In this paper, we propose a new technique for image fusion in multi-view through-the-wall radar imaging system. As most existing image fusion methods for through-the-wall radar imaging only consider a global fusion operator, it is desirable to consider the differences between each pixel using a local operator. Here, we present a fuzzy logic-based method for pixel-wise image fusion. The performance of the proposed method is evaluated on both simulated and real data from through-the-wall radar imaging system. Experimental results show that the proposed method yields improved performance, compared to existing methods.
{"title":"Fuzzy Logic-Based Image Fusion for Multi-view Through-the-Wall Radar","authors":"C. H. Seng, A. Bouzerdoum, F. Tivive, M. Amin","doi":"10.1109/DICTA.2010.78","DOIUrl":"https://doi.org/10.1109/DICTA.2010.78","url":null,"abstract":"In this paper, we propose a new technique for image fusion in multi-view through-the-wall radar imaging system. As most existing image fusion methods for through-the-wall radar imaging only consider a global fusion operator, it is desirable to consider the differences between each pixel using a local operator. Here, we present a fuzzy logic-based method for pixel-wise image fusion. The performance of the proposed method is evaluated on both simulated and real data from through-the-wall radar imaging system. Experimental results show that the proposed method yields improved performance, compared to existing methods.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117121404","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}
J. Mitra, A. Oliver, R. Martí, X. Lladó, J. Vilanova, F. Mériaudeau
Registration is an important step during prostate biopsy with interventional Ultrasound (US) to project the Magnetic Resonance (MR) information of the corresponding slice of a pre-acquired MR volume of the same patient. This paper presents a method of deformable registration between US and MR prostate modalities using Thin-Plate Splines (TPS). The use of radial-basis functions such as splines is a typical approach for deformable registration wherein, TPS are more computationally efficient than Bsplines. However, registration with TPS employs strategic choice of correspondence points in the moving and reference images and therefore, has been rarely used by researchers for prostate registration. Aiming to deal with this issue, a novel method to automatically choose correspondence points (control points) based on the prostate geometry is presented in this paper. Shepard’s interpolation is used with the TPS in order to deal with the interpolation artifacts produced by reverse TPS transform. To evaluate the accuracy of our correspondence generation method, two intuitive geometric methods for prostate contour sampling are also implemented. Our registration results are validated using 4 patient datasets obtaining an average DSC of 0.97 ± 0.01.
{"title":"Multimodal Prostate Registration Using Thin-Plate Splines from Automatic Correspondences","authors":"J. Mitra, A. Oliver, R. Martí, X. Lladó, J. Vilanova, F. Mériaudeau","doi":"10.1109/DICTA.2010.104","DOIUrl":"https://doi.org/10.1109/DICTA.2010.104","url":null,"abstract":"Registration is an important step during prostate biopsy with interventional Ultrasound (US) to project the Magnetic Resonance (MR) information of the corresponding slice of a pre-acquired MR volume of the same patient. This paper presents a method of deformable registration between US and MR prostate modalities using Thin-Plate Splines (TPS). The use of radial-basis functions such as splines is a typical approach for deformable registration wherein, TPS are more computationally efficient than Bsplines. However, registration with TPS employs strategic choice of correspondence points in the moving and reference images and therefore, has been rarely used by researchers for prostate registration. Aiming to deal with this issue, a novel method to automatically choose correspondence points (control points) based on the prostate geometry is presented in this paper. Shepard’s interpolation is used with the TPS in order to deal with the interpolation artifacts produced by reverse TPS transform. To evaluate the accuracy of our correspondence generation method, two intuitive geometric methods for prostate contour sampling are also implemented. Our registration results are validated using 4 patient datasets obtaining an average DSC of 0.97 ± 0.01.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125024189","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}
An automatic building detection technique using LIDAR data and multispectral imagery has been proposed. Two masks are obtained from the LIDAR data: a `primary building mask' and a `secondary building mask'. The primary building mask indicates the void areas where the laser does not reach below a certain height threshold. The secondary building mask indicates the filled areas, from where the laser reflects, above the same threshold. Line segments are extracted from around the void areas in the primary building mask. Line segments around trees are removed using the normalized difference vegetation index derived from the orthorectified multispectral images. The initial building positions are obtained based on the remaining line segments. The complete buildings are detected from their initial positions using the two masks and multispectral images in the YIQ colour system. It is experimentally shown that the proposed technique can successfully detect buildings, when assessed in terms of 15 indices including completeness, correctness and quality.
{"title":"Automatic Building Detection Using LIDAR Data and Multispectral Imagery","authors":"M. Awrangjeb, M. Ravanbakhsh, C. Fraser","doi":"10.1109/DICTA.2010.17","DOIUrl":"https://doi.org/10.1109/DICTA.2010.17","url":null,"abstract":"An automatic building detection technique using LIDAR data and multispectral imagery has been proposed. Two masks are obtained from the LIDAR data: a `primary building mask' and a `secondary building mask'. The primary building mask indicates the void areas where the laser does not reach below a certain height threshold. The secondary building mask indicates the filled areas, from where the laser reflects, above the same threshold. Line segments are extracted from around the void areas in the primary building mask. Line segments around trees are removed using the normalized difference vegetation index derived from the orthorectified multispectral images. The initial building positions are obtained based on the remaining line segments. The complete buildings are detected from their initial positions using the two masks and multispectral images in the YIQ colour system. It is experimentally shown that the proposed technique can successfully detect buildings, when assessed in terms of 15 indices including completeness, correctness and quality.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123193688","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}
Contour-based corner detectors directly or indirectly estimate a significance measure (e.g. curvature) on the points of a planar curve and select the curvature extrema points as corners. While an extensive number of contour-based corner detectors have been proposed over the last four decades, there is no comparative study of recently proposed promising detectors. This paper is an attempt to fill this gap. We present the general frame-work of the contour-based corner detection technique and discuss two major issues – curve smoothing and curvature estimation, which have major impacts on the corner detection performance. A number of promising detectors are compared using an automatic evaluation system on a common large dataset. It is observed that while the detectors using indirect curvature estimation techniques are more robust, the detectors using direct curvature estimation techniques are faster.
{"title":"A Comparative Study on Contour-Based Corner Detectors","authors":"M. Awrangjeb, Guojun Lu, C. Fraser","doi":"10.1109/DICTA.2010.25","DOIUrl":"https://doi.org/10.1109/DICTA.2010.25","url":null,"abstract":"Contour-based corner detectors directly or indirectly estimate a significance measure (e.g. curvature) on the points of a planar curve and select the curvature extrema points as corners. While an extensive number of contour-based corner detectors have been proposed over the last four decades, there is no comparative study of recently proposed promising detectors. This paper is an attempt to fill this gap. We present the general frame-work of the contour-based corner detection technique and discuss two major issues – curve smoothing and curvature estimation, which have major impacts on the corner detection performance. A number of promising detectors are compared using an automatic evaluation system on a common large dataset. It is observed that while the detectors using indirect curvature estimation techniques are more robust, the detectors using direct curvature estimation techniques are faster.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115930650","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}
S. Fang, Y. Liu, S. Vinci-Booher, Bruce Anthony, F. Zhou
3D shape reconstruction is often a necessary step to obtain geometric information from multiple 2D images for shape analysis. In this paper, a new shape analysis technique is proposed using surface features derived directly from the video volume of 2D images. It avoids the explicit 3D reconstruction process, which is often not very robust and accurate for surface feature analysis. Video volumes are created from stacks of 2D images taken from a pre-determined set of views. Surface features are extracted from the video volumes for shape analysis. This technique is applied to a medical diagnosis application for Fetal Alcohol Syndrome (FAS) using images of mouse embryos.
{"title":"Surface Analysis from Video Volumes for Fetal Alcohol Syndrome Classification","authors":"S. Fang, Y. Liu, S. Vinci-Booher, Bruce Anthony, F. Zhou","doi":"10.1109/DICTA.2010.13","DOIUrl":"https://doi.org/10.1109/DICTA.2010.13","url":null,"abstract":"3D shape reconstruction is often a necessary step to obtain geometric information from multiple 2D images for shape analysis. In this paper, a new shape analysis technique is proposed using surface features derived directly from the video volume of 2D images. It avoids the explicit 3D reconstruction process, which is often not very robust and accurate for surface feature analysis. Video volumes are created from stacks of 2D images taken from a pre-determined set of views. Surface features are extracted from the video volumes for shape analysis. This technique is applied to a medical diagnosis application for Fetal Alcohol Syndrome (FAS) using images of mouse embryos.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130028773","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 explores a discriminative part-based approach for recognising people in video. It uses many regions to model the background and foreground and a random forest for classification. The objective is to overcome the limitations of more holistic approaches that try to recognise people as a single region with the consequential need to segment each person as one representation. Attributes of each blob, their relationships and variation over video frames are argued to be useful features for discrimination. In this paper the attributes of each blob are considered as a first step in the recognition process. We evaluate our approach through a comparison of three state of the art classifiers: Bagging, Adaboost and a Multilayer Perceptron (MLP), with the Random Forest (RF) using 10 fold cross validation. A detailed statistical analysis shows that the random forest classifier is more accurate compared to the other methods in terms of discrimination between regions describing people and those of the background.
{"title":"Part Based Recognition of Pedestrians Using Multiple Features and Random Forests","authors":"Gladis John, G. West, M. Lazarescu","doi":"10.1109/DICTA.2010.68","DOIUrl":"https://doi.org/10.1109/DICTA.2010.68","url":null,"abstract":"This paper explores a discriminative part-based approach for recognising people in video. It uses many regions to model the background and foreground and a random forest for classification. The objective is to overcome the limitations of more holistic approaches that try to recognise people as a single region with the consequential need to segment each person as one representation. Attributes of each blob, their relationships and variation over video frames are argued to be useful features for discrimination. In this paper the attributes of each blob are considered as a first step in the recognition process. We evaluate our approach through a comparison of three state of the art classifiers: Bagging, Adaboost and a Multilayer Perceptron (MLP), with the Random Forest (RF) using 10 fold cross validation. A detailed statistical analysis shows that the random forest classifier is more accurate compared to the other methods in terms of discrimination between regions describing people and those of the background.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134025795","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}
Feature enhancement in an image is to reinforce some exacted features so that it can be used for object classification and detection. As the thermal image is lack of texture and colorful information, the techniques for visual image feature enhancement is insufficient to apply to thermal images. In this paper, we propose a new gradient-based approach for feature enhancement in thermal image. We use the statistical properties of gradient of foreground object profiles, and formulate object features with gradient saliency. Empirical evaluation of the proposed approach shows significant performance improved on human contours which can be used for detection and classification.
{"title":"Feature Enhancement Using Gradient Salience on Thermal Image","authors":"Zelin Li, Jian Zhang, Qiang Wu, G. Geers","doi":"10.1109/DICTA.2010.99","DOIUrl":"https://doi.org/10.1109/DICTA.2010.99","url":null,"abstract":"Feature enhancement in an image is to reinforce some exacted features so that it can be used for object classification and detection. As the thermal image is lack of texture and colorful information, the techniques for visual image feature enhancement is insufficient to apply to thermal images. In this paper, we propose a new gradient-based approach for feature enhancement in thermal image. We use the statistical properties of gradient of foreground object profiles, and formulate object features with gradient saliency. Empirical evaluation of the proposed approach shows significant performance improved on human contours which can be used for detection and classification.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134430334","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}
I. Svalbe, Nikesh Nazareth, N. Normand, S. Chandra
Ghosts are digital images that contain highly constrained patterns of signed pixel values. The pixels are located so as to create zero-sums when discrete projections are taken across the image at a pre-determined set of angles. Ghosts can be applied to create image/anti-image pairs. An image that is entangled with its anti-image can be used to achieve forward error-correction in redundant data transmission schemes. Ghosts can also be used to help reconstruct images from asymmetric sets of real, noisy tomographic projection data. Minimal ghosts do these tasks most efficiently. We present here new methods to construct minimal ghost images that employ just 2N pixels to obtain zero-sum projections for N angles. Construction of an Nth order ghost had previously required O(2N) pixels.
{"title":"On Constructing Minimal Ghosts","authors":"I. Svalbe, Nikesh Nazareth, N. Normand, S. Chandra","doi":"10.1109/DICTA.2010.56","DOIUrl":"https://doi.org/10.1109/DICTA.2010.56","url":null,"abstract":"Ghosts are digital images that contain highly constrained patterns of signed pixel values. The pixels are located so as to create zero-sums when discrete projections are taken across the image at a pre-determined set of angles. Ghosts can be applied to create image/anti-image pairs. An image that is entangled with its anti-image can be used to achieve forward error-correction in redundant data transmission schemes. Ghosts can also be used to help reconstruct images from asymmetric sets of real, noisy tomographic projection data. Minimal ghosts do these tasks most efficiently. We present here new methods to construct minimal ghost images that employ just 2N pixels to obtain zero-sum projections for N angles. Construction of an Nth order ghost had previously required O(2N) pixels.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132162463","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}
Most digital cameras use a single image sensor to capture colour images. As a result, only one colour at each pixel location is acquired. Demosaicking is a technique to estimate all the other missing colour pixel information in order to produce a full colour image, while inverse demosaicking refers to the recovery of the single image sensor values from the full colour image. Early digital cameras using primitive demosaicking algorithms to produce a full colour image have resulted in inferior quality images with colour artifacts. Generally, the removal of those artifacts is not achievable by the application of direct filtering. If we can recover the actual image sensor values from a full colour image and re-demosaic it again using state-of-the-art recently developed demosaicking algorithms, a better image can be produced without filtering. In this paper, a novel technique using wavelet transform is proposed to inverse demosaic a full colour image in order to recover the actual sensor values. It is then re-demosaicked using an advanced recently developed demosaicking method to reproduce an output image with minimal colour artifacts.
{"title":"Reduction of Colour Artifacts Using Inverse Demosaicking","authors":"J. S. J. Li, S. Randhawa","doi":"10.1109/DICTA.2010.27","DOIUrl":"https://doi.org/10.1109/DICTA.2010.27","url":null,"abstract":"Most digital cameras use a single image sensor to capture colour images. As a result, only one colour at each pixel location is acquired. Demosaicking is a technique to estimate all the other missing colour pixel information in order to produce a full colour image, while inverse demosaicking refers to the recovery of the single image sensor values from the full colour image. Early digital cameras using primitive demosaicking algorithms to produce a full colour image have resulted in inferior quality images with colour artifacts. Generally, the removal of those artifacts is not achievable by the application of direct filtering. If we can recover the actual image sensor values from a full colour image and re-demosaic it again using state-of-the-art recently developed demosaicking algorithms, a better image can be produced without filtering. In this paper, a novel technique using wavelet transform is proposed to inverse demosaic a full colour image in order to recover the actual sensor values. It is then re-demosaicked using an advanced recently developed demosaicking method to reproduce an output image with minimal colour artifacts.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"906 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132567978","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}
Facial expression is the most natural and instinctive means for human beings to communicate with each other Automatic analysis of human facial expression remains a very challenging area of research in computer vision and machine learning. In this paper, a novel human emotion detection is proposed based on well-known local binary pattern (LBP) and a newly developed feature matrix. Facial feature is extracted using LBP. A unique feature matrix is then combined to apply to Adaptive Neuro Fuzzy Inference System to generate five facial expression models, namely, happy, sad, angry, disgust and surprise. A number of experiments are carried out on facial expression determination with different LBP techniques by varying the number of points and radius of neighbourhood to JAFFE face database. The proposed system achieves very high accuracy with LBP(16,2) which has outperformed most of the existing methods.
{"title":"A Novel Neuro Fuzzy Approach to Human Emotion Determination","authors":"Suvam Chatterjee, Hao Shi","doi":"10.1109/DICTA.2010.114","DOIUrl":"https://doi.org/10.1109/DICTA.2010.114","url":null,"abstract":"Facial expression is the most natural and instinctive means for human beings to communicate with each other Automatic analysis of human facial expression remains a very challenging area of research in computer vision and machine learning. In this paper, a novel human emotion detection is proposed based on well-known local binary pattern (LBP) and a newly developed feature matrix. Facial feature is extracted using LBP. A unique feature matrix is then combined to apply to Adaptive Neuro Fuzzy Inference System to generate five facial expression models, namely, happy, sad, angry, disgust and surprise. A number of experiments are carried out on facial expression determination with different LBP techniques by varying the number of points and radius of neighbourhood to JAFFE face database. The proposed system achieves very high accuracy with LBP(16,2) which has outperformed most of the existing methods.","PeriodicalId":246460,"journal":{"name":"2010 International Conference on Digital Image Computing: Techniques and Applications","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132687453","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：