Hyperspectral imaging systems produce very large quantities of high fidelity information presenting an arduous task of exploitation for the image analyst. The Lockheed Martin Advanced Technology Center (LM/ATC) is investigating an aural cueing technique by which the spectral information is sonically encoded. This creates an image exploitation system that employs multiple sensory modalities, auditory as well as visual, to facilitate analysis of multimodal imagery. This paper summarizes the encoding technique and describe several examples from a Fourier transform spectrometer whereby the spectral information is combined with traditional panchromatic imagery to create a multimodal imaging system
{"title":"Hyperspectral aural cueing","authors":"R. Kendrick, J. Mudge, D. Christie, E. Barrett","doi":"10.1109/AIPR.2005.31","DOIUrl":"https://doi.org/10.1109/AIPR.2005.31","url":null,"abstract":"Hyperspectral imaging systems produce very large quantities of high fidelity information presenting an arduous task of exploitation for the image analyst. The Lockheed Martin Advanced Technology Center (LM/ATC) is investigating an aural cueing technique by which the spectral information is sonically encoded. This creates an image exploitation system that employs multiple sensory modalities, auditory as well as visual, to facilitate analysis of multimodal imagery. This paper summarizes the encoding technique and describe several examples from a Fourier transform spectrometer whereby the spectral information is combined with traditional panchromatic imagery to create a multimodal imaging system","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117349253","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 content-based 3D mosaic representation for long video sequences of 3D and dynamic scenes captured by a camera on a mobile platform. The motion of the camera has a dominant direction of motion (as on an airplane or ground vehicle), but 6 degrees-of-freedom (DOF) motion is allowed. In the first step, a pair of generalized parallel-perspective (pushbroom) stereo mosaics is generated that captured both the 3D and dynamic aspects of the scene under the camera coverage. In the second step, a segmentation-based stereo matching algorithm is applied to extract parametric representation of the color, structure and motion of the dynamic and/or 3D objects in urban scenes where a lot of planar surfaces exist. Based on these results, the content-based 3D mosaic (CB3M) representation is created, which is a highly compressed visual representation for very long video sequences of dynamic 3D scenes. Experimental results are given
{"title":"Content-based 3D mosaic representation for video of dynamic 3D scenes","authors":"Zhigang Zhu, Hao Tang, G. Wolberg, J. Layne","doi":"10.1109/AIPR.2005.25","DOIUrl":"https://doi.org/10.1109/AIPR.2005.25","url":null,"abstract":"We propose a content-based 3D mosaic representation for long video sequences of 3D and dynamic scenes captured by a camera on a mobile platform. The motion of the camera has a dominant direction of motion (as on an airplane or ground vehicle), but 6 degrees-of-freedom (DOF) motion is allowed. In the first step, a pair of generalized parallel-perspective (pushbroom) stereo mosaics is generated that captured both the 3D and dynamic aspects of the scene under the camera coverage. In the second step, a segmentation-based stereo matching algorithm is applied to extract parametric representation of the color, structure and motion of the dynamic and/or 3D objects in urban scenes where a lot of planar surfaces exist. Based on these results, the content-based 3D mosaic (CB3M) representation is created, which is a highly compressed visual representation for very long video sequences of dynamic 3D scenes. Experimental results are given","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116164207","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 novel technique of reduction of the significance of overlapping features for efficient classification of complex patterns based on sparse network of windows where the features are the intensities at each pixel location of an image is proposed in this paper. Theoretical analysis performed on a set of patterns with overlapping features shows that the reduction of the significance of those features will improve the distinctiveness of the classifier. The methodology of classification is implemented in determining the pose and orientation of the face images in this paper. Classifying a face image of a particular pose from the rest of the face images with pose angles different from the first is essentially a two class problem. The probability distribution of the intensities at each pixel location over the entire training database of images is determined for both the classes and a measure of significance of the features is obtained based on the closeness in the relative probabilities of the two classes at that pixel. Features with equal probabilities are given least significance and features with largest difference in probabilities of the two classes are given highest significance. An efficient multilevel architecture for face detection with multiple classifiers for various face poses and orientations, keeping in view of the inherent symmetry of human face is also presented. The multiple levels in the classifier architecture deal with images of face regions in different degrees of orientations, poses and rotations in a hierarchical manner. An optimum image handling methodology resulted in reducing the number of classifiers required in the multilevel architecture to approximately half. Investigation of accuracy of head-pose estimation using the proposed technique is carried out. The proposed classification technique along with the architecture has been successful in discriminating face images whose pose angles are 100 apart. Comparison with other recent multiclass classification approaches in the context of pose estimation is carried out and it is observed that the technique is better both in terms of speed and accuracy
{"title":"An improved SNoW based classification technique for head-pose estimation and face detection","authors":"Satyanadh Gundimada, V. Asari","doi":"10.1109/AIPR.2005.16","DOIUrl":"https://doi.org/10.1109/AIPR.2005.16","url":null,"abstract":"A novel technique of reduction of the significance of overlapping features for efficient classification of complex patterns based on sparse network of windows where the features are the intensities at each pixel location of an image is proposed in this paper. Theoretical analysis performed on a set of patterns with overlapping features shows that the reduction of the significance of those features will improve the distinctiveness of the classifier. The methodology of classification is implemented in determining the pose and orientation of the face images in this paper. Classifying a face image of a particular pose from the rest of the face images with pose angles different from the first is essentially a two class problem. The probability distribution of the intensities at each pixel location over the entire training database of images is determined for both the classes and a measure of significance of the features is obtained based on the closeness in the relative probabilities of the two classes at that pixel. Features with equal probabilities are given least significance and features with largest difference in probabilities of the two classes are given highest significance. An efficient multilevel architecture for face detection with multiple classifiers for various face poses and orientations, keeping in view of the inherent symmetry of human face is also presented. The multiple levels in the classifier architecture deal with images of face regions in different degrees of orientations, poses and rotations in a hierarchical manner. An optimum image handling methodology resulted in reducing the number of classifiers required in the multilevel architecture to approximately half. Investigation of accuracy of head-pose estimation using the proposed technique is carried out. The proposed classification technique along with the architecture has been successful in discriminating face images whose pose angles are 100 apart. Comparison with other recent multiclass classification approaches in the context of pose estimation is carried out and it is observed that the technique is better both in terms of speed and accuracy","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121936908","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}
K. Linden, W. Neal, J. Waldman, A. Gatesman, A. Danylov
Definition and design of a terahertz standoff imaging system has been theoretically investigated. Utilizing terahertz quantum cascade lasers for transmitter and local oscillator, a detailed analysis of the expected performance of an active standoff imaging system based on coherent heterodyne detection has been carried out. Five atmospheric windows between 0.3 THz and 4.0 THz have been identified and quantified by carrying out laboratory measurements of atmospheric transmission as a function of relative humidity. Using the approximate center frequency of each of these windows, detailed calculations of expected system performance vs target distance, pixel resolution, and relative humidity were carried out. It is shown that with 1.5 THz laser radiation, a 10m standoff distance, 1 m times 1 m target area, and a 1cm times 1cm pixel resolution, a viable imaging system should be achievable. Performance calculations for various target distances, target pixel resolution, and laser frequency are presented
{"title":"Terahertz laser based standoff imaging system","authors":"K. Linden, W. Neal, J. Waldman, A. Gatesman, A. Danylov","doi":"10.1109/AIPR.2005.42","DOIUrl":"https://doi.org/10.1109/AIPR.2005.42","url":null,"abstract":"Definition and design of a terahertz standoff imaging system has been theoretically investigated. Utilizing terahertz quantum cascade lasers for transmitter and local oscillator, a detailed analysis of the expected performance of an active standoff imaging system based on coherent heterodyne detection has been carried out. Five atmospheric windows between 0.3 THz and 4.0 THz have been identified and quantified by carrying out laboratory measurements of atmospheric transmission as a function of relative humidity. Using the approximate center frequency of each of these windows, detailed calculations of expected system performance vs target distance, pixel resolution, and relative humidity were carried out. It is shown that with 1.5 THz laser radiation, a 10m standoff distance, 1 m times 1 m target area, and a 1cm times 1cm pixel resolution, a viable imaging system should be achievable. Performance calculations for various target distances, target pixel resolution, and laser frequency are presented","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130211308","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 multiband target detection algorithms implemented in hyperspectral imaging systems represent perhaps the most successful example of image fusion. A core suite of such signal processing methods that fuse spectral channels has been implemented in an operational system; more systems are planned. Stricter performance requirements for future remote sensing applications will be met by evolutionary improvements on these techniques. Here we first describe the operational methods and then the related next generation nonlinear methods, whose performance is currently being evaluated. Next we show how a "dual" representation of these algorithms can serve as a springboard to a radically new direction in algorithm research. Using nonlinear mathematics borrowed from machine learning concepts, we show how hyperspectral data from a high-dimensional spectral space can be transformed onto a manifold of even higher dimension, in which robust decision surfaces can be more easily generated. Such surfaces, when projected back into spectral space, appear as enveloping blankets that circumscribe clutter distributions in a way that the standard, covariance-based methods cannot. This property may permit the design of extremely low false-alarm rate solutions to remote detection problems
{"title":"Hyperspectral detection algorithms: operational, next generation, on the horizon","authors":"A. Schaum","doi":"10.1109/AIPR.2005.32","DOIUrl":"https://doi.org/10.1109/AIPR.2005.32","url":null,"abstract":"The multiband target detection algorithms implemented in hyperspectral imaging systems represent perhaps the most successful example of image fusion. A core suite of such signal processing methods that fuse spectral channels has been implemented in an operational system; more systems are planned. Stricter performance requirements for future remote sensing applications will be met by evolutionary improvements on these techniques. Here we first describe the operational methods and then the related next generation nonlinear methods, whose performance is currently being evaluated. Next we show how a \"dual\" representation of these algorithms can serve as a springboard to a radically new direction in algorithm research. Using nonlinear mathematics borrowed from machine learning concepts, we show how hyperspectral data from a high-dimensional spectral space can be transformed onto a manifold of even higher dimension, in which robust decision surfaces can be more easily generated. Such surfaces, when projected back into spectral space, appear as enveloping blankets that circumscribe clutter distributions in a way that the standard, covariance-based methods cannot. This property may permit the design of extremely low false-alarm rate solutions to remote detection problems","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130844215","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}
Li Tao, H. T. Ngo, Ming Z. Zhang, A. Livingston, V. Asari
A system of multisensor image fusion and enhancement for visibility improvement is proposed in this paper for helping drivers driving at night or under bad weather conditions. Video stream captured by a CCD camera is enhanced, then aligned and fused with another stream captured by a thermal camera to improve the visibility of roads in extremely low lighting conditions. A nonlinear image enhancement technique capable of dynamic range compression and contrast enhancement is developed to enhance the visible images prior to fusion. The thermal image and the enhanced visible image are then aligned based on prior information obtained on image registration process. Pixel-level multiresolution based image fusion method is applied to merge source images. After image fusion, a color restoration is performed on fused images with the chromatic information of visible images. The entire image processing and analysis system is being installed in an FPGA environment. Preliminary results obtained in various experiments conducted with the proposed system are encouraging
{"title":"A multisensor image fusion and enhancement system for assisting drivers in poor lighting conditions","authors":"Li Tao, H. T. Ngo, Ming Z. Zhang, A. Livingston, V. Asari","doi":"10.1109/AIPR.2005.9","DOIUrl":"https://doi.org/10.1109/AIPR.2005.9","url":null,"abstract":"A system of multisensor image fusion and enhancement for visibility improvement is proposed in this paper for helping drivers driving at night or under bad weather conditions. Video stream captured by a CCD camera is enhanced, then aligned and fused with another stream captured by a thermal camera to improve the visibility of roads in extremely low lighting conditions. A nonlinear image enhancement technique capable of dynamic range compression and contrast enhancement is developed to enhance the visible images prior to fusion. The thermal image and the enhanced visible image are then aligned based on prior information obtained on image registration process. Pixel-level multiresolution based image fusion method is applied to merge source images. After image fusion, a color restoration is performed on fused images with the chromatic information of visible images. The entire image processing and analysis system is being installed in an FPGA environment. Preliminary results obtained in various experiments conducted with the proposed system are encouraging","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132404035","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 report on the development and characterization of a field-portable hyperspectral imager designed to collect 128-band image cubes simultaneously in both the 4-5.25 /spl mu/m (mid wave infrared, MWIR) and 8-10.5 /spl mu/m (long wave infrared, LWIR) bands for detection of target as well as chemical/biological agents. The imager uses a specially designed diffractive optics Ge lens with a cooled dual-band 320/spl times/240 HgCdTe focal plane array. This lens performs both imaging and dispersive functions. The imager collects a single-color full scene image with a narrow band in the LWIR (e.g., at 8 /spl mu/m) using the first order diffraction and corresponding single-color image in the MWIR (4 /spl mu/m in this case) using the second order diffraction at the same time. Images at different wavelengths are obtained by moving the lens along its optical axis to focus the corresponding wavelengths. Here we discuss the imager and present field test data and results.
{"title":"A field-portable simultaneous dual-band infrared hyperspectral imager","authors":"N. Gupta, Dale Smith","doi":"10.1109/AIPR.2005.8","DOIUrl":"https://doi.org/10.1109/AIPR.2005.8","url":null,"abstract":"We report on the development and characterization of a field-portable hyperspectral imager designed to collect 128-band image cubes simultaneously in both the 4-5.25 /spl mu/m (mid wave infrared, MWIR) and 8-10.5 /spl mu/m (long wave infrared, LWIR) bands for detection of target as well as chemical/biological agents. The imager uses a specially designed diffractive optics Ge lens with a cooled dual-band 320/spl times/240 HgCdTe focal plane array. This lens performs both imaging and dispersive functions. The imager collects a single-color full scene image with a narrow band in the LWIR (e.g., at 8 /spl mu/m) using the first order diffraction and corresponding single-color image in the MWIR (4 /spl mu/m in this case) using the second order diffraction at the same time. Images at different wavelengths are obtained by moving the lens along its optical axis to focus the corresponding wavelengths. Here we discuss the imager and present field test data and results.","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121291811","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. Sayedelahl, R. P. Bording, M. Chouikha, J. Zeng
The subject of seismic migration is one of the most varied in seismic data processing. Many algorithms have been developed to perform this task, including Kirchhoff migration, finite-difference reverse time migration, and several types of phase shift migration. The purpose of this study is to investigate the possibility of using seismic inversion algorithms for radar signal processing to improve signal quality and reduce the effects of clutter based on the study of known geophysical inversion algorithms. The finite-difference reverse time migration method was studied in detail since it is one of the most accurate and general depth migration algorithms. It uses the finite difference wave equation modeling as a means of migrating seismic data. Preliminary experiments on the synthetic data generated from different models (a geophysical model and models similar to radar cases) were performed using the reverse-time migration algorithm
{"title":"A study of seismic inverse methods for radar signal processing","authors":"A. Sayedelahl, R. P. Bording, M. Chouikha, J. Zeng","doi":"10.1109/AIPR.2005.12","DOIUrl":"https://doi.org/10.1109/AIPR.2005.12","url":null,"abstract":"The subject of seismic migration is one of the most varied in seismic data processing. Many algorithms have been developed to perform this task, including Kirchhoff migration, finite-difference reverse time migration, and several types of phase shift migration. The purpose of this study is to investigate the possibility of using seismic inversion algorithms for radar signal processing to improve signal quality and reduce the effects of clutter based on the study of known geophysical inversion algorithms. The finite-difference reverse time migration method was studied in detail since it is one of the most accurate and general depth migration algorithms. It uses the finite difference wave equation modeling as a means of migrating seismic data. Preliminary experiments on the synthetic data generated from different models (a geophysical model and models similar to radar cases) were performed using the reverse-time migration algorithm","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126466232","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 study applies a technique from multi-spectral image classification to object detection in hyperspectral imagery. Reducing the decision surface around the object spectral signature helps extract objects from backgrounds. The object search is achieved through computation of the Mahalanobis distance between the average object spectral signature and the test pixel spectrum, a whitened Euclidean distance (WED). This restricted object search (WED), the adaptive cosine estimator (ACE), and the matched filter (MF) were applied to independent data sets, specifically to visible/near IR data collected from Aberdeen, MD and Yuma, Arizona. The robustness of this approach to object detection was tested by inserting object signatures taken directly from the scene and from statistically transformed object signatures from one time to another. This study found a substantial reduction in the number of false alarms (1 to 2 orders of magnitude) using WED and ACE relative to MF for the two independent data collects. No additional parameters are needed for WED. No spatial filtering is used in this study. No degradation in object detection is observed upon inserting the covariance matrix for the entire image into the Mahalanobis metric relative to using covariance matrix taken from the object.
{"title":"Segmentation approach and comparison to hyperspectral object detection algorithms","authors":"R. Mayer, J. Edwards, J. Antoniades","doi":"10.1109/AIPR.2005.41","DOIUrl":"https://doi.org/10.1109/AIPR.2005.41","url":null,"abstract":"This study applies a technique from multi-spectral image classification to object detection in hyperspectral imagery. Reducing the decision surface around the object spectral signature helps extract objects from backgrounds. The object search is achieved through computation of the Mahalanobis distance between the average object spectral signature and the test pixel spectrum, a whitened Euclidean distance (WED). This restricted object search (WED), the adaptive cosine estimator (ACE), and the matched filter (MF) were applied to independent data sets, specifically to visible/near IR data collected from Aberdeen, MD and Yuma, Arizona. The robustness of this approach to object detection was tested by inserting object signatures taken directly from the scene and from statistically transformed object signatures from one time to another. This study found a substantial reduction in the number of false alarms (1 to 2 orders of magnitude) using WED and ACE relative to MF for the two independent data collects. No additional parameters are needed for WED. No spatial filtering is used in this study. No degradation in object detection is observed upon inserting the covariance matrix for the entire image into the Mahalanobis metric relative to using covariance matrix taken from the object.","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114099225","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, we present a comprehensive validation analysis to evaluate the performance of three existing mammogram segmentation algorithms against manual segmentation results produced by two expert radiologists. These studies are especially important for the development of computer-aided cancer detection (CAD) systems, which will significantly help improve early detection of breast cancer. Three typical segmentation methods were implemented and applied to 50 malignant mammography images chosen from the University of South Florida's Digital Database for Screening Mammography (DDSM): (a) region growing combined with maximum likelihood modeling (Kinnard model), (b) an active deformable contour model (snake model), and (c) a standard potential field model (standard model). A comprehensive statistical validation protocol was applied to evaluate the computer and expert outlined segmentation results; both sets of results were examined from the inter- and intra-observer points of view. Experimental results are presented and discussed in this communication
{"title":"Performance assessment of mammography image segmentation algorithms","authors":"K. Byrd, J. Zeng, M. Chouikha","doi":"10.1109/AIPR.2005.39","DOIUrl":"https://doi.org/10.1109/AIPR.2005.39","url":null,"abstract":"In this paper, we present a comprehensive validation analysis to evaluate the performance of three existing mammogram segmentation algorithms against manual segmentation results produced by two expert radiologists. These studies are especially important for the development of computer-aided cancer detection (CAD) systems, which will significantly help improve early detection of breast cancer. Three typical segmentation methods were implemented and applied to 50 malignant mammography images chosen from the University of South Florida's Digital Database for Screening Mammography (DDSM): (a) region growing combined with maximum likelihood modeling (Kinnard model), (b) an active deformable contour model (snake model), and (c) a standard potential field model (standard model). A comprehensive statistical validation protocol was applied to evaluate the computer and expert outlined segmentation results; both sets of results were examined from the inter- and intra-observer points of view. Experimental results are presented and discussed in this communication","PeriodicalId":130204,"journal":{"name":"34th Applied Imagery and Pattern Recognition Workshop (AIPR'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116269498","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：