Compared to the fruitful research outputs in 2D palm print recognition, the research in hyper spectral palm print recognition is quite limited in literature. When 2D slices of hyper spectral data was processed separately and then fused at different levels for palm recognition, the information contained in the 3D data is not fully exploited. We proposed a 3D Gabor wavelet based approach in this paper to extract features in spatial and spectrum domain simultaneously. A set of 3D Gabor wavelets with different frequencies and orientations were designed and convolved with the cube to extract discriminative information in the joint spatial-spectral domain. For each location in the 3D cube, the wavelet who produces the maximum response is identified and the response is coded using a two-bits code according to the phase information. The similarity between two hyper spectal cubes are then calculated using hamming distance measurement. The HK-PolyU Hyper spectral Palm print Database captured from 380 palms were used for experiments. Results show that the fused feature substantially outperformed the accuracy of individual wavelet. As low as 4% EER was achieved.
{"title":"Coding 3D Gabor Features for Hyperspectral Palmprint Recognition","authors":"L. Shen, Wenfeng Wu, Sen Jia, Zhenhua Guo","doi":"10.1109/ICMB.2014.36","DOIUrl":"https://doi.org/10.1109/ICMB.2014.36","url":null,"abstract":"Compared to the fruitful research outputs in 2D palm print recognition, the research in hyper spectral palm print recognition is quite limited in literature. When 2D slices of hyper spectral data was processed separately and then fused at different levels for palm recognition, the information contained in the 3D data is not fully exploited. We proposed a 3D Gabor wavelet based approach in this paper to extract features in spatial and spectrum domain simultaneously. A set of 3D Gabor wavelets with different frequencies and orientations were designed and convolved with the cube to extract discriminative information in the joint spatial-spectral domain. For each location in the 3D cube, the wavelet who produces the maximum response is identified and the response is coded using a two-bits code according to the phase information. The similarity between two hyper spectal cubes are then calculated using hamming distance measurement. The HK-PolyU Hyper spectral Palm print Database captured from 380 palms were used for experiments. Results show that the fused feature substantially outperformed the accuracy of individual wavelet. As low as 4% EER was achieved.","PeriodicalId":273636,"journal":{"name":"2014 International Conference on Medical Biometrics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132266238","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}
Wenxue Hong, Zhongpeng Zhang, Jingmin Luan, Shaoxiong Li, Tao Zhang, Haisheng Liu
This article is the research on value order of the syndrome elements based on differentiation diagnosis during the clinical practice of inquiry of Traditional Chinese Medicine. In order to fit the principle of Chinese diagnostics, a complex system model of Traditional Chinese Medicine diagnosis has been conducted by applying the description of multilayer complex system, and there are three layers of complex system model included diseases, syndromes and symptoms. After establishing the framework of diagnosis knowledge of Traditional Chinese Medicine by using the mathematics method of formal concept analysis, a new diagnosis method of Traditional Chinese Medicine has been proposed based on representation principle of structural partial-ordered attribute diagram, intend to fulfill the request of clinical application. This method provided a scientific solution for analyzing the syndrome element value order of Chinese diagnostics by merging multi-disciplines. During the clinical application, there are total 112 cases has been collected. Among this cases, there are 48.21 percent of it has over 80 percent matches with the diagnosis of clinical experts, and there are 90.18 percent of it has over 60 percent matches with the diagnosis of clinical experts. The result of this method corresponded the Chinese diagnostics, and its effectiveness and practicability has been proved.
{"title":"A Research about Value Order Measurement System of Traditional Chinese Medicine Syndrome Elements","authors":"Wenxue Hong, Zhongpeng Zhang, Jingmin Luan, Shaoxiong Li, Tao Zhang, Haisheng Liu","doi":"10.1109/ICMB.2014.20","DOIUrl":"https://doi.org/10.1109/ICMB.2014.20","url":null,"abstract":"This article is the research on value order of the syndrome elements based on differentiation diagnosis during the clinical practice of inquiry of Traditional Chinese Medicine. In order to fit the principle of Chinese diagnostics, a complex system model of Traditional Chinese Medicine diagnosis has been conducted by applying the description of multilayer complex system, and there are three layers of complex system model included diseases, syndromes and symptoms. After establishing the framework of diagnosis knowledge of Traditional Chinese Medicine by using the mathematics method of formal concept analysis, a new diagnosis method of Traditional Chinese Medicine has been proposed based on representation principle of structural partial-ordered attribute diagram, intend to fulfill the request of clinical application. This method provided a scientific solution for analyzing the syndrome element value order of Chinese diagnostics by merging multi-disciplines. During the clinical application, there are total 112 cases has been collected. Among this cases, there are 48.21 percent of it has over 80 percent matches with the diagnosis of clinical experts, and there are 90.18 percent of it has over 60 percent matches with the diagnosis of clinical experts. The result of this method corresponded the Chinese diagnostics, and its effectiveness and practicability has been proved.","PeriodicalId":273636,"journal":{"name":"2014 International Conference on Medical Biometrics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131811592","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}
Wenxue Hong, Jialin Song, Cunfang Zheng, Jingmin Luan, Shaoxiong Li, Tao Zhang, Haisheng Liu
Syndrome elements are the smallest units of syndrome classification and the basic elements of syndrome differentiation. Introduction of Traditional Chinese Medicine (TCM) syndrome elements can increase the accuracy of the treatment after syndrome differentiation, and this is conducive to standardization of the study of TCM syndrome. The standardization has significant significance for the TCM syndrome differentiation. This paper presents a method of pattern discovery on TCM syndrome elements, on the basis of the principle of inquiring diagnosis in TCM. The clinical results are very similar with the research results of Beijing University of Chinese Medicine in the National Basic Research Program of China (973 Program). The results suggest that the method based on inquiring diagnosis of Traditional Chinese Medicine can be used as the syndrome elements pattern discovery methods for different diseases, and syndrome elements patterns have certain rules from health to disease of human populations.
{"title":"Comparative Study on Pattern Discovery of Traditional Chinese Medicine Common Syndrome Elements","authors":"Wenxue Hong, Jialin Song, Cunfang Zheng, Jingmin Luan, Shaoxiong Li, Tao Zhang, Haisheng Liu","doi":"10.1109/ICMB.2014.19","DOIUrl":"https://doi.org/10.1109/ICMB.2014.19","url":null,"abstract":"Syndrome elements are the smallest units of syndrome classification and the basic elements of syndrome differentiation. Introduction of Traditional Chinese Medicine (TCM) syndrome elements can increase the accuracy of the treatment after syndrome differentiation, and this is conducive to standardization of the study of TCM syndrome. The standardization has significant significance for the TCM syndrome differentiation. This paper presents a method of pattern discovery on TCM syndrome elements, on the basis of the principle of inquiring diagnosis in TCM. The clinical results are very similar with the research results of Beijing University of Chinese Medicine in the National Basic Research Program of China (973 Program). The results suggest that the method based on inquiring diagnosis of Traditional Chinese Medicine can be used as the syndrome elements pattern discovery methods for different diseases, and syndrome elements patterns have certain rules from health to disease of human populations.","PeriodicalId":273636,"journal":{"name":"2014 International Conference on Medical Biometrics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127754321","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}
Zhikun Zhuang, Yang Chen, H. Shu, L. Luo, C. Toumoulin, J. Coatrieux
Although effectively reducing the radiation exposure to patients, low dose CT (LDCT) images are often significantly degraded by severely increased mottled noise/artifacts, which can lead to lowered diagnostic accuracy in clinic. The nonlocal means (NLM) filtering can effectively remove mottled noise/artifacts by utilizing large-scale patch similarity information in LDCT images. But the NLM filtering application in LDCT imaging is also accompanied with high computation cost as a large searching window is often required to include much neighboring information for noise/artifact suppression. To accelerate the NLM filtering and improve its clinical feasibility, we propose in this paper an improved GPUbased parallelization approach. In addition to the straight pixel wise parallelization, the improved parallelization approach exploits the high I/O speed of GPU shared memory. Quantitative experiment demonstrates that significant acceleration is achieved with respect to the traditional pixel-wise parallelization.
{"title":"Fast Low-Dose CT Image Processing Using Improved Parallelized Nonlocal Means Filtering","authors":"Zhikun Zhuang, Yang Chen, H. Shu, L. Luo, C. Toumoulin, J. Coatrieux","doi":"10.1109/ICMB.2014.33","DOIUrl":"https://doi.org/10.1109/ICMB.2014.33","url":null,"abstract":"Although effectively reducing the radiation exposure to patients, low dose CT (LDCT) images are often significantly degraded by severely increased mottled noise/artifacts, which can lead to lowered diagnostic accuracy in clinic. The nonlocal means (NLM) filtering can effectively remove mottled noise/artifacts by utilizing large-scale patch similarity information in LDCT images. But the NLM filtering application in LDCT imaging is also accompanied with high computation cost as a large searching window is often required to include much neighboring information for noise/artifact suppression. To accelerate the NLM filtering and improve its clinical feasibility, we propose in this paper an improved GPUbased parallelization approach. In addition to the straight pixel wise parallelization, the improved parallelization approach exploits the high I/O speed of GPU shared memory. Quantitative experiment demonstrates that significant acceleration is achieved with respect to the traditional pixel-wise parallelization.","PeriodicalId":273636,"journal":{"name":"2014 International Conference on Medical Biometrics","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129764684","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}
Automated classification of medical images is very useful for physicians and surgeons in the diagnoses of complex diseases. Computerized medical pattern recognition tools can capture subtle image properties of various pathological patterns and therefore narrow down the gap of reproducible results for reliable decision making under uncertainty. In this paper, a nonstationary mapping of spatial uncertainty in medical images is introduced for feature extraction, which can be effectively applied for diagnostic pattern classification. Experimental results obtained from using abdominal computed tomography imaging and comparisons with other feature extraction methods demonstrate the usefulness of the proposed mapping model.
{"title":"Nonstationary Mapping of Spatial Uncertainty for Medical Image Classification","authors":"T. Pham","doi":"10.1109/ICMB.2014.46","DOIUrl":"https://doi.org/10.1109/ICMB.2014.46","url":null,"abstract":"Automated classification of medical images is very useful for physicians and surgeons in the diagnoses of complex diseases. Computerized medical pattern recognition tools can capture subtle image properties of various pathological patterns and therefore narrow down the gap of reproducible results for reliable decision making under uncertainty. In this paper, a nonstationary mapping of spatial uncertainty in medical images is introduced for feature extraction, which can be effectively applied for diagnostic pattern classification. Experimental results obtained from using abdominal computed tomography imaging and comparisons with other feature extraction methods demonstrate the usefulness of the proposed mapping model.","PeriodicalId":273636,"journal":{"name":"2014 International Conference on Medical Biometrics","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130495434","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：