Pub Date : 2008-11-01DOI: 10.1109/IPTA.2008.4743786
S. Prakash, U. Jayaraman, P. Gupta
The paper presents an efficient distance transform and template based technique for automatic ear localization from a side face image. The technique first segments skin and non-skin regions in the face and then uses template based approach to find the ear location within the skin regions. Ear detection proceeds as follows. First, edge map of the skin regions is computed and further processed to eliminate the spurious edges based on length and curvature based criterion. After getting the clean edge map, its distance transform is obtained on which ear localization process is carried out. Distance transform image of the edge map of an off-line created ear template is employed for ear localization. A Zernike moment based shape descriptor is used to verify the detections. The technique is tested on IIT Kanpur ear database which contains around 150 ear images and found to be giving 95.2% accuracy.
{"title":"Ear Localization from Side Face Images using Distance Transform and Template Matching","authors":"S. Prakash, U. Jayaraman, P. Gupta","doi":"10.1109/IPTA.2008.4743786","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743786","url":null,"abstract":"The paper presents an efficient distance transform and template based technique for automatic ear localization from a side face image. The technique first segments skin and non-skin regions in the face and then uses template based approach to find the ear location within the skin regions. Ear detection proceeds as follows. First, edge map of the skin regions is computed and further processed to eliminate the spurious edges based on length and curvature based criterion. After getting the clean edge map, its distance transform is obtained on which ear localization process is carried out. Distance transform image of the edge map of an off-line created ear template is employed for ear localization. A Zernike moment based shape descriptor is used to verify the detections. The technique is tested on IIT Kanpur ear database which contains around 150 ear images and found to be giving 95.2% accuracy.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114265159","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743784
Rajavel . Pl, R. Aravind
This paper proposes a wrapping based directional Hartley transform (WDirHT) in the Hartley domain. The wrapping based curvelet transform is used to construct the WDirHT in the Hartley domain. The WDirHT is a sparse representation than curvelet transform. The redundancy factor of the transform is 2.82 with computational complexity of O(N2log2N) for NxN image and takes less computation time for reconstruction. The WDirHT is used for content based image retrieval (CBIR) application. The sparse nature of WDirHT coefficients is exploited to derive the feature vector for CBIR application. The CBIR algorithm has been tested on different image database and the results show that the retrieval rate is better compared to the several multiresolution CBIR methods.
{"title":"Wrapping Based Directional Hartley Transform and Content Based Image Retrieval","authors":"Rajavel . Pl, R. Aravind","doi":"10.1109/IPTA.2008.4743784","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743784","url":null,"abstract":"This paper proposes a wrapping based directional Hartley transform (WDirHT) in the Hartley domain. The wrapping based curvelet transform is used to construct the WDirHT in the Hartley domain. The WDirHT is a sparse representation than curvelet transform. The redundancy factor of the transform is 2.82 with computational complexity of O(N2log2N) for NxN image and takes less computation time for reconstruction. The WDirHT is used for content based image retrieval (CBIR) application. The sparse nature of WDirHT coefficients is exploited to derive the feature vector for CBIR application. The CBIR algorithm has been tested on different image database and the results show that the retrieval rate is better compared to the several multiresolution CBIR methods.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114462089","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743756
M. Zaied, O. Jemai, C. Ben Amar
A wavelets neural network is a hybrid classifier composed of a neuronal contraption and wavelets as functions of activation. Our approach of face recognition is divided in two parts: the training phase and the recognition phase. The first consists in optimizing a wavelets neural network for every training picture face. A new technique of training of these wavelets networks which based on the frames theory is proposed as a remedy to the inconveniences of the classical training algorithms. The specificity of a BWNN to a face and the notion of SuperWavelet have been exploited to propose an approach of face recognition. Finally, we have compared our method of recognition to other ones which are used for face recognition that are applied on the AT&T (ORL) and FERET faces basis. We reached a face recognition rate that exceeds 90% for two images per person in the training step.
{"title":"Training of the Beta wavelet networks by the frames theory: Application to face recognition","authors":"M. Zaied, O. Jemai, C. Ben Amar","doi":"10.1109/IPTA.2008.4743756","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743756","url":null,"abstract":"A wavelets neural network is a hybrid classifier composed of a neuronal contraption and wavelets as functions of activation. Our approach of face recognition is divided in two parts: the training phase and the recognition phase. The first consists in optimizing a wavelets neural network for every training picture face. A new technique of training of these wavelets networks which based on the frames theory is proposed as a remedy to the inconveniences of the classical training algorithms. The specificity of a BWNN to a face and the notion of SuperWavelet have been exploited to propose an approach of face recognition. Finally, we have compared our method of recognition to other ones which are used for face recognition that are applied on the AT&T (ORL) and FERET faces basis. We reached a face recognition rate that exceeds 90% for two images per person in the training step.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124920119","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743777
A. Bevilacqua, A. Gherardi
Quantitative measurements of changes in skin topographic structures are of a great importance in the dermocosmetic field to assess subjects response to medical or cosmetic treatments. Recently, non invasive skin evaluations are possible in vivo thanks to new technologies. However, some concerns about high system cost are limiting, de facto, a widespread use of these devices for a routine based approach. In this work, a new low-cost skin surface characterization system based on the analysis of capacitive images has been evaluated. Comparative analysis between capacitive skin samples and replica based casts of skin tissue have been achieved through optical profilometry to better understand the potentiality and limitations of the proposed system.
{"title":"Characterization of a capacitive imaging system for skin surface analysis","authors":"A. Bevilacqua, A. Gherardi","doi":"10.1109/IPTA.2008.4743777","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743777","url":null,"abstract":"Quantitative measurements of changes in skin topographic structures are of a great importance in the dermocosmetic field to assess subjects response to medical or cosmetic treatments. Recently, non invasive skin evaluations are possible in vivo thanks to new technologies. However, some concerns about high system cost are limiting, de facto, a widespread use of these devices for a routine based approach. In this work, a new low-cost skin surface characterization system based on the analysis of capacitive images has been evaluated. Comparative analysis between capacitive skin samples and replica based casts of skin tissue have been achieved through optical profilometry to better understand the potentiality and limitations of the proposed system.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"26 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120893306","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743748
T. Q. Syed, Vincent Vigneron, S. Lelandais, Georgia Barlovatz-Meimon, Michel Malo, C. Charriere-Bertrand, Christophe Montagne
In this paper, we present a work which is performed by biologists and computer scientists both. The aim of this work is to evaluate the migratory potential of cancerous cells. Cancer is characterised by primary tumour. When some cells move they create new tumours, which are called metastases. It is very important to understand this migration process in order to be able to arrest it and increase the chances of a cure. Today, biologists analyse images from different cell cultures and manually count one by one the cells present therein. It is a hard and fastidious work, so here we present some algorithms to automatically perform these tasks of detection and counting. The images that we have are very low contrasted, with a gradient of illumination, and the cells are numerous and tightly aggregated. In this paper different algorithms are evocated and results compared for about 150 images comprising more than 65,000 cells.
{"title":"Detection and Counting of \"in vivo\" cells to predict cell migratory potential","authors":"T. Q. Syed, Vincent Vigneron, S. Lelandais, Georgia Barlovatz-Meimon, Michel Malo, C. Charriere-Bertrand, Christophe Montagne","doi":"10.1109/IPTA.2008.4743748","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743748","url":null,"abstract":"In this paper, we present a work which is performed by biologists and computer scientists both. The aim of this work is to evaluate the migratory potential of cancerous cells. Cancer is characterised by primary tumour. When some cells move they create new tumours, which are called metastases. It is very important to understand this migration process in order to be able to arrest it and increase the chances of a cure. Today, biologists analyse images from different cell cultures and manually count one by one the cells present therein. It is a hard and fastidious work, so here we present some algorithms to automatically perform these tasks of detection and counting. The images that we have are very low contrasted, with a gradient of illumination, and the cells are numerous and tightly aggregated. In this paper different algorithms are evocated and results compared for about 150 images comprising more than 65,000 cells.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114250030","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743794
F. Galland, P. Réfrégier
In this presentation, we propose to discuss some interesting properties of segmentation techniques based on the minimization of the stochastic complexity. We emphasize the general framework provided by the minimization of the stochastic complexity for segmentation purpose, some of its main advantages and also some of the motivating perspectives that are open by such approaches. We illustrate this presentation with different results obtained in our research group with polygonal parametric shape descriptions, level set models of contours and polygonal grids to partition images into an arbitrary number of homogeneous regions.
{"title":"Segmentation of noisy images using information theory based approaches","authors":"F. Galland, P. Réfrégier","doi":"10.1109/IPTA.2008.4743794","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743794","url":null,"abstract":"In this presentation, we propose to discuss some interesting properties of segmentation techniques based on the minimization of the stochastic complexity. We emphasize the general framework provided by the minimization of the stochastic complexity for segmentation purpose, some of its main advantages and also some of the motivating perspectives that are open by such approaches. We illustrate this presentation with different results obtained in our research group with polygonal parametric shape descriptions, level set models of contours and polygonal grids to partition images into an arbitrary number of homogeneous regions.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133535936","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743785
P. Tabrizi, R. Zoroofi
Drowsiness detection is vital in preventing traffic accidents. Eye state analysis - detecting whether the eye is open or closed - is critical step for drowsiness detection. In this paper, we propose an easy algorithm for pupil center and iris boundary localization and a new algorithm for eye state analysis, which we incorporate into a four step system for drowsiness detection: face detection, eye detection, eye state analysis, and drowsy decision. This new system requires no training data at any step or special cameras. Our eye detection algorithm uses Eye Map, thus achieving excellent pupil center and iris boundary localization results on the IMM database. Our novel eye state analysis algorithm detects eye state using the saturation (S) channel of the HSV color space. We analyze our eye state analysis algorithm using five video sequences and show superior results compared to the common technique based on distance between eyelids.
{"title":"Open/Closed Eye Analysis for Drowsiness Detection","authors":"P. Tabrizi, R. Zoroofi","doi":"10.1109/IPTA.2008.4743785","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743785","url":null,"abstract":"Drowsiness detection is vital in preventing traffic accidents. Eye state analysis - detecting whether the eye is open or closed - is critical step for drowsiness detection. In this paper, we propose an easy algorithm for pupil center and iris boundary localization and a new algorithm for eye state analysis, which we incorporate into a four step system for drowsiness detection: face detection, eye detection, eye state analysis, and drowsy decision. This new system requires no training data at any step or special cameras. Our eye detection algorithm uses Eye Map, thus achieving excellent pupil center and iris boundary localization results on the IMM database. Our novel eye state analysis algorithm detects eye state using the saturation (S) channel of the HSV color space. We analyze our eye state analysis algorithm using five video sequences and show superior results compared to the common technique based on distance between eyelids.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"141 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125835492","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743741
O. Ben Sassi, T. Delleji, A. Taleb-Ahmed, I. Feki, A. Ben Hamida
Image registration in medical imagery is one useful technique with an important role especially for pathology survey and control, medical treatment, or for post-operative control. It is based essentially on the similarity criterion measurement because it defines the objective criterion used to estimate registration quality between the homologous structures of images. This paper describes one application of the SSIM method as a similarity metric in the image registration technique. Usually the SSIM method is used in the images' quality measurement, it consists in the combination of the comparison of luminance, the comparison of contrast, and the comparison of structure between two images. This property allowed us to adapt this approach in MR image monomodal registration and demonstrate its performance.
{"title":"MR Image Monomodal Registration Using Structure Similarity Index","authors":"O. Ben Sassi, T. Delleji, A. Taleb-Ahmed, I. Feki, A. Ben Hamida","doi":"10.1109/IPTA.2008.4743741","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743741","url":null,"abstract":"Image registration in medical imagery is one useful technique with an important role especially for pathology survey and control, medical treatment, or for post-operative control. It is based essentially on the similarity criterion measurement because it defines the objective criterion used to estimate registration quality between the homologous structures of images. This paper describes one application of the SSIM method as a similarity metric in the image registration technique. Usually the SSIM method is used in the images' quality measurement, it consists in the combination of the comparison of luminance, the comparison of contrast, and the comparison of structure between two images. This property allowed us to adapt this approach in MR image monomodal registration and demonstrate its performance.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129600926","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743745
K. Rafik, B.H. Ahmed, F. Imed, Taleb-Ahmed Abdelmalik
The electrical activity inside the brain consists of currents generated by biochemical sources at cellular level. This activity can be measured by an electroencephalography. Neurologists have been interested in determining the location of the epileptogenic zones from measured potential on the scalp in order to avoid invasive techniques. The problem is recognizing by inverse problem. In this paper we propose an amelioration of the inverse problem method "sLORETA-FOCUSS" given by smoothing the current density distribution. We present a comparative study of the sLORETA-FOCUSS and the new solution named recursive sLORETA-FOCUSS. The found results demonstrate that the new method is able to give good results in term of localization error, simulated time, and precision of reconstruction in 3D.
{"title":"Recursive sLORETA-FOCUSS Algorithm for EEG Dipoles Localization","authors":"K. Rafik, B.H. Ahmed, F. Imed, Taleb-Ahmed Abdelmalik","doi":"10.1109/IPTA.2008.4743745","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743745","url":null,"abstract":"The electrical activity inside the brain consists of currents generated by biochemical sources at cellular level. This activity can be measured by an electroencephalography. Neurologists have been interested in determining the location of the epileptogenic zones from measured potential on the scalp in order to avoid invasive techniques. The problem is recognizing by inverse problem. In this paper we propose an amelioration of the inverse problem method \"sLORETA-FOCUSS\" given by smoothing the current density distribution. We present a comparative study of the sLORETA-FOCUSS and the new solution named recursive sLORETA-FOCUSS. The found results demonstrate that the new method is able to give good results in term of localization error, simulated time, and precision of reconstruction in 3D.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126212212","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743775
S. Bouchafa, B. Zavidovique
This paper deals with obstacle detection from a moving camera using the new concept of c-velocity space. By analogy to the v-disparity space in stereovision based approaches, our method focuses on the extraction of 3D-planar structures like obstacles, road or buildings from a moving scene. The camera is assumed first to have a translational motion so that the dominant apparent motion generates a scale change along images. The c-velocity space is then defined as a cumulative frame in which planar surfaces are transformed into straight lines. Equations ruling the phenomenon are given and explained. Results on synthetic images are shown to meet the theory. Eventually results on real data are commented on as for the uncertainty introduced by the location of the FOE and other types of perturbations.
{"title":"Moving plane detection under translational camera motion using the c-velocity concept","authors":"S. Bouchafa, B. Zavidovique","doi":"10.1109/IPTA.2008.4743775","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743775","url":null,"abstract":"This paper deals with obstacle detection from a moving camera using the new concept of c-velocity space. By analogy to the v-disparity space in stereovision based approaches, our method focuses on the extraction of 3D-planar structures like obstacles, road or buildings from a moving scene. The camera is assumed first to have a translational motion so that the dominant apparent motion generates a scale change along images. The c-velocity space is then defined as a cumulative frame in which planar surfaces are transformed into straight lines. Equations ruling the phenomenon are given and explained. Results on synthetic images are shown to meet the theory. Eventually results on real data are commented on as for the uncertainty introduced by the location of the FOE and other types of perturbations.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116839600","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：