Medical image registration is widely used in clinical diagnosis, treatment, quality assurance and it's also the prerequisite to realize the fusion and reconstruction. This paper presents an improved medical image registration algorithm based on mutual information. First of all, B-spline gradient operator is adopted to detect edges of the reference image and the floating image and then get binarization image respectively. Next, in order to obtain the centroid coordinates, the moments of the binarization image is calculated. According to the edge detection operator, the rotation angle of thereference image and floating image are obtained. In this paper, improved mutual information (IMI) is used as a measure ofsimilarity between the reference and floating images. Theexperimental results show that the proposed algorithm has theadvantages of low computational complexity and high accuracy, and overcomes the shortcomings of the traditional mutual information easily falling into local optimum.
{"title":"An Improved Medical Image Registration Algorithm Based on Mutual Information","authors":"Tian Lan, Hongbo Jiang, Yi Ding, Zhiguang Qin","doi":"10.1109/ICVISP.2017.9","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.9","url":null,"abstract":"Medical image registration is widely used in clinical diagnosis, treatment, quality assurance and it's also the prerequisite to realize the fusion and reconstruction. This paper presents an improved medical image registration algorithm based on mutual information. First of all, B-spline gradient operator is adopted to detect edges of the reference image and the floating image and then get binarization image respectively. Next, in order to obtain the centroid coordinates, the moments of the binarization image is calculated. According to the edge detection operator, the rotation angle of thereference image and floating image are obtained. In this paper, improved mutual information (IMI) is used as a measure ofsimilarity between the reference and floating images. Theexperimental results show that the proposed algorithm has theadvantages of low computational complexity and high accuracy, and overcomes the shortcomings of the traditional mutual information easily falling into local optimum.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125657252","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}
Unmanned Aerial Vehicles(UAV) are more and more wildly used recent years in many fields. It's convenient to acquire more static and dynamic information by uav aerial videos to grasp the scene situation. Frames registration, panoramic image mosaic, moving objects detection and tracking are the key and foundation of the aerial video analysis and processing. Firstly, we use a l_q-estimation method to remove the outliers and match the feature points robustly. Then we utilize a Moving Direct Linear Transformation (MDLT) method to find the homography of the frames more accurately, and stitch the frame sequence to a panorama. Finally, we apply a 5-frame difference method on the warped frames to detect the moving objects, and use a long-term visual tracking method to track the object of interest in complex scenes. The experiments show that our method achieve good results in different conditions.
{"title":"Panorama Stitching, Moving Object Detection and Tracking in UAV Videos","authors":"Quanlu Wei, Songyang Lao, Liang Bai","doi":"10.1109/ICVISP.2017.13","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.13","url":null,"abstract":"Unmanned Aerial Vehicles(UAV) are more and more wildly used recent years in many fields. It's convenient to acquire more static and dynamic information by uav aerial videos to grasp the scene situation. Frames registration, panoramic image mosaic, moving objects detection and tracking are the key and foundation of the aerial video analysis and processing. Firstly, we use a l_q-estimation method to remove the outliers and match the feature points robustly. Then we utilize a Moving Direct Linear Transformation (MDLT) method to find the homography of the frames more accurately, and stitch the frame sequence to a panorama. Finally, we apply a 5-frame difference method on the warped frames to detect the moving objects, and use a long-term visual tracking method to track the object of interest in complex scenes. The experiments show that our method achieve good results in different conditions.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116430685","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 self-adaptive differential evolution with dynamic selecting mutation strategy (DSMSDE) is proposed to improve the performance of differential evolution algorithm by three improvements. Mutation strategies are dynamically selected, and the successfully updated individuals are stored into the archive, which is beneficial for improving the convergence performance. A mechanism that is related to the best individual at the current population is employed to help the stagnation solutions to get rid of local minima. Self-adaptive parameters control is used to accelerate the convergence speed. DSMSDE is compared with the other state-of-the-art algorithms, and they are tested on nine benchmark functions. Experimental results show that DSMSDE has higher accuracy, faster speed and better reliability.
{"title":"A Self-Adaptive Differential Evolution with Dynamic Selecting Mutation Strategy","authors":"Xin Shen, D. Zou, Xin Zhang","doi":"10.1109/ICVISP.2017.26","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.26","url":null,"abstract":"A self-adaptive differential evolution with dynamic selecting mutation strategy (DSMSDE) is proposed to improve the performance of differential evolution algorithm by three improvements. Mutation strategies are dynamically selected, and the successfully updated individuals are stored into the archive, which is beneficial for improving the convergence performance. A mechanism that is related to the best individual at the current population is employed to help the stagnation solutions to get rid of local minima. Self-adaptive parameters control is used to accelerate the convergence speed. DSMSDE is compared with the other state-of-the-art algorithms, and they are tested on nine benchmark functions. Experimental results show that DSMSDE has higher accuracy, faster speed and better reliability.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128943012","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}
Choosing current major video coding standard, called H.264, to compress ultra-high resolution videos will cause low performance of compression in bitrate because of fixed macroblocks in H.264. For solving the large bitrate problem, a new video coding standard called High Efficiency Video Coding (HEVC) includes a quadtree-based Coding Unit (CU) block partitioning structure is established. However, HEVC causes a significant increase in computational complexity, compared to H.264 due to the necessity of searching the optimal Largest Coding Unit (LCU) partition. In this paper, we propose the fast luma-based CU partition (FLCUP) for HEVC intra prediction coding, which reduces significant computational complexity with negligible distortion in rate-distortion performance. FLCUP performs two steps: 1) analyzing the complexity of an original frame and 2) predicting LCU partition. Current the complexity of an original frame of LCU is analyzed by Discrete Wavelet Transform and several thresholds are obtained from experimental results. After analyzing the complexity of an original frame, FLCUP could predict the LCU partition for encoder without the unnecessary depth searching. Experimental results show that compared to the standard HEVC, FLCUP reduces the computational complexity by 38.63% at the cost of increasing only 1.62% in BD rate.
{"title":"Expediting Determination of Coding Unit Partition Based on Quantization Parameter and Frame Complexity","authors":"Chich-Wei Su, Chow-Sing Lin","doi":"10.1109/ICVISP.2017.20","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.20","url":null,"abstract":"Choosing current major video coding standard, called H.264, to compress ultra-high resolution videos will cause low performance of compression in bitrate because of fixed macroblocks in H.264. For solving the large bitrate problem, a new video coding standard called High Efficiency Video Coding (HEVC) includes a quadtree-based Coding Unit (CU) block partitioning structure is established. However, HEVC causes a significant increase in computational complexity, compared to H.264 due to the necessity of searching the optimal Largest Coding Unit (LCU) partition. In this paper, we propose the fast luma-based CU partition (FLCUP) for HEVC intra prediction coding, which reduces significant computational complexity with negligible distortion in rate-distortion performance. FLCUP performs two steps: 1) analyzing the complexity of an original frame and 2) predicting LCU partition. Current the complexity of an original frame of LCU is analyzed by Discrete Wavelet Transform and several thresholds are obtained from experimental results. After analyzing the complexity of an original frame, FLCUP could predict the LCU partition for encoder without the unnecessary depth searching. Experimental results show that compared to the standard HEVC, FLCUP reduces the computational complexity by 38.63% at the cost of increasing only 1.62% in BD rate.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"156 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128768371","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}
With the rapid development of optical industry and computer technology, optical interference measurement has become an important means of non-contact measurement. The noise and uneven distribution of light intensity are the main problems in the interference image, which make the traditional threshold segmentation methods are difficult to accurately segment the image. Based on twice mean filter subtraction, the method of image binaryzation can effectively solve the influence of noise and uneven illumination, and improve the accuracy of the segmentation. But with the fixed size of the filter window can not achieve a larger difference in the size of the interference fringes accurate segmentation. In order to realize the automation of interference image processing and improve the adaptability of algorithms, this paper presents a method which is adaptive template filtering subtraction binarization. This method can effectively segment the interference fringes with different thickness.
{"title":"A Kind of Effective Method for Interference Image Binarization","authors":"Qun Zhou, Min Wang, Xiaoping Shao","doi":"10.1109/ICVISP.2017.12","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.12","url":null,"abstract":"With the rapid development of optical industry and computer technology, optical interference measurement has become an important means of non-contact measurement. The noise and uneven distribution of light intensity are the main problems in the interference image, which make the traditional threshold segmentation methods are difficult to accurately segment the image. Based on twice mean filter subtraction, the method of image binaryzation can effectively solve the influence of noise and uneven illumination, and improve the accuracy of the segmentation. But with the fixed size of the filter window can not achieve a larger difference in the size of the interference fringes accurate segmentation. In order to realize the automation of interference image processing and improve the adaptability of algorithms, this paper presents a method which is adaptive template filtering subtraction binarization. This method can effectively segment the interference fringes with different thickness.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122270738","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}
In this paper the content based image retrieval system, using hybrid approach of features such as Texture and Color is presented. The color feature is extracted through Color Histogram and texture is extracted using Haar Wavelet Transformation. The combination of these features is robust to scaling and translation of objects in an image. The proposed system has demonstrated a promising and faster retrieval method on an image database containing general-purpose color images. The performance has been evaluated by comparing with the existing systems in the literature. The expansion of content based image retrieval technique can be found in a number of different domains. Content Based Image Retrieval is putting into practice for the image retrieval problem that is the problem of searching for digital images in large databases.
{"title":"Multilevel Haar Wavelet Transform and Histogram Usage in Content Based Image Retrieval System","authors":"D. Dhotre, G. Bamnote","doi":"10.1109/ICVISP.2017.34","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.34","url":null,"abstract":"In this paper the content based image retrieval system, using hybrid approach of features such as Texture and Color is presented. The color feature is extracted through Color Histogram and texture is extracted using Haar Wavelet Transformation. The combination of these features is robust to scaling and translation of objects in an image. The proposed system has demonstrated a promising and faster retrieval method on an image database containing general-purpose color images. The performance has been evaluated by comparing with the existing systems in the literature. The expansion of content based image retrieval technique can be found in a number of different domains. Content Based Image Retrieval is putting into practice for the image retrieval problem that is the problem of searching for digital images in large databases.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123481079","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}
This paper introduces a new general mathematical method for calculating the poles and zeros of a digital filter when transforming the poles and zeros of an analog filter in the s-domain into the poles and zeros of a digital filter in the zdomain by using inverse bilinear z-transformation with prewarping frequency technique. This paper also analyzes the poles and zeros of the digital Butterworth filters and indicates where they are distributed in the geometric curve in the zdomain, which allows visualization of the pole-zero locations and the stability of the desired digital filter design. In addition, the center frequency and the notch frequency are discussed in the designing of the digital Butterworth band stop. From that, the relationships among the lower frequency, the upper frequency and the notch frequency are derived and used as a new method to design a digital Butterworth band stop filter. In a special case, in which the notch frequency is equal to onequarter of the sampling frequency fs, the pole-zero transfer functions of the digital Butterworth filters are also investigated and it can be used to design a half-band filter in multi-rate digital signal processing.
{"title":"A New Formulation for Design of Digital IIR Band Stop Filters","authors":"Phuoc Si Nguyen","doi":"10.1109/ICVISP.2017.23","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.23","url":null,"abstract":"This paper introduces a new general mathematical method for calculating the poles and zeros of a digital filter when transforming the poles and zeros of an analog filter in the s-domain into the poles and zeros of a digital filter in the zdomain by using inverse bilinear z-transformation with prewarping frequency technique. This paper also analyzes the poles and zeros of the digital Butterworth filters and indicates where they are distributed in the geometric curve in the zdomain, which allows visualization of the pole-zero locations and the stability of the desired digital filter design. In addition, the center frequency and the notch frequency are discussed in the designing of the digital Butterworth band stop. From that, the relationships among the lower frequency, the upper frequency and the notch frequency are derived and used as a new method to design a digital Butterworth band stop filter. In a special case, in which the notch frequency is equal to onequarter of the sampling frequency fs, the pole-zero transfer functions of the digital Butterworth filters are also investigated and it can be used to design a half-band filter in multi-rate digital signal processing.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127578146","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}
The mathematical formula extraction is the prerequisite of formula structure analysis, recognition and retrieval. This paper studies the formula extraction method for the printed Chinese scientific and technical document images, proposes a criterion based on connected component run-length feature to estimate formulae in text lines, and then improves the formula location method based on rules. The connected component run-length's change regularity was analyzed firstly for all symbols in a text line. Then Change-rate threshold was set to estimate whether there is formula in this line. Finally, improved formula extraction method was given. The experimental results on the samples collected from printed Chinese scientific and technical documents showed that the proposed method is effective in estimate the embedded formula, and improves the accuracy of the formula location.
{"title":"An Improved Formula Extraction Method of Printed Chinese Layouts Based on Connected Component Run-Length Feature","authors":"Fang Yang, Chunning Hou, Xue-dong Tian","doi":"10.1109/ICVISP.2017.28","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.28","url":null,"abstract":"The mathematical formula extraction is the prerequisite of formula structure analysis, recognition and retrieval. This paper studies the formula extraction method for the printed Chinese scientific and technical document images, proposes a criterion based on connected component run-length feature to estimate formulae in text lines, and then improves the formula location method based on rules. The connected component run-length's change regularity was analyzed firstly for all symbols in a text line. Then Change-rate threshold was set to estimate whether there is formula in this line. Finally, improved formula extraction method was given. The experimental results on the samples collected from printed Chinese scientific and technical documents showed that the proposed method is effective in estimate the embedded formula, and improves the accuracy of the formula location.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122558650","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}
Veronika Haaf, Martin Neukamp, Jutta Hämmerle-Uhl, A. Uhl
Experiments with real-world non-NIR illumination as well as wavelength-specific acquisition settings are conducted with respect to impact on iris recognition performance, in particular considering variations in genuine score distribution. Illumination includes daylight, light bulbs, fluorescent tubes, halogen lamps, and mixed modes, while acquisition is done in visible wavelength, near infrared wavelength, and a combination of both. Results indicate very different results for blue and brown eyes respectively, with halogen illumination and visible and mixed-mode acquisition being an interesting option for a compromise setting.
{"title":"Real-World Non-NIR Illumination and Wavelength-Specific Acquisition Variants in Iris Recognition","authors":"Veronika Haaf, Martin Neukamp, Jutta Hämmerle-Uhl, A. Uhl","doi":"10.1109/ICVISP.2017.22","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.22","url":null,"abstract":"Experiments with real-world non-NIR illumination as well as wavelength-specific acquisition settings are conducted with respect to impact on iris recognition performance, in particular considering variations in genuine score distribution. Illumination includes daylight, light bulbs, fluorescent tubes, halogen lamps, and mixed modes, while acquisition is done in visible wavelength, near infrared wavelength, and a combination of both. Results indicate very different results for blue and brown eyes respectively, with halogen illumination and visible and mixed-mode acquisition being an interesting option for a compromise setting.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134061704","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}
We propose a novel image stitching method using multiple homographies. The method can stitch images having different parallaxes, such as an image that contains distant buildings and close trees. Such images might not be stitched with fine quality by single global homography. Therefore, we select a background homography by analyzing the inliers of the homographies estimated by RANSAC (random sample consensus) for leave-one-out segmented regions, and the left segmented region of the background homography is designated as an object region. Then, the object homography is estimated by the object region. Using these multiple homographies, image stitching and multi-band blending are performed. With this method, images having different parallaxes are stitched with higher visual quality than with other methods using single homography and multiple homographies.
{"title":"Image Stitching Using Multiple Homographies Estimated by Segmented Regions for Different Parallaxes","authors":"Daeho Lee, Jaeyoung Yoon, S. Lim","doi":"10.1109/ICVISP.2017.19","DOIUrl":"https://doi.org/10.1109/ICVISP.2017.19","url":null,"abstract":"We propose a novel image stitching method using multiple homographies. The method can stitch images having different parallaxes, such as an image that contains distant buildings and close trees. Such images might not be stitched with fine quality by single global homography. Therefore, we select a background homography by analyzing the inliers of the homographies estimated by RANSAC (random sample consensus) for leave-one-out segmented regions, and the left segmented region of the background homography is designated as an object region. Then, the object homography is estimated by the object region. Using these multiple homographies, image stitching and multi-band blending are performed. With this method, images having different parallaxes are stitched with higher visual quality than with other methods using single homography and multiple homographies.","PeriodicalId":404467,"journal":{"name":"2017 International Conference on Vision, Image and Signal Processing (ICVISP)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133864692","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：