Pub Date : 2001-09-26DOI: 10.1109/ICIAP.2001.957022
T. Caetano, D. Barone
We present a multivariate statistical model to represent the human skin color. There are no limitations regarding whether the person is white or black, once the model is able to learn automatically the ethnicity of the person involved. We propose to model the skin color in the chromatic subspace, which is by default normalized with respect to illumination. First, skin samples from both white and black people are collected. These samples are then used to estimate a parametric statistical model, which consists of a mixture of Gaussian probability density functions (pdfs). Estimation is performed by a learning process based on the expectation-maximization (EM) algorithm. Experiments are carried out and receiver operating characteristics (ROC curves) are obtained to analyse the performance of the estimated model. The results are compared to those of models that use a single Gaussian density.
{"title":"A probabilistic model for the human skin color","authors":"T. Caetano, D. Barone","doi":"10.1109/ICIAP.2001.957022","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957022","url":null,"abstract":"We present a multivariate statistical model to represent the human skin color. There are no limitations regarding whether the person is white or black, once the model is able to learn automatically the ethnicity of the person involved. We propose to model the skin color in the chromatic subspace, which is by default normalized with respect to illumination. First, skin samples from both white and black people are collected. These samples are then used to estimate a parametric statistical model, which consists of a mixture of Gaussian probability density functions (pdfs). Estimation is performed by a learning process based on the expectation-maximization (EM) algorithm. Experiments are carried out and receiver operating characteristics (ROC curves) are obtained to analyse the performance of the estimated model. The results are compared to those of models that use a single Gaussian density.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131010350","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957060
D. Tegolo, F. Isgrò
This paper investigates the removal of line scratches from old moving pictures and gives a twofold contribution. First, it presents a simple technique for detecting the scratches, based on an analysis of the statistics of the grey levels. Second, the scratch removal is approached as an optimisation problem, which is solved by using a genetic algorithm. The method can be classified as a static approach, as it works independently on each single frame of the sequence. It does not require any a-priori knowledge of the absolute position of the scratch, nor an external starting population of chromosomes for the genetic algorithm. The central column of the line scratch once detected is changed with a conventional linear interpolation; this transformation is the starting point of the optimisation process.
{"title":"A genetic algorithm for scratch removal in static images","authors":"D. Tegolo, F. Isgrò","doi":"10.1109/ICIAP.2001.957060","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957060","url":null,"abstract":"This paper investigates the removal of line scratches from old moving pictures and gives a twofold contribution. First, it presents a simple technique for detecting the scratches, based on an analysis of the statistics of the grey levels. Second, the scratch removal is approached as an optimisation problem, which is solved by using a genetic algorithm. The method can be classified as a static approach, as it works independently on each single frame of the sequence. It does not require any a-priori knowledge of the absolute position of the scratch, nor an external starting population of chromosomes for the genetic algorithm. The central column of the line scratch once detected is changed with a conventional linear interpolation; this transformation is the starting point of the optimisation process.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115801546","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957039
James Ze Wang, Yanping Du
The region-based approach has become a popular research trend in the field of multimedia database retrieval. We present the Region Frequency and Inverse Picture Frequency (RF/sup */IPF) weighting, a measure developed to unify region-based multimedia retrieval systems with text-based information retrieval systems. The weighting measure gives the highest weight to regions that occur often in a small number of images in the database. These regions are considered discriminators. With this weighting measure, we can blend image retrieval techniques with TF/sup */IDF-based text retrieval techniques for large-scale Web applications. The RF/sup */IPF weighting has been implemented as a part of our experimental SIMPLIcity image retrieval system and tested on a database of about 200000 general-purpose images. Experiments have shown that this technique is effective in discriminating images of different semantics. Additionally, the overall similarity approach enables a simple querying interface for multimedia information retrieval systems.
{"title":"RF/sup */IPF: a weighting scheme for multimedia information retrieval","authors":"James Ze Wang, Yanping Du","doi":"10.1109/ICIAP.2001.957039","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957039","url":null,"abstract":"The region-based approach has become a popular research trend in the field of multimedia database retrieval. We present the Region Frequency and Inverse Picture Frequency (RF/sup */IPF) weighting, a measure developed to unify region-based multimedia retrieval systems with text-based information retrieval systems. The weighting measure gives the highest weight to regions that occur often in a small number of images in the database. These regions are considered discriminators. With this weighting measure, we can blend image retrieval techniques with TF/sup */IDF-based text retrieval techniques for large-scale Web applications. The RF/sup */IPF weighting has been implemented as a part of our experimental SIMPLIcity image retrieval system and tested on a database of about 200000 general-purpose images. Experiments have shown that this technique is effective in discriminating images of different semantics. Additionally, the overall similarity approach enables a simple querying interface for multimedia information retrieval systems.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"371 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134374667","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957076
S. Battiato, M. Mancuso, A. Bosco, M. Guarnera
The paper presents a new and statistically robust algorithm able to improve the performance of the standard DCT compression algorithm for both perceived quality and compression size. The approach proposed combines together an information theoretical/statistical approach with HVS (human visual system) response functions. The methodology applied permits us to obtain a suitable quantization table for specific classes of images and specific viewing conditions. The paper presents a case study where the right parameters are learned after an extensive experimental phase, for three specific classes: document, landscape and portrait. The results show both perceptive and measured (in term of PSNR) improvement. A further application shows how it is possible obtain significant improvement profiling the relative DCT error inside the pipeline of images acquired by typical digital sensors.
{"title":"Psychovisual and statistical optimization of quantization tables for DCT compression engines","authors":"S. Battiato, M. Mancuso, A. Bosco, M. Guarnera","doi":"10.1109/ICIAP.2001.957076","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957076","url":null,"abstract":"The paper presents a new and statistically robust algorithm able to improve the performance of the standard DCT compression algorithm for both perceived quality and compression size. The approach proposed combines together an information theoretical/statistical approach with HVS (human visual system) response functions. The methodology applied permits us to obtain a suitable quantization table for specific classes of images and specific viewing conditions. The paper presents a case study where the right parameters are learned after an extensive experimental phase, for three specific classes: document, landscape and portrait. The results show both perceptive and measured (in term of PSNR) improvement. A further application shows how it is possible obtain significant improvement profiling the relative DCT error inside the pipeline of images acquired by typical digital sensors.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124776377","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.956988
Ying Ren, C. Chua, Yeong-Khing Ho
This paper proposes a new method for moving object (foreground) detection with non-stationary background using background subtraction. While background subtraction has traditionally worked well for stationary backgrounds, the same cannot be implied for a nonstationary viewing sensor. To a limited extent, motion compensation for non-stationary backgrounds can be applied, but in practice, it is difficult to realize the motion compensation to sufficient accuracy and the background subtraction algorithm will fail for a moving scene. The problem is further compounded when the moving target to be detected/tracked is small, since the pixel error in motion compensating the background will subsume the small target. A spatial distribution of Gaussians (SDG) model is proposed to deal with moving object detection having motion compensation which is only approximately extracted. The distribution of each background pixel is temporally and spatially modeled; a pixel in the current frame is then classified based on this statistical model. The emphasis of this approach is on the robust detection of moving objects even with approximately accurate motion compensation, noise, or environmental changes. Test cases involving the detection of small moving objects with a highly textured background and a pan-tilt tracking system are demonstrated successfully.
{"title":"Motion detection with non-stationary background","authors":"Ying Ren, C. Chua, Yeong-Khing Ho","doi":"10.1109/ICIAP.2001.956988","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956988","url":null,"abstract":"This paper proposes a new method for moving object (foreground) detection with non-stationary background using background subtraction. While background subtraction has traditionally worked well for stationary backgrounds, the same cannot be implied for a nonstationary viewing sensor. To a limited extent, motion compensation for non-stationary backgrounds can be applied, but in practice, it is difficult to realize the motion compensation to sufficient accuracy and the background subtraction algorithm will fail for a moving scene. The problem is further compounded when the moving target to be detected/tracked is small, since the pixel error in motion compensating the background will subsume the small target. A spatial distribution of Gaussians (SDG) model is proposed to deal with moving object detection having motion compensation which is only approximately extracted. The distribution of each background pixel is temporally and spatially modeled; a pixel in the current frame is then classified based on this statistical model. The emphasis of this approach is on the robust detection of moving objects even with approximately accurate motion compensation, noise, or environmental changes. Test cases involving the detection of small moving objects with a highly textured background and a pan-tilt tracking system are demonstrated successfully.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125340353","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957020
Markos Markou, Sameer Singh, Mona Sharma
Scene analysis is an important area of research with the aim of identifying objects and their relationships in natural scenes. The MINERVA benchmark has recently been introduced in this area for testing different image processing and classification schemes. We present results on the classification of eight natural objects in the complete set of 448 natural images using neural networks. An exhaustive set of experiments with this benchmark has been conducted using four different segmentation methods and five texture-based feature extraction methods. The results in this paper show the performance of a neural network classifier on a ten fold cross-validation task. On the basis of the results produced, we are able to rank how well different image segmentation algorithms are suited to the task of region of interest identification in these images, and we also see how well texture extraction algorithms rank on the basis of classification results.
{"title":"Neural network analysis of MINERVA scene analysis benchmark","authors":"Markos Markou, Sameer Singh, Mona Sharma","doi":"10.1109/ICIAP.2001.957020","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957020","url":null,"abstract":"Scene analysis is an important area of research with the aim of identifying objects and their relationships in natural scenes. The MINERVA benchmark has recently been introduced in this area for testing different image processing and classification schemes. We present results on the classification of eight natural objects in the complete set of 448 natural images using neural networks. An exhaustive set of experiments with this benchmark has been conducted using four different segmentation methods and five texture-based feature extraction methods. The results in this paper show the performance of a neural network classifier on a ten fold cross-validation task. On the basis of the results produced, we are able to rank how well different image segmentation algorithms are suited to the task of region of interest identification in these images, and we also see how well texture extraction algorithms rank on the basis of classification results.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126613325","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957038
Alberto Valinetti, Andrea Fusiello, Vittorio Murino
This paper presents a technique for tracking complex objects (both polyhedral and smooth boundaries) in a monocular sequence. Our aim is to use this model tracking method in an augmented reality context to compute the pose of a real object to be able to register it with a synthetic one. A scalar score function for an object pose is defined, based on the local image gradient along the projected model boundaries. A local search is then carried out in the configuration space of the pose to maximize the score. This technique is robust to occlusions, since the whole object contour is used, not just a few control points. The proposed method is effective yet simple. No image feature extraction is necessary and no complex temporal evolution is used. Experimental results with a real sequence show the good performance of our technique.
{"title":"Model tracking for video-based virtual reality","authors":"Alberto Valinetti, Andrea Fusiello, Vittorio Murino","doi":"10.1109/ICIAP.2001.957038","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957038","url":null,"abstract":"This paper presents a technique for tracking complex objects (both polyhedral and smooth boundaries) in a monocular sequence. Our aim is to use this model tracking method in an augmented reality context to compute the pose of a real object to be able to register it with a synthetic one. A scalar score function for an object pose is defined, based on the local image gradient along the projected model boundaries. A local search is then carried out in the configuration space of the pose to maximize the score. This technique is robust to occlusions, since the whole object contour is used, not just a few control points. The proposed method is effective yet simple. No image feature extraction is necessary and no complex temporal evolution is used. Experimental results with a real sequence show the good performance of our technique.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121906004","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957019
Giosuè Lo Bosco
The paper describes a new algorithm for image segmentation. It is based on a genetic approach that allow us to consider the segmentation problem as a global optimization problem (GOP). For this purpose, a fitness function, based on the similarity between images, has been defined. The similarity is a function of both the intensity and the spatial position of pixels. Preliminary results, obtained using real images, show a good performance of the segmentation algorithm.
{"title":"A genetic algorithm for image segmentation","authors":"Giosuè Lo Bosco","doi":"10.1109/ICIAP.2001.957019","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957019","url":null,"abstract":"The paper describes a new algorithm for image segmentation. It is based on a genetic approach that allow us to consider the segmentation problem as a global optimization problem (GOP). For this purpose, a fitness function, based on the similarity between images, has been defined. The similarity is a function of both the intensity and the spatial position of pixels. Preliminary results, obtained using real images, show a good performance of the segmentation algorithm.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131292810","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957036
R. Cucchiara, C. Grana, A. Prati, M. Piccardi
Many approaches to moving object detection for traffic monitoring and video surveillance proposed in the literature are based on background suppression methods. How to correctly and efficiently update the background model and how to deal with shadows are two of the more distinguishing and challenging features of such approaches. This work presents a general-purpose method for segmentation of moving visual objects (MVO) based on an object-level classification in MVO, ghosts and shadows. Background suppression needs the background model to be estimated and updated: we use motion and shadow information to selectively exclude from the background model MVO and their shadows, while retaining ghosts. The color information (in the HSV color space) is exploited to shadow suppression and, consequently, to enhance both MVO segmentation and background update.
{"title":"Detecting objects, shadows and ghosts in video streams by exploiting color and motion information","authors":"R. Cucchiara, C. Grana, A. Prati, M. Piccardi","doi":"10.1109/ICIAP.2001.957036","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957036","url":null,"abstract":"Many approaches to moving object detection for traffic monitoring and video surveillance proposed in the literature are based on background suppression methods. How to correctly and efficiently update the background model and how to deal with shadows are two of the more distinguishing and challenging features of such approaches. This work presents a general-purpose method for segmentation of moving visual objects (MVO) based on an object-level classification in MVO, ghosts and shadows. Background suppression needs the background model to be estimated and updated: we use motion and shadow information to selectively exclude from the background model MVO and their shadows, while retaining ghosts. The color information (in the HSV color space) is exploited to shadow suppression and, consequently, to enhance both MVO segmentation and background update.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132339570","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957070
A. Branca, E. Stella, N. Ancona, A. Distante
We examine the problem of object positioning in the 3D Euclidean space from uncalibrated images. It is well known that this can be accomplished if partial information about some points or planes in the observed scene are available. We consider the specific context of plotting the 3D position of a goal-bound soccer ball. In this context we know the position in the 3D Euclidean space of the straight lines defining the boundary of the goal-mouth structure. The method we consider handles pairs of uncalibrated images using the "plane + parallax" (P+P) approach. We propose to estimate the distance of the ball from the goal-plane through its parallax displacement between the two views with respect to the physical planar surface of the goal-plane. The performance of the approach has been determined on synthetic data obtained simulating different real contexts. Moreover the method has been tested also on real images acquired with a binocular system appropriately positioned in a real environment.
{"title":"Goal distance estimation in soccer game","authors":"A. Branca, E. Stella, N. Ancona, A. Distante","doi":"10.1109/ICIAP.2001.957070","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957070","url":null,"abstract":"We examine the problem of object positioning in the 3D Euclidean space from uncalibrated images. It is well known that this can be accomplished if partial information about some points or planes in the observed scene are available. We consider the specific context of plotting the 3D position of a goal-bound soccer ball. In this context we know the position in the 3D Euclidean space of the straight lines defining the boundary of the goal-mouth structure. The method we consider handles pairs of uncalibrated images using the \"plane + parallax\" (P+P) approach. We propose to estimate the distance of the ball from the goal-plane through its parallax displacement between the two views with respect to the physical planar surface of the goal-plane. The performance of the approach has been determined on synthetic data obtained simulating different real contexts. Moreover the method has been tested also on real images acquired with a binocular system appropriately positioned in a real environment.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"209 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122909939","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：