2009 IEEE International Conference on Signal and Image Processing Applications最新文献_第8页

A level set based predictor-corrector algorithm for vessel segmentation 基于水平集的血管分割预测校正算法

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478611

Wei Yan, T. Zhu, Yongming Xie, Wai-Man Pang, J. Qin, Jianhuang Wu, P. Heng

{"title":"A level set based predictor-corrector algorithm for vessel segmentation","authors":"Wei Yan, T. Zhu, Yongming Xie, Wai-Man Pang, J. Qin, Jianhuang Wu, P. Heng","doi":"10.1109/ICSIPA.2009.5478611","DOIUrl":"https://doi.org/10.1109/ICSIPA.2009.5478611","url":null,"abstract":"Vessel segmentation is an essential task in many computer-aided medical systems. However, the topology complexity of vascular structures and the intensity inhomogeneity of angiogram make it a challenging problem. We propose a level set based predictor-corrector algorithm to meet these challenges. In the predictor step, the overall contour of vessel structures is delineated by piecewise constant (PC) model, which is insensitive to the initial contour and adaptive to the complex morphological variations of vessel structures. In the corrector step, the segmented results are refined by an improved local binary fitting (LBF) model, which can efficiently deal with intensity inhomogeneity in the angiogram, especially in the distal part of the vessels. Compared to original LBF model, our approach can avoid the emergence of new contour in non-vascular regions. The proposed algorithm takes both global and local information into consideration and combines the advantages of PC model and LBF model. Experimental results on MRA images demonstrate the feasibility of our algorithm.","PeriodicalId":400165,"journal":{"name":"2009 IEEE International Conference on Signal and Image Processing Applications","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129802788","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 simple approach to determine the best threshold value for automatic image thresholding 一个简单的方法来确定最佳阈值的自动图像阈值

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478623

Abdul Halim Ismail, M. Marhaban

引用次数: 13

Extraction of human gait features from enhanced human silhouette images 增强人体轮廓图像中步态特征的提取

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478691

Hu Ng, W. Tan, Hau-Lee Tong, J. Abdullah, R. Komiya

引用次数: 11

Multi-level segmentation method for serial computed tomography brain images 串行计算机断层扫描脑图像的多级分割方法

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478636

W. M. Diyana, W. Zaki, M. Faizal, A. Fauzi, R. Besar, W. Munirah, Wan Siti Halimatul Munirah Wan Ahmad

引用次数: 5

A new robust wavelet based algorithm for baseline wandering cancellation in ECG signals 一种新的基于小波的心电信号基线漂移消除算法

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478671

A. Sargolzaei, K. Faez, S. Sargolzaei

{"title":"A new robust wavelet based algorithm for baseline wandering cancellation in ECG signals","authors":"A. Sargolzaei, K. Faez, S. Sargolzaei","doi":"10.1109/ICSIPA.2009.5478671","DOIUrl":"https://doi.org/10.1109/ICSIPA.2009.5478671","url":null,"abstract":"Wavelet transform has been emerged over recent years as a powerful time-frequency analysis and signal coding tool favored for the interrogation of complex non stationary signals. Its application to bio-signal processing has been at the forefront of these developments where it has been found particularly useful in the study of these, often problematic, signals: none more so than the Electrocardiogram (ECG). In this paper, the emerging roles of the wavelet transform in the ECG preprocessing and noise removing step is discussed in detail. One of the most important noise sources, baseline wandering, which can be affected ECG signal analysis is introduced and a new method based on wavelet transform is being proposed. The proposed method construct a model of baseline wander with multiresolution analysis of the signal using discrete wavelet transform and then remove the baseline wander from the ECG signal using the constructed model. Simulations were carried out to show the performance of the algorithm using the MIT-BIH noise stress test database and PTB diagnosis database. The quality of the results by the proposed technique is found to meet or exceed that of published results using other conventional methods such as kalman filtering and conventional digital filters.","PeriodicalId":400165,"journal":{"name":"2009 IEEE International Conference on Signal and Image Processing Applications","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117054445","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: 27

Efficient textile recognition via decomposition of co-occurrence matrices 通过共现矩阵的分解有效识别纺织品

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478606

K. Loke, M. Cheong

引用次数: 13

An elastic band model for Shape retrieval 形状检索的弹性带模型

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478678

Soonwook Hwang, Won-Du Chang, Jungpil Shin

引用次数: 0

A Neural Network based system for Persian sign language recognition 基于神经网络的波斯语手语识别系统

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478627

Azadeh Kiani Sarkaleh, F. Poorahangaryan, Bahman Zanj, A. Karami

引用次数: 22

Tapping and detecting optical signals from optical CDMA networks 从光CDMA网络提取和检测光信号

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478617

H. Bakarman, F. Hasoon, S. Shaari, M. Ismail

引用次数: 1

A New approach of Rate-Quantization modeling for Intra and Inter frames in H.264 rate control H.264帧内帧间速率量化建模的新方法

2009 IEEE International Conference on Signal and Image Processing Applications Pub Date : 2009-11-01 DOI: 10.1109/ICSIPA.2009.5478701

Miryem Hrarti, Hakim Saadane, M. Larabi, A. Tamtaoui, D. Aboutajdine

{"title":"A New approach of Rate-Quantization modeling for Intra and Inter frames in H.264 rate control","authors":"Miryem Hrarti, Hakim Saadane, M. Larabi, A. Tamtaoui, D. Aboutajdine","doi":"10.1109/ICSIPA.2009.5478701","DOIUrl":"https://doi.org/10.1109/ICSIPA.2009.5478701","url":null,"abstract":"Video encoding rate control has been the research focus in the recent years. The existing rate control algorithms use Rate-Distortion (R-D) or Rate-Quantization (R-Q) models. These latter assume that the enhancement of the bit allocation process, the quantization parameter determination and the buffer management are essentially based on the improvement of complexity measures estimation. Inaccurate estimation leads to wrong quantization parameters and affects significantly the global performance. Therefore, several improved frame complexity measures are proposed in literature. The efficiency of such measures is however limited by the linear prediction model which remains still inaccurate to encode complexity between two neighbour frames. In this paper, we propose a new approach of Rate-Quantization modeling for both Intra and Inter frame without any complexity measure estimation. This approach results from extensive experiments and proposes two Rate-Quantization models. The first one (M1) aims at determining an optimal initial quantization parameter for Intra frames based on sequence target bit-rate and frame rate. The second model (M2) determines the quantization parameter of Inter coding unit (Frame or Macroblock) according to the statistics of the previous coded ones. This model substitutes both linear and quadratic models used in H.264 rate controller. The simulations have been carried out using both JM10.2 and JM15.0 reference softwares. Compared to JM10.2, M1 alone, improves the PSNR up to 1.93dB, M2 achieves a closer output bit-rate and similar quality while the combined model (M1+M2) minimizes the computational complexity. (M1+M2) outperforms both JM10.2 and JM15.0 in terms of PSNR.","PeriodicalId":400165,"journal":{"name":"2009 IEEE International Conference on Signal and Image Processing Applications","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123816598","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