Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864522
Zhang Xuejian, X. Liang
The implementation of MRI reconstruction algorithms based on a multi-core DSP (TMS320C6678) is described in this paper. As a state-of-the-art device, TMS320C6678 has powerful computing capability and high data throughput. The tasks of Fourier reconstruction and image combination (sum-of-squares) of multi-channels are assigned to different cores of the DSP; K-space data import, data processing and data communication are implemented using high efficiency multi-core programming. Simulation results indicate that the total processing time of 16 channels is less than 100 ms (image size: 256×256), which met mainly the real-time imaging requirement.
{"title":"The real-time implementation of MRI reconstruction algorithms based on a multi-core DSP","authors":"Zhang Xuejian, X. Liang","doi":"10.1109/ICMIPE.2013.6864522","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864522","url":null,"abstract":"The implementation of MRI reconstruction algorithms based on a multi-core DSP (TMS320C6678) is described in this paper. As a state-of-the-art device, TMS320C6678 has powerful computing capability and high data throughput. The tasks of Fourier reconstruction and image combination (sum-of-squares) of multi-channels are assigned to different cores of the DSP; K-space data import, data processing and data communication are implemented using high efficiency multi-core programming. Simulation results indicate that the total processing time of 16 channels is less than 100 ms (image size: 256×256), which met mainly the real-time imaging requirement.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128750849","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}
A new image registration and fusion method based on Multi-Atlas was proposed in this thesis. It treats all Atlas images as a series of data nodes and clusters them through massage propagation to obtain different exemplars, then uses these exemplars to participate in the normal atlas segmentation, orders them based on the dice similar coefficient, iterate, gets the final accurate segmentation. In term of registration, three-step registration is adopted: first rigid registration, then affine registration and B spline registration. Besides, fusion strategy called Joint Label Fusion is used, which is first used for right ventricle. The method makes split operation by registration and fusion method based on Multi-Atlas image, corrects a Multi-Atlas label fusion error caused by the registration, thereby optimizes segmentation result.
{"title":"Accurate segmentation for right ventricles based on Multi-Atlas","authors":"Yaonan Zhang, X. Meng, Chuanshen Chen, Qian Song, Yu Xu","doi":"10.1109/ICMIPE.2013.6864527","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864527","url":null,"abstract":"A new image registration and fusion method based on Multi-Atlas was proposed in this thesis. It treats all Atlas images as a series of data nodes and clusters them through massage propagation to obtain different exemplars, then uses these exemplars to participate in the normal atlas segmentation, orders them based on the dice similar coefficient, iterate, gets the final accurate segmentation. In term of registration, three-step registration is adopted: first rigid registration, then affine registration and B spline registration. Besides, fusion strategy called Joint Label Fusion is used, which is first used for right ventricle. The method makes split operation by registration and fusion method based on Multi-Atlas image, corrects a Multi-Atlas label fusion error caused by the registration, thereby optimizes segmentation result.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127025832","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}
Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864560
Yijia Zhang, C. Duan, Datian Ye, Zhengrong Liang
Efficient and accurate segmentation of bladder wall on MR images is the most challenging part in constructing the virtual cystoscopy. Segmentation results directly affect the subsequent processing. We present an approach of segmenting the bladder wall by solving minimum-cut problem on closure graphs which was firstly used to solve open-pit mining problem. The results were obtained by optimizing the cost functions designed for individual surface and geometric constraints defining the surface smoothness and interaction. This approach yielded precise results in segmenting the inner border of the bladder wall in 2D space, and has the potential to be extended to higher-dimensional space.
{"title":"The segmentation of MR bladder wall in 3D based on minimum closed set model","authors":"Yijia Zhang, C. Duan, Datian Ye, Zhengrong Liang","doi":"10.1109/ICMIPE.2013.6864560","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864560","url":null,"abstract":"Efficient and accurate segmentation of bladder wall on MR images is the most challenging part in constructing the virtual cystoscopy. Segmentation results directly affect the subsequent processing. We present an approach of segmenting the bladder wall by solving minimum-cut problem on closure graphs which was firstly used to solve open-pit mining problem. The results were obtained by optimizing the cost functions designed for individual surface and geometric constraints defining the surface smoothness and interaction. This approach yielded precise results in segmenting the inner border of the bladder wall in 2D space, and has the potential to be extended to higher-dimensional space.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122819682","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}
Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864534
Yaonan Zhang, Yu Xu, Jiangyuan Zhu, Tingting Sun
In order to make a diagnosis of cardiovascular disease, the edge of ventricular endometrial and skeleton line of ventricular septum are extracted by using computer-aided diagnosis techniques, and some shape analyses are done with the results, including the calculation of length of ventricular endometrial edge which plays an important role in analyzing heart contractions motion and the ventricular interval length which can be used as a reference when making a diagnosis of myocardial hypertrophy. Then an algorithm of auto-calculation of ventricular septum skeleton curvature is proposed as well as the conception of ventricular septum offset. In the meantime, calculation and data analysis of ventricular septum offset are all presented. Finally the evaluation of ventricular septum is achieved and be improved.
{"title":"The shape analysis of ventricular septum based on medical images","authors":"Yaonan Zhang, Yu Xu, Jiangyuan Zhu, Tingting Sun","doi":"10.1109/ICMIPE.2013.6864534","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864534","url":null,"abstract":"In order to make a diagnosis of cardiovascular disease, the edge of ventricular endometrial and skeleton line of ventricular septum are extracted by using computer-aided diagnosis techniques, and some shape analyses are done with the results, including the calculation of length of ventricular endometrial edge which plays an important role in analyzing heart contractions motion and the ventricular interval length which can be used as a reference when making a diagnosis of myocardial hypertrophy. Then an algorithm of auto-calculation of ventricular septum skeleton curvature is proposed as well as the conception of ventricular septum offset. In the meantime, calculation and data analysis of ventricular septum offset are all presented. Finally the evaluation of ventricular septum is achieved and be improved.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133780466","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}
Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864561
Sandler Ri, Zhao Hong-guang, Hou Sen, Lin Qiu-yu, Guan Feng
Objective: To evaluate the results of 99Tcm-sistamibi scintigraphy of patients with suspected primary hyperparathyroidism (PHPT). Methods: The results of 99Tcm-sistamibi scintigraphy and initial parathyroid hormone (PTH) measurement in 198 patients with suspicious PHPT were retrospectively analyzed. 198 patients with clinical suspicion of PHPT underwent 99Tcm-sistamibi scintigraphy and measured PTH. Ninety patients underwent surgery. The postoperative pathology was used as the gold standard for PHPT. The sensitivities, specificities, positive predictive values, negative predictive values, accuracies of 99Tcm-sistamibi scintigraphy, 99Tcm-sistamibi scintigraphy combined with dynamic monitoring of PTH measurement were compared and evaluated. Results: The sensitivities, specificities, positive predictive values, negative predictive values, accuracies of 99Tcm-sistamibi scintigraphy and 99Tcm-sistamibi scintigraphy combined with dynamic monitoring PTH measurement was 80%, 94.29%; 65%, 35%; 88.89%,88.61%; 48.15%,63.64%; 77.78%,81.11%, respectively. Conclusion: Detection of 99Tcm-sistamibi scintigraphy combined with dynamic monitoring PTH measurement can increase the diagnostic accuracy and decrease the rate of missed diagnosis.
{"title":"Diagnostic value of 99Tcm-sistamibi scintigraphy in hyperparathyroidism","authors":"Sandler Ri, Zhao Hong-guang, Hou Sen, Lin Qiu-yu, Guan Feng","doi":"10.1109/ICMIPE.2013.6864561","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864561","url":null,"abstract":"Objective: To evaluate the results of <sup>99</sup>Tc<sup>m</sup>-sistamibi scintigraphy of patients with suspected primary hyperparathyroidism (PHPT). Methods: The results of <sup>99</sup>Tc<sup>m</sup>-sistamibi scintigraphy and initial parathyroid hormone (PTH) measurement in 198 patients with suspicious PHPT were retrospectively analyzed. 198 patients with clinical suspicion of PHPT underwent <sup>99</sup>Tc<sup>m</sup>-sistamibi scintigraphy and measured PTH. Ninety patients underwent surgery. The postoperative pathology was used as the gold standard for PHPT. The sensitivities, specificities, positive predictive values, negative predictive values, accuracies of <sup>99</sup>Tc<sup>m</sup>-sistamibi scintigraphy, <sup>99</sup>Tc<sup>m</sup>-sistamibi scintigraphy combined with dynamic monitoring of PTH measurement were compared and evaluated. Results: The sensitivities, specificities, positive predictive values, negative predictive values, accuracies of <sup>99</sup>Tc<sup>m</sup>-sistamibi scintigraphy and <sup>99</sup>Tc<sup>m</sup>-sistamibi scintigraphy combined with dynamic monitoring PTH measurement was 80%, 94.29%; 65%, 35%; 88.89%,88.61%; 48.15%,63.64%; 77.78%,81.11%, respectively. Conclusion: Detection of <sup>99</sup>Tc<sup>m</sup>-sistamibi scintigraphy combined with dynamic monitoring PTH measurement can increase the diagnostic accuracy and decrease the rate of missed diagnosis.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132545118","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}
Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864567
L. Ding, Huailing Zhang, Yaoqin Xie
During radiotherapy, tumors in thorax or abdomen may deviate from the beam because of the physiological or physical influence, such as breathing. Extracorporeal marker is an important substitution to locate the tumors affected by respiratory motion. In this paper, a multi-camera vision system is proposed to track the extracorporeal marker on the model which can simulate respiratory motion. By acquiring the video of the marker, the barycentric coordinates of the markers are obtained. Finally, the 3D coordinate are calculated through calibrating the internal and external parameters of the cameras.
{"title":"Respiratory motion tracking with a multi-camera vision system","authors":"L. Ding, Huailing Zhang, Yaoqin Xie","doi":"10.1109/ICMIPE.2013.6864567","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864567","url":null,"abstract":"During radiotherapy, tumors in thorax or abdomen may deviate from the beam because of the physiological or physical influence, such as breathing. Extracorporeal marker is an important substitution to locate the tumors affected by respiratory motion. In this paper, a multi-camera vision system is proposed to track the extracorporeal marker on the model which can simulate respiratory motion. By acquiring the video of the marker, the barycentric coordinates of the markers are obtained. Finally, the 3D coordinate are calculated through calibrating the internal and external parameters of the cameras.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134213634","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}
Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864504
Fang Yang, M. Hamit, A. Kutluk, Chuanbo Yan, Li Li, Weikang Yuan, D. Kong
Image feature extraction technology has been widely used in medical field, but there is no related research on image feature extraction of high morbidity of esophageal cancer in Xinjiang. In this paper, feature extraction based on gray-scale histograms was applied in X-ray barium angiogram in high morbidity of esophageal cancer in Xinjiang. For the X-ray barium angiogram, converting RGB image to the grayscale intensity image, through median filter to remove the image noise and using histogram equalization to enhance the contrast; then the gray-level histograms was used to get the features of the images, and the classification ability of features was evaluated by Bayes discriminant analysis. The result show that feature classification ability was different when classifying different images, which provides a new direction for the research of computer aided diagnosis system for the high incidence of Kazak esophageal cancer in Xinjiang Uygur Autonomous Region.
{"title":"Feature extraction and analysis on X-ray image of Xinjiang Kazak Esophageal cancer by using gray-level histograms","authors":"Fang Yang, M. Hamit, A. Kutluk, Chuanbo Yan, Li Li, Weikang Yuan, D. Kong","doi":"10.1109/ICMIPE.2013.6864504","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864504","url":null,"abstract":"Image feature extraction technology has been widely used in medical field, but there is no related research on image feature extraction of high morbidity of esophageal cancer in Xinjiang. In this paper, feature extraction based on gray-scale histograms was applied in X-ray barium angiogram in high morbidity of esophageal cancer in Xinjiang. For the X-ray barium angiogram, converting RGB image to the grayscale intensity image, through median filter to remove the image noise and using histogram equalization to enhance the contrast; then the gray-level histograms was used to get the features of the images, and the classification ability of features was evaluated by Bayes discriminant analysis. The result show that feature classification ability was different when classifying different images, which provides a new direction for the research of computer aided diagnosis system for the high incidence of Kazak esophageal cancer in Xinjiang Uygur Autonomous Region.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134362433","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}
Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864530
Wen De-hui, Liu Cheng-liang, Wang Yi-cheng, Z. Xiao-fei, Liu Xiang-yu, Liu Jun-feng, Liu Hong-qiang, Gao Xin-chun
To analyze postoperative risk factors in deep venous thrombosis of lower extremities. Methods: A retrospective analysis was made on the postoperative data of 834 patients who received Color Doppler Flow Imaging (CDFI) for their veins of lower extremities at a 3 first-class ternary hospital from Oct., 2011 to Jun., 2013, then the χ test and multivariate Logistic regression analysis were performed on the possible risk factors contributed to thrombosis. Results: The results of χ test and multivariate Logistic regression analysis showed: age> 50 years (OR = 3.541), prolonged procedure time (OR = 3.409), postoperative heart failure (OR = 2.906), postoperative anxiety (OR = 2.508), postoperative fever (OR = 2.619), smoking (OR = 2.185), prolonged bed rest (OR = 2.995) were important risk factors; while postoperative moderate drinking (OR = 0.462), wearing elastic stockings (OR = 0.374) were protective factors. Conclusion: CDFI is an ideal examination method in the diagnosis of deep venous thrombosis of lower extremities, and the postoperative care should be strengthened to reduce this thrombosis[1].
{"title":"Application of Color Doppler Flow Imaging for analysis on postoperative risk factors contributed to deep venous thrombosis of lower extremities","authors":"Wen De-hui, Liu Cheng-liang, Wang Yi-cheng, Z. Xiao-fei, Liu Xiang-yu, Liu Jun-feng, Liu Hong-qiang, Gao Xin-chun","doi":"10.1109/ICMIPE.2013.6864530","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864530","url":null,"abstract":"To analyze postoperative risk factors in deep venous thrombosis of lower extremities. Methods: A retrospective analysis was made on the postoperative data of 834 patients who received Color Doppler Flow Imaging (CDFI) for their veins of lower extremities at a 3 first-class ternary hospital from Oct., 2011 to Jun., 2013, then the χ test and multivariate Logistic regression analysis were performed on the possible risk factors contributed to thrombosis. Results: The results of χ test and multivariate Logistic regression analysis showed: age> 50 years (OR = 3.541), prolonged procedure time (OR = 3.409), postoperative heart failure (OR = 2.906), postoperative anxiety (OR = 2.508), postoperative fever (OR = 2.619), smoking (OR = 2.185), prolonged bed rest (OR = 2.995) were important risk factors; while postoperative moderate drinking (OR = 0.462), wearing elastic stockings (OR = 0.374) were protective factors. Conclusion: CDFI is an ideal examination method in the diagnosis of deep venous thrombosis of lower extremities, and the postoperative care should be strengthened to reduce this thrombosis[1].","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123999109","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}
Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864550
Hongbo Guo, Yuqing Hou, Jingjing Yu, Chen Jin, Xiaowei He
Bioluminescence tomography (BLT) is a promising molecular imaging tool that may play an important role in preclinical research. However, the accurate and stable reconstruction of interior targets remains a challenge for wide application of this imaging modality. We present a novel reconstruction scheme to improve the BLT result by using the simplified spherical harmonics approximation model and homotopy method. In order to accurately model light propagation in biological tissue, the best approximation order is determined by comparing results of the SPN model (N = 1, 3, 5) with the Monte Carlo (MC) simulation data. Based on this forward model, a two-stage reconstruction using l1 Homotopy algorithm is then performed. Experimental results on a digital mouse model demonstrate that proposed reconstruction method yield improved results in terms of location accuracy, reconstructed density and time cost.
{"title":"Improved reconstruction for bioluminescence tomography by using the simplified spherical harmonics approximation model and homotopy method","authors":"Hongbo Guo, Yuqing Hou, Jingjing Yu, Chen Jin, Xiaowei He","doi":"10.1109/ICMIPE.2013.6864550","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864550","url":null,"abstract":"Bioluminescence tomography (BLT) is a promising molecular imaging tool that may play an important role in preclinical research. However, the accurate and stable reconstruction of interior targets remains a challenge for wide application of this imaging modality. We present a novel reconstruction scheme to improve the BLT result by using the simplified spherical harmonics approximation model and homotopy method. In order to accurately model light propagation in biological tissue, the best approximation order is determined by comparing results of the SPN model (N = 1, 3, 5) with the Monte Carlo (MC) simulation data. Based on this forward model, a two-stage reconstruction using l1 Homotopy algorithm is then performed. Experimental results on a digital mouse model demonstrate that proposed reconstruction method yield improved results in terms of location accuracy, reconstructed density and time cost.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124653173","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}
Pub Date : 2013-10-01DOI: 10.1109/ICMIPE.2013.6864549
Lei Zeng, Jing Chen, Li Tong, B. Yan, X. Ping
Many images suffer from poor contrast. It is necessary to enhance the contrast of images. Image enhancement improves an image appearance by increasing dominance of some features or by decreasing ambiguity between different regions of the image. Histogram equalization (HE) is widely used for contrast enhancement in a variety of applications due to its simple function and effectiveness. However, it usually results in excessive contrast enhancement, which causes the unnatural look and visual artifacts of the processed image. The improved algorithms, such as Brightness preserving Bi-Histogram Equalization, Recursive Mean-Separate Histogram Equalization, Dual Sub-Image Histogram Equalization and so on, are devoted to preserving the input image brightness and will be disappointed when the input image has low luminance. A novel method based on histogram similarity is developed to overcome the drawbacks of the classic HE algorithms for gray scale images. Compared to some of the conventional HE methods, the proposed method produces better contrast and image quality.
{"title":"Image contrast enhancement based on histogram similarity","authors":"Lei Zeng, Jing Chen, Li Tong, B. Yan, X. Ping","doi":"10.1109/ICMIPE.2013.6864549","DOIUrl":"https://doi.org/10.1109/ICMIPE.2013.6864549","url":null,"abstract":"Many images suffer from poor contrast. It is necessary to enhance the contrast of images. Image enhancement improves an image appearance by increasing dominance of some features or by decreasing ambiguity between different regions of the image. Histogram equalization (HE) is widely used for contrast enhancement in a variety of applications due to its simple function and effectiveness. However, it usually results in excessive contrast enhancement, which causes the unnatural look and visual artifacts of the processed image. The improved algorithms, such as Brightness preserving Bi-Histogram Equalization, Recursive Mean-Separate Histogram Equalization, Dual Sub-Image Histogram Equalization and so on, are devoted to preserving the input image brightness and will be disappointed when the input image has low luminance. A novel method based on histogram similarity is developed to overcome the drawbacks of the classic HE algorithms for gray scale images. Compared to some of the conventional HE methods, the proposed method produces better contrast and image quality.","PeriodicalId":135461,"journal":{"name":"2013 IEEE International Conference on Medical Imaging Physics and Engineering","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123331289","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：