Pub Date : 2003-09-17DOI: 10.1109/ICIAP.2003.1234116
H. Legal-Ayala, J. Facon
We present a new segmentation approach by thresholding based on learning strategy. This strategy is based only on one image and its ideal thresholded version. A decision matrix is generated from each pixel and each gray level. At the moment of new image segmentation, the best solution for each pixel is evaluated by means of K nearest neighbors in the decision matrix. Comparative tests were performed on signature, fingerprint and magnetic resonance images.
{"title":"Segmentation approach by learning: different image applications","authors":"H. Legal-Ayala, J. Facon","doi":"10.1109/ICIAP.2003.1234116","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234116","url":null,"abstract":"We present a new segmentation approach by thresholding based on learning strategy. This strategy is based only on one image and its ideal thresholded version. A decision matrix is generated from each pixel and each gray level. At the moment of new image segmentation, the best solution for each pixel is evaluated by means of K nearest neighbors in the decision matrix. Comparative tests were performed on signature, fingerprint and magnetic resonance images.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126249950","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234119
G. Garibotto, M. Corvi, Carlo Cibei, Sara Sciarrino
The proposed system is aimed at detecting and classifying 3D moving objects for security control of unmanned automatic railway stations. Most common approaches are based on active sensors like optical barriers or laser scanning devices. The proposed approach, named 3DMODS, is based on stereo vision technology, using a prediction-verification paradigm. Adaptive change detection is performed at the video rate to detect immediately moving objects in the scene. Object features are collected by "scanning" the scene with different parallel planes at variable height, to verify the volumetric consistency of the detected object. A prediction of stereo correspondence is performed, using homographic transformation on the set of predefined 3D planes, to verify whether the detected change is really a moving 3D object with a significant size, or just a phantom caused by shadows or highlights. A simple classification scheme is currently implemented to decide for an alarm candidate in case of relevant object size, but much more complex and flexible solutions are possible, to recognize all the relevant objects in the scene and achieve much more robust alarm detection performance.
{"title":"3DMODS: 3D moving obstacle detection system","authors":"G. Garibotto, M. Corvi, Carlo Cibei, Sara Sciarrino","doi":"10.1109/ICIAP.2003.1234119","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234119","url":null,"abstract":"The proposed system is aimed at detecting and classifying 3D moving objects for security control of unmanned automatic railway stations. Most common approaches are based on active sensors like optical barriers or laser scanning devices. The proposed approach, named 3DMODS, is based on stereo vision technology, using a prediction-verification paradigm. Adaptive change detection is performed at the video rate to detect immediately moving objects in the scene. Object features are collected by \"scanning\" the scene with different parallel planes at variable height, to verify the volumetric consistency of the detected object. A prediction of stereo correspondence is performed, using homographic transformation on the set of predefined 3D planes, to verify whether the detected change is really a moving 3D object with a significant size, or just a phantom caused by shadows or highlights. A simple classification scheme is currently implemented to decide for an alarm candidate in case of relevant object size, but much more complex and flexible solutions are possible, to recognize all the relevant objects in the scene and achieve much more robust alarm detection performance.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117336565","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234026
C. Conde, Antonio Ruiz, E. Cabello
Principal components analysis (PCA) has been one of the most applied methods for face verification using only 2D information, in fact, PCA is practically the method of choice for face verification applications in the real-world. An alternative method to reduce the problem dimension is working with low resolution images. In our experiments, three classifiers have been considered to compare the results achieved using PCA versus the results obtained using low resolution images. An initial set of located faces has been used for PCA matrix computation and for training all classifiers. The images belonging to the testing set were chosen to be different from the training ones. Classifiers considered are k-nearest neighbours (KNN), radial basis function (RBF) artificial neural networks, and support vector machine (SVM). Results show that SVM always achieves better results than the other classifiers. With SVM, correct verification difference between PCA and low resolution processing is only 0.13% (99.52% against 99.39%).
{"title":"PCA vs low resolution images in face verification","authors":"C. Conde, Antonio Ruiz, E. Cabello","doi":"10.1109/ICIAP.2003.1234026","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234026","url":null,"abstract":"Principal components analysis (PCA) has been one of the most applied methods for face verification using only 2D information, in fact, PCA is practically the method of choice for face verification applications in the real-world. An alternative method to reduce the problem dimension is working with low resolution images. In our experiments, three classifiers have been considered to compare the results achieved using PCA versus the results obtained using low resolution images. An initial set of located faces has been used for PCA matrix computation and for training all classifiers. The images belonging to the testing set were chosen to be different from the training ones. Classifiers considered are k-nearest neighbours (KNN), radial basis function (RBF) artificial neural networks, and support vector machine (SVM). Results show that SVM always achieves better results than the other classifiers. With SVM, correct verification difference between PCA and low resolution processing is only 0.13% (99.52% against 99.39%).","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"53 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133635032","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234034
L. Panini, R. Cucchiara
This paper describes an approach for human posture classification that has been devised for indoor surveillance in domotic applications. The approach was initially inspired to a previous work of Haritaoglou et al. (1998) that uses histogram projections to classify people's posture. We modify and improve the generality of the approach by adding a machine learning phase in order to generate probability maps. A statistic classifier has then defined that compares the probability maps and the histogram profiles extracted from each of the moving people. The approach is very robust if the initial constraints are satisfied and exhibits a very low computational time so that it can be used to process live videos with standard platforms.
{"title":"A machine learning approach for human posture detection in domotics applications","authors":"L. Panini, R. Cucchiara","doi":"10.1109/ICIAP.2003.1234034","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234034","url":null,"abstract":"This paper describes an approach for human posture classification that has been devised for indoor surveillance in domotic applications. The approach was initially inspired to a previous work of Haritaoglou et al. (1998) that uses histogram projections to classify people's posture. We modify and improve the generality of the approach by adding a machine learning phase in order to generate probability maps. A statistic classifier has then defined that compares the probability maps and the histogram profiles extracted from each of the moving people. The approach is very robust if the initial constraints are satisfied and exhibits a very low computational time so that it can be used to process live videos with standard platforms.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131687497","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234031
M. Hild, Motonobu Hashimoto, Kazunobu Yoshida
We propose an object recognition method in which the identity of objects is determined by observing the finger pointing action of persons. The system determines the head and hands regions, tracks them in real time, and verifies them through an analysis of 3D data points. Then it determines the pointing direction and intersects it with an environment model. Intersection computations are based on potential field models for both the finger pointing process and the object representations.
{"title":"Object recognition via recognition of finger pointing actions","authors":"M. Hild, Motonobu Hashimoto, Kazunobu Yoshida","doi":"10.1109/ICIAP.2003.1234031","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234031","url":null,"abstract":"We propose an object recognition method in which the identity of objects is determined by observing the finger pointing action of persons. The system determines the head and hands regions, tracks them in real time, and verifies them through an analysis of 3D data points. Then it determines the pointing direction and intersects it with an environment model. Intersection computations are based on potential field models for both the finger pointing process and the object representations.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132471402","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234061
E. Catanzariti, M. Ciminello, R. Prevete
This paper presents a multiresolution approach to the computer aided detection of clustered microcalcifications in digitized mammograms based on Gabor elementary functions. A bank of Gabor functions with varying spatial extent and tuned to different spatial frequencies is used for the extraction of microcalcifications characteristics. Classification is performed by an artificial neural network with supervised learning. First results show that most microcalcifications, isolated or clustered, are detected by our algorithm with a 95% value both for sensibility and specificity as measured on a test data set.
{"title":"Computer aided detection of clustered microcalcifications in digitized mammograms using Gabor functions","authors":"E. Catanzariti, M. Ciminello, R. Prevete","doi":"10.1109/ICIAP.2003.1234061","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234061","url":null,"abstract":"This paper presents a multiresolution approach to the computer aided detection of clustered microcalcifications in digitized mammograms based on Gabor elementary functions. A bank of Gabor functions with varying spatial extent and tuned to different spatial frequencies is used for the extraction of microcalcifications characteristics. Classification is performed by an artificial neural network with supervised learning. First results show that most microcalcifications, isolated or clustered, are detected by our algorithm with a 95% value both for sensibility and specificity as measured on a test data set.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126759686","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234040
F. Bertamini, R. Brunelli, O. Lanz, A. Roat, A. Santuari, F. Tobia, Qing Xu
This paper presents Olympus, a modular processing architecture for a distributed ambient intelligence. The system is aimed at detailed reporting of people wandering and gesturing in complex indoor environments. The design of the architecture has been driven by two main principles: reliable algorithm testing and system scalability. The first goal has been achieved through the development of Zeus, a real time 3D rendering engine that provides simulated sensory inputs supported by automatically generated ground truth for performance evaluation. The rendering engine is supported by Cronos, a flexible tool for the synthesis of choreographed motion of people visiting museums, based on modified force fields. Scalability has been achieved by developing Hermes, a modular architecture for multi-platform video grabbing, MPEG4 compression, stream delivery, and processing using a LAN as a distributed processing environment. A set of processing modules has been developed to increase the realism of generated synthetic images which have been used to develop and evaluate algorithms for people detection.
{"title":"Olympus: an ambient intelligence architecture on the verge of reality","authors":"F. Bertamini, R. Brunelli, O. Lanz, A. Roat, A. Santuari, F. Tobia, Qing Xu","doi":"10.1109/ICIAP.2003.1234040","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234040","url":null,"abstract":"This paper presents Olympus, a modular processing architecture for a distributed ambient intelligence. The system is aimed at detailed reporting of people wandering and gesturing in complex indoor environments. The design of the architecture has been driven by two main principles: reliable algorithm testing and system scalability. The first goal has been achieved through the development of Zeus, a real time 3D rendering engine that provides simulated sensory inputs supported by automatically generated ground truth for performance evaluation. The rendering engine is supported by Cronos, a flexible tool for the synthesis of choreographed motion of people visiting museums, based on modified force fields. Scalability has been achieved by developing Hermes, a modular architecture for multi-platform video grabbing, MPEG4 compression, stream delivery, and processing using a LAN as a distributed processing environment. A set of processing modules has been developed to increase the realism of generated synthetic images which have been used to develop and evaluate algorithms for people detection.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126852989","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234051
Y. Hu, T. Nagao
The paper describes a new method for locating and recognizing colored patterns of characters in complex scene images where translation, rotation, scale and contrast are unknown. A model of local shape feature vectors is presented. It consists of three vectors and represents some identifiable features in a pattern of characters. Based on this model, potential search points are first found from an unknown target image with this model matched to its edge image. Then, a template matching technique is employed on these candidate points, and the results are classified by a simple nearest neighborhood method and a best match is finally picked out in each cluster. Thus, multiple instances of a pattern of characters are matched and recognized. Experimental results demonstrate the effectiveness of this method.
{"title":"Matching of characters in scene images by using local shape feature vectors","authors":"Y. Hu, T. Nagao","doi":"10.1109/ICIAP.2003.1234051","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234051","url":null,"abstract":"The paper describes a new method for locating and recognizing colored patterns of characters in complex scene images where translation, rotation, scale and contrast are unknown. A model of local shape feature vectors is presented. It consists of three vectors and represents some identifiable features in a pattern of characters. Based on this model, potential search points are first found from an unknown target image with this model matched to its edge image. Then, a template matching technique is employed on these candidate points, and the results are classified by a simple nearest neighborhood method and a best match is finally picked out in each cluster. Thus, multiple instances of a pattern of characters are matched and recognized. Experimental results demonstrate the effectiveness of this method.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115596094","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234124
M. Pietikäinen
Faces and hands recorded under natural environments are frequently subject to illumination variations which affect their color appearance. This is a problem when the color cue is used to detect skin candidates at pixel level. Traditionally, color constancy has been suggested for correction, but after a lot of effort no good solution suitable for machine vision has emerged. However, many approaches have been proposed for general skin detection, but they are typically tested under mild changes in illumination chromaticity or do not define the variation range. This makes it difficult to evaluate their applicability for objects under varying illumination. The paper compares four state-of-the-art skin detection schemes under realistic conditions with drastic chromaticity change.
{"title":"Detection of skin color under changing illumination: a comparative study","authors":"M. Pietikäinen","doi":"10.1109/ICIAP.2003.1234124","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234124","url":null,"abstract":"Faces and hands recorded under natural environments are frequently subject to illumination variations which affect their color appearance. This is a problem when the color cue is used to detect skin candidates at pixel level. Traditionally, color constancy has been suggested for correction, but after a lot of effort no good solution suitable for machine vision has emerged. However, many approaches have been proposed for general skin detection, but they are typically tested under mild changes in illumination chromaticity or do not define the variation range. This makes it difficult to evaluate their applicability for objects under varying illumination. The paper compares four state-of-the-art skin detection schemes under realistic conditions with drastic chromaticity change.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114609052","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234033
L. Marchesotti, S. Piva, C. Regazzoni
This paper presents an agent-based architecture designed to functionally combine data from an homogeneous network of sensors for tracking purposes. The system has been developed in a video surveillance context to detect, classify and track moving objects in a scene of interest. Although single camera systems could perform the tasks outlined above, they would not be able to deal with topologically complex environments such as corridor, corners and indoor locations in general. The multi-sensor approach has been used to overcome these problems, nevertheless issues arise such as data fusion, synchronization and camera calibration. The sensor fusion approach here purposed uses autonomous software agents to negotiate the combination of data and the fusion is carried out by appropriate signal processing algorithms. The system has been tested with indoor video sequences to show the system's ability to preserve identity and of correct trajectory estimation of the tracked object.
{"title":"An agent-based approach for tracking people in indoor complex environments","authors":"L. Marchesotti, S. Piva, C. Regazzoni","doi":"10.1109/ICIAP.2003.1234033","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234033","url":null,"abstract":"This paper presents an agent-based architecture designed to functionally combine data from an homogeneous network of sensors for tracking purposes. The system has been developed in a video surveillance context to detect, classify and track moving objects in a scene of interest. Although single camera systems could perform the tasks outlined above, they would not be able to deal with topologically complex environments such as corridor, corners and indoor locations in general. The multi-sensor approach has been used to overcome these problems, nevertheless issues arise such as data fusion, synchronization and camera calibration. The sensor fusion approach here purposed uses autonomous software agents to negotiate the combination of data and the fusion is carried out by appropriate signal processing algorithms. The system has been tested with indoor video sequences to show the system's ability to preserve identity and of correct trajectory estimation of the tracked object.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114863124","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：