Pub Date : 2008-11-01DOI: 10.1109/IPTA.2008.4743760
Pujan Ziaie, T. Müller, Alois Knoll
In this paper, a reliable, fast and robust approach for static hand gesture recognition in the domain of a human-robot interaction system is presented. The method is based on computing the likelihood of different existing gesture-types and assigning a probability to every type by using Bayesian inference rules. For this purpose, two classes of geometrical invariants has been defined and the gesture likelihoods of both of the invariant-classes are estimated by means of a modified K-nearest neighbors classifier. One of the invariant-classes consists of the well-known Hu moments and the other one encompasses five defined geometrical attributes that are transformation, rotation and scale invariant, which are obtained from the outer-contour of a hand. Given the experimental results of this approach in the domain of the Joint-Action Science and Technology (JAST) project, it appears to have a very considerable performance of more than 95% correct classification results on average for three types of gestures (pointing, grasping and holding-out) under various lighting conditions and hand poses.
{"title":"A Novel Approach to Hand-Gesture Recognition in a Human-Robot Dialog System","authors":"Pujan Ziaie, T. Müller, Alois Knoll","doi":"10.1109/IPTA.2008.4743760","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743760","url":null,"abstract":"In this paper, a reliable, fast and robust approach for static hand gesture recognition in the domain of a human-robot interaction system is presented. The method is based on computing the likelihood of different existing gesture-types and assigning a probability to every type by using Bayesian inference rules. For this purpose, two classes of geometrical invariants has been defined and the gesture likelihoods of both of the invariant-classes are estimated by means of a modified K-nearest neighbors classifier. One of the invariant-classes consists of the well-known Hu moments and the other one encompasses five defined geometrical attributes that are transformation, rotation and scale invariant, which are obtained from the outer-contour of a hand. Given the experimental results of this approach in the domain of the Joint-Action Science and Technology (JAST) project, it appears to have a very considerable performance of more than 95% correct classification results on average for three types of gestures (pointing, grasping and holding-out) under various lighting conditions and hand poses.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"14 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":"123830625","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.2008.4743739
J. Rakotondralambo, Gérard Michaille, R. Brouzet, William Puech
In this paper, the main objective is to establish an existence result of a variational model in image segmentation constrained by a given vector field. In the one dimensional case, we give a discrete version converging in a variational way to the continuous model. We finally describe the numerical analysis of this model with application in image segmentation.
{"title":"Variational approximation of a constraint signal by a Mumford-Shah type energy functional","authors":"J. Rakotondralambo, Gérard Michaille, R. Brouzet, William Puech","doi":"10.1109/IPTA.2008.4743739","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743739","url":null,"abstract":"In this paper, the main objective is to establish an existence result of a variational model in image segmentation constrained by a given vector field. In the one dimensional case, we give a discrete version converging in a variational way to the continuous model. We finally describe the numerical analysis of this model with application in image segmentation.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"26 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":"114978614","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.2008.4743793
H. Frigui
In this paper, we describe algorithms that perform fuzzy clustering and feature weighting simultaneously and in an unsupervised manner. These algorithms are conceptually and computationally simple, and learn a different set of feature weights for each identified cluster. The cluster dependent feature weights offer two advantages. First, they guide the clustering process to partition the data into more meaningful clusters. Second, they can be used in the subsequent steps of a learning system to improve its learning behavior. An extension of the algorithm to deal with an unknown number of clusters is also presented. The extension is based on competitive agglomeration, whereby the number of clusters is over-specified, and adjacent clusters are allowed to compete for data points in a manner that causes clusters which lose in the competition to gradually become depleted and vanish. We illustrate the performance of the proposed approach by using it to segment color images, categorize text document collections, and build a multi-modal thesaurus and use it to annotate image regions.
{"title":"Clustering: Algorithms and Applications","authors":"H. Frigui","doi":"10.1109/IPTA.2008.4743793","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743793","url":null,"abstract":"In this paper, we describe algorithms that perform fuzzy clustering and feature weighting simultaneously and in an unsupervised manner. These algorithms are conceptually and computationally simple, and learn a different set of feature weights for each identified cluster. The cluster dependent feature weights offer two advantages. First, they guide the clustering process to partition the data into more meaningful clusters. Second, they can be used in the subsequent steps of a learning system to improve its learning behavior. An extension of the algorithm to deal with an unknown number of clusters is also presented. The extension is based on competitive agglomeration, whereby the number of clusters is over-specified, and adjacent clusters are allowed to compete for data points in a manner that causes clusters which lose in the competition to gradually become depleted and vanish. We illustrate the performance of the proposed approach by using it to segment color images, categorize text document collections, and build a multi-modal thesaurus and use it to annotate image regions.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"26 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":"123524574","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.2008.4743770
D. Boukerroui, W. Touhami, J. Cocquerez
Recently, we proposed an original approach, in a statistical framework, for fully automatic detection of pathological kidneys in 2D CT images. In this paper, we propose some important improvements of our previous work and an attempt to classify the identified regions into pathological vs non pathological. To this end, we propose two indexing methods to construct the signatures coding the relevant information. The index is then used in a supervised classification technique to discriminate the kidney images. These approaches are tested on more than 500 clinically acquired images and promising results are obtained.
{"title":"Automatic regions of interest identification and classification in CT images: Application to kidney cysts","authors":"D. Boukerroui, W. Touhami, J. Cocquerez","doi":"10.1109/IPTA.2008.4743770","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743770","url":null,"abstract":"Recently, we proposed an original approach, in a statistical framework, for fully automatic detection of pathological kidneys in 2D CT images. In this paper, we propose some important improvements of our previous work and an attempt to classify the identified regions into pathological vs non pathological. To this end, we propose two indexing methods to construct the signatures coding the relevant information. The index is then used in a supervised classification technique to discriminate the kidney images. These approaches are tested on more than 500 clinically acquired images and promising results are obtained.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"71 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":"122697274","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.2008.4743737
N. Khiari, H. Mahersia, K. Hamrouni
This work presents a new iris recognition method based on steerable pyramid transform. This method consists of four steps: localization, normalization, features extraction and matching. After locating the iris boundaries by Hough Transform, normalization is operated by unwrapping the circular ring and isolating the noisy regions. Steerable pyramid filters are then used to capture orientation details from the iris texture. The features are extracted on each filtered sub-image to form a fixed length feature vector which will be compared to other vectors in the matching step. This technique has been tested on infrared light iris images. It has been compared, in both identification and verification modes, to known methods.
{"title":"Iris Recognition using Steerable Pyramids","authors":"N. Khiari, H. Mahersia, K. Hamrouni","doi":"10.1109/IPTA.2008.4743737","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743737","url":null,"abstract":"This work presents a new iris recognition method based on steerable pyramid transform. This method consists of four steps: localization, normalization, features extraction and matching. After locating the iris boundaries by Hough Transform, normalization is operated by unwrapping the circular ring and isolating the noisy regions. Steerable pyramid filters are then used to capture orientation details from the iris texture. The features are extracted on each filtered sub-image to form a fixed length feature vector which will be compared to other vectors in the matching step. This technique has been tested on infrared light iris images. It has been compared, in both identification and verification modes, to known methods.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"45 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":"130081858","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.2008.4743773
A. Boudabous, A. Ben Atitallah, P. Kadionik, L. Khriji, N. Masmoudi
Recently, Vector Directional Filter (VDF) have been developed either as software based applications or hardware using DSP (digital single processing) technologies. In this paper, we present a new efficient hardware/software (HW/SW) codesign implementation of the VDF using embedded system development board. By means of VHDL language, hardware accelerator including VDF algorithm is implemented with fast pipelined architecture. The remaining parts were realized in software using NIOS II softcore processor and Clinux as operating system. Experimental results confirm that the use of hardware accelerator gives good results concerning image quality and filtering speed.
{"title":"FPGA Codesign Implementation of Vector Directional Filter","authors":"A. Boudabous, A. Ben Atitallah, P. Kadionik, L. Khriji, N. Masmoudi","doi":"10.1109/IPTA.2008.4743773","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743773","url":null,"abstract":"Recently, Vector Directional Filter (VDF) have been developed either as software based applications or hardware using DSP (digital single processing) technologies. In this paper, we present a new efficient hardware/software (HW/SW) codesign implementation of the VDF using embedded system development board. By means of VHDL language, hardware accelerator including VDF algorithm is implemented with fast pipelined architecture. The remaining parts were realized in software using NIOS II softcore processor and Clinux as operating system. Experimental results confirm that the use of hardware accelerator gives good results concerning image quality and filtering speed.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"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":"128306679","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.2008.4743772
K. Kim, Jun-Hyeong Do, H. Ryu, J.-Y. Kim
In oriental medicine, the status of a tongue is the important indicator to diagnose one's health like physiological and clinicopathological changes of inner parts of the body. The method of a tongue diagnosis is not only convenient but also non-invasive and widely used in oriental medicine. However, a tongue diagnosis is affected by examination circumstances a lot like a light source, patient's posture, and doctor's condition. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, segmenting a tongue from a facial image captured and classifying tongue coating are inevitable but difficult since the colors of a tongue, lips, and skin in a mouth are similar. The proposed method includes preprocessing, over-segmentation, detecting positions with a local minimum over shading from the structure of a tongue, correcting local minima or detecting edge with color difference, and smoothing edges, where preprocessing performs downsampling to reduce computation time, histogram equalization, and edge enhancement, which produces the region of a segmented tongue, and then decomposes the color components of the region into hue, saturation and brightness, resulting in segmenting the regions of tongue coatings and classifying them. Finally, a tongue is segmented from a face image and classified into kinds of coatings and substance with a tongue from a digital tongue diagnosis system. The results illustrate the segmented region to include effective information, excluding a non-tongue region and the accurate diagnosis of coatings. It can be used to make an objective and standardized diagnosis.
{"title":"Tongue diagnosis method for extraction of effective region and classification of tongue coating","authors":"K. Kim, Jun-Hyeong Do, H. Ryu, J.-Y. Kim","doi":"10.1109/IPTA.2008.4743772","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743772","url":null,"abstract":"In oriental medicine, the status of a tongue is the important indicator to diagnose one's health like physiological and clinicopathological changes of inner parts of the body. The method of a tongue diagnosis is not only convenient but also non-invasive and widely used in oriental medicine. However, a tongue diagnosis is affected by examination circumstances a lot like a light source, patient's posture, and doctor's condition. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, segmenting a tongue from a facial image captured and classifying tongue coating are inevitable but difficult since the colors of a tongue, lips, and skin in a mouth are similar. The proposed method includes preprocessing, over-segmentation, detecting positions with a local minimum over shading from the structure of a tongue, correcting local minima or detecting edge with color difference, and smoothing edges, where preprocessing performs downsampling to reduce computation time, histogram equalization, and edge enhancement, which produces the region of a segmented tongue, and then decomposes the color components of the region into hue, saturation and brightness, resulting in segmenting the regions of tongue coatings and classifying them. Finally, a tongue is segmented from a face image and classified into kinds of coatings and substance with a tongue from a digital tongue diagnosis system. The results illustrate the segmented region to include effective information, excluding a non-tongue region and the accurate diagnosis of coatings. It can be used to make an objective and standardized diagnosis.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"15 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":"126861364","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.2008.4743789
N. Al Kitbi, A. Dawood
Blocking artifacts occur in images and video streams that are compressed to low bit rates using block discrete cosine transform (DCT)-based compression standards. It appears as artificial block boundaries between adjacent blocks of the compressed images. In this paper, new methods to reduce blocking effect are proposed. They were tested on different images and different compression ratios (quality factors), and they were evaluated using objective and subjective measures. In general, results of testing were obtained as expected. One technique, namely: The "two sides average+Sobel edge detector" achieved higher values for approximately all tested images in both, objective and subjective quality measures.
{"title":"Deblocking Algorithms with Edge Filters for DCT Compressed Images","authors":"N. Al Kitbi, A. Dawood","doi":"10.1109/IPTA.2008.4743789","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743789","url":null,"abstract":"Blocking artifacts occur in images and video streams that are compressed to low bit rates using block discrete cosine transform (DCT)-based compression standards. It appears as artificial block boundaries between adjacent blocks of the compressed images. In this paper, new methods to reduce blocking effect are proposed. They were tested on different images and different compression ratios (quality factors), and they were evaluated using objective and subjective measures. In general, results of testing were obtained as expected. One technique, namely: The \"two sides average+Sobel edge detector\" achieved higher values for approximately all tested images in both, objective and subjective quality measures.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"12 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":"133073414","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.2008.4743753
Sarra Sakji-Nsibi, A. Benazza-Benyahia
In this work, we address the problem of multichannel image retrieval in the compressed wavelet-based domain. A wavelet transform is applied to each component. Then, two approaches are applied to extract features from the multiresolution representations. In the first one, the wavelet coefficients of each component are considered as mutually independent and hence, features are separately computed. In the second, the distribution of the multivariate wavelet coefficients is modeled by a multivariate model driven by the copulas theory. The parameters of this multivariate distribution are chosen as relevant signatures of the image. The contribution of this paper is to investigate the influence of the copula density on the retrieval performances. To this respect, we have tested the Gaussian copula density and two Archimedean copula densities (the Clayton and the Gumbel copulas). Experimental results indicate that the Archimedea n copulas outperfom the Gaussian one in terms of precision and recall of retrieval.
{"title":"Multivariate indexing of multichannel images based on the copula theory","authors":"Sarra Sakji-Nsibi, A. Benazza-Benyahia","doi":"10.1109/IPTA.2008.4743753","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743753","url":null,"abstract":"In this work, we address the problem of multichannel image retrieval in the compressed wavelet-based domain. A wavelet transform is applied to each component. Then, two approaches are applied to extract features from the multiresolution representations. In the first one, the wavelet coefficients of each component are considered as mutually independent and hence, features are separately computed. In the second, the distribution of the multivariate wavelet coefficients is modeled by a multivariate model driven by the copulas theory. The parameters of this multivariate distribution are chosen as relevant signatures of the image. The contribution of this paper is to investigate the influence of the copula density on the retrieval performances. To this respect, we have tested the Gaussian copula density and two Archimedean copula densities (the Clayton and the Gumbel copulas). Experimental results indicate that the Archimedea n copulas outperfom the Gaussian one in terms of precision and recall of retrieval.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"11 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":"124199855","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.2008.4743779
A. Bevilacqua, A. Gherardi, L. Carozza
Automatic pattern recognition is a hard task to carry out when shapes or textures have to be detected. This can be even more difficult when accurate photometric measures are required. Nevertheless, most of times the feasibility to have a measurable ground truth at our disposal (it maybe is achievable using other sensors) gives us a reference point that makes the researcher task easier. In this paper, we present a method to segment automatically a light-shadow line in a very high-contrasted scene, in the context of an industrial automotive application, where the ground truth is the line as being perceived by sight from an experienced operator. After segmenting the line, some measures have been achieved related to accuracy and precision of a reference parameter of the line (the "elbow"), using an industrial prototype integral with the headlamp to be tested. The experiments prove how the method we developed is able to detect perturbation of the headlamp beam in pitch and yaw lower than 1/10deg, this representing an excellent outcome.
{"title":"Accurate eye-like segmentation in a heavily untextured contrasted scene","authors":"A. Bevilacqua, A. Gherardi, L. Carozza","doi":"10.1109/IPTA.2008.4743779","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743779","url":null,"abstract":"Automatic pattern recognition is a hard task to carry out when shapes or textures have to be detected. This can be even more difficult when accurate photometric measures are required. Nevertheless, most of times the feasibility to have a measurable ground truth at our disposal (it maybe is achievable using other sensors) gives us a reference point that makes the researcher task easier. In this paper, we present a method to segment automatically a light-shadow line in a very high-contrasted scene, in the context of an industrial automotive application, where the ground truth is the line as being perceived by sight from an experienced operator. After segmenting the line, some measures have been achieved related to accuracy and precision of a reference parameter of the line (the \"elbow\"), using an industrial prototype integral with the headlamp to be tested. The experiments prove how the method we developed is able to detect perturbation of the headlamp beam in pitch and yaw lower than 1/10deg, this representing an excellent outcome.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"2 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":"122711371","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：