coefficients; the two edge images obtained respectively by the morphology and wavelet are fused according to some rules at last. The experimental results show that the performance obtained by the method proposed in this paper is better than the one obtained by either of morphology method and wavelet method.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121099755","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
A 16Gbps Real-Time BF-based LDPC Decoder for IEEE 802.3an Standard 基于IEEE 802.3an标准的16Gbps实时带宽LDPC解码器
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.19
Jui-Hui Hung, Sau-Gee Chen
{"title":"A 16Gbps Real-Time BF-based LDPC Decoder for IEEE 802.3an Standard","authors":"Jui-Hui Hung, Sau-Gee Chen","doi":"10.1109/CMSP.2011.19","DOIUrl":"https://doi.org/10.1109/CMSP.2011.19","url":null,"abstract":"Existing LDPC decoders are mostly based onbelief-propagation (BP) algorithms for high decodingperformance but demand high hardware cost, especially forapplications with very high throughputs. In order toalleviate the problem, this work proposes a high-throughputLDPC decoder based on the much simpler bit-flipping (BF)algorithms, for the (2048, 1723) RS-LDPC code adopted inthe IEEE 802.3an standard. High decoding performancesand low iteration numbers are achieved by introducing astrategy of flipping low-correlation bits and an additionalsyndrome vote scheme. As a result, the decodingperformance is comparable to the most popular BP-basedmin-sum algorithm (MSA) but with much lowercomputational complexity. Besides, the decoder achieveshigh hardware utilization with real-time processingcapability. Synthesized with UMC 90nm process, thedecoder chip area, throughput and average powerdissipation are 1.22M gates, 16Gbps and 315mW,respectively, at 500MHz clock rate.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121476737","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 Method of Character Recognition Based on General Characteristic and Connected Regions 一种基于一般特征和连通区域的字符识别方法
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.25
Meng Qing-yuan, Huang Hongping, Bai Yanping
{"title":"A Method of Character Recognition Based on General Characteristic and Connected Regions","authors":"Meng Qing-yuan, Huang Hongping, Bai Yanping","doi":"10.1109/CMSP.2011.25","DOIUrl":"https://doi.org/10.1109/CMSP.2011.25","url":null,"abstract":"In this paper, by analyzing the number of concave domain and cycles and the characteristic of connected domain of the characters, we present a method of character recognition based on above mentioned features. At first, the characters are divided into two classes according to cycles: the character with cycles and the character without cycles. Then, we detect if the character has sunk parts in its four directions (up, down, left, right).According to the results, the character can be recognized or divided into six classes. At last, we recognize the character using the characteristic of connected domain, and obtain the final recognition results. The experiment shows that the algorithm has a good performance in English characters recognition.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115850909","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
Compressed Locally Embedding 压缩局部嵌入
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.138
Jianbin Wu, Zhonglong Zheng
{"title":"Compressed Locally Embedding","authors":"Jianbin Wu, Zhonglong Zheng","doi":"10.1109/CMSP.2011.138","DOIUrl":"https://doi.org/10.1109/CMSP.2011.138","url":null,"abstract":"The common strategy of Spectral manifold learning algorithms, e.g., Locally Linear Embedding (LLE) and Laplacian Eigenmap (LE), facilitates neighborhood relationships which can be constructed by $knn$ or $epsilon$ criterion. This paper presents a simple technique for constructing the nearest neighborhood based on the combination of $ell_{2}$ and $ell_{1}$ norm. The proposed criterion, called Locally Compressive Preserving (CLE), gives rise to a modified spectral manifold learning technique. Illuminated by the validated discriminating power of sparse representation, we additionally formulate the semi-supervised learning variation of CLE, SCLE for short, based on the proposed criterion to utilize both labeled and unlabeled data for inference on a graph. Extensive experiments on both manifold visualization and semi-supervised classification demonstrate the superiority of the proposed algorithm.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130788818","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
Enhanced Low Complex Cost Function for H.264/AVC Intra Mode Decision H.264/AVC模式内决策的增强低复杂代价函数
2011 International Conference on Multimedia and Signal Processing Pub Date : 2011-05-14 DOI: 10.1109/CMSP.2011.17
M. G. Sarwer, Q.M. Jonathan Wu
{"title":"Enhanced Low Complex Cost Function for H.264/AVC Intra Mode Decision","authors":"M. G. Sarwer, Q.M. Jonathan Wu","doi":"10.1109/CMSP.2011.17","DOIUrl":"https://doi.org/10.1109/CMSP.2011.17","url":null,"abstract":"In order to reduce the computation of rate-distortion optimization (RDO) module of H.264/AVC intra encoder, this paper proposes an enhanced low complexity cost function. The enhanced cost function uses sum of absolute Hadamard-transformed differences (SATD) and mean absolute deviation of the residual block to estimate distortion part of the cost function. A threshold based large coefficients count is also used for estimating the bit-rate part. The proposed method improves the rate-distortion performance of the conventional fast cost functions while maintaining low complexity requirement. As the results, the encoding process can be significantly accelerated with use of the proposed cost function. Simulation results confirm that the proposed method reduces about 85% of computation of original encoder with negligible rate-distortion performance degradation.","PeriodicalId":309902,"journal":{"name":"2011 International Conference on Multimedia and Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130973338","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
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