N. Sauwen, D. Sima, M. Acou, E. Achten, F. Maes, U. Himmelreich, S. Huffel
Segmentation plays an important role in the clinical management of brain tumors. Clinical practice would benefit from accurate and automated volumetric delineation of the tumor and its subcompartments. We present a semi-automated framework for brain tumor segmentation based on regularized nonnegative matrix factorization (NMF). L1-regularization is incorporated into the NMF objective function to promote spatial consistency and sparseness of the tissue abundance maps. The pathological sources are initialized through user-defined voxel selection. Knowledge about the spatial location of the selected voxels is combined with tissue adjacency constraints in a post-processing step to enhance segmentation quality. The method is applied to the BRATS 2013 Leaderboard dataset, consisting of publicly available multi-sequence MRI data of brain tumor patients. Our method performs well in comparison with state-of-the-art, in particular for the enhancing tumor region, for which we reach the highest Dice score among all participants.
{"title":"A Semi-Automated Segmentation Framework for MRI Based Brain Tumor Segmentation Using Regularized Nonnegative Matrix Factorization","authors":"N. Sauwen, D. Sima, M. Acou, E. Achten, F. Maes, U. Himmelreich, S. Huffel","doi":"10.1109/SITIS.2016.23","DOIUrl":"https://doi.org/10.1109/SITIS.2016.23","url":null,"abstract":"Segmentation plays an important role in the clinical management of brain tumors. Clinical practice would benefit from accurate and automated volumetric delineation of the tumor and its subcompartments. We present a semi-automated framework for brain tumor segmentation based on regularized nonnegative matrix factorization (NMF). L1-regularization is incorporated into the NMF objective function to promote spatial consistency and sparseness of the tissue abundance maps. The pathological sources are initialized through user-defined voxel selection. Knowledge about the spatial location of the selected voxels is combined with tissue adjacency constraints in a post-processing step to enhance segmentation quality. The method is applied to the BRATS 2013 Leaderboard dataset, consisting of publicly available multi-sequence MRI data of brain tumor patients. Our method performs well in comparison with state-of-the-art, in particular for the enhancing tumor region, for which we reach the highest Dice score among all participants.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123284802","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}
To construct a cooking motion model, we needed to analyze features of cooking motions. Our aim was to recognize cooking motions by tracking the motions of the joints of a cook's arms with a three-dimensional depth sensor. To recognize the motions, we needed to analyze their features of interest. We selected "cutting" and "mixing" as cooking motions of interest. Cutting is a motion where the cook's forearm moves up and down and the upper arm moves forward and back. Mixing is a motion where the cook's forearm moves as if drawing a wide circle in front of the body. Therefore, we focused on the motions of the forearm and upper arm as features of the cooking motion. With regard to the x-axis of the forearm, cutting had a small value for the logarithmic power, but mixing had a large value. This indicates a change in the same manner as the assumed motion. These results showed that the fifth logarithmic power of the x-axis can be used as a feature of cooking motions.
{"title":"Motion Analysis for Cooking Motion Recognition","authors":"Yuma Hijioka, Makoto Murakami, T. Kimoto","doi":"10.1109/SITIS.2016.93","DOIUrl":"https://doi.org/10.1109/SITIS.2016.93","url":null,"abstract":"To construct a cooking motion model, we needed to analyze features of cooking motions. Our aim was to recognize cooking motions by tracking the motions of the joints of a cook's arms with a three-dimensional depth sensor. To recognize the motions, we needed to analyze their features of interest. We selected \"cutting\" and \"mixing\" as cooking motions of interest. Cutting is a motion where the cook's forearm moves up and down and the upper arm moves forward and back. Mixing is a motion where the cook's forearm moves as if drawing a wide circle in front of the body. Therefore, we focused on the motions of the forearm and upper arm as features of the cooking motion. With regard to the x-axis of the forearm, cutting had a small value for the logarithmic power, but mixing had a large value. This indicates a change in the same manner as the assumed motion. These results showed that the fifth logarithmic power of the x-axis can be used as a feature of cooking motions.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132559089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper examines the application of a deep learning approach to automatic coin recognition, via a mobile device and client-server architecture. We show that a convolutional neural network is effective for coin identification. During the training phase, we determine the optimum size of the training dataset necessary to achieve high classification accuracy with low variance. In addition, we propose a client-server architecture that enables a user to identify coins by photographing it with a smartphone. The image provided by the user is matched with the neural network on a remote server. A high correlation suggests that the image is a match. The application is a first step towards the automatic identification of coins and may help coin experts in their study of coins and reduce the associated expense of numismatic applications.
{"title":"Implementation of a Coin Recognition System for Mobile Devices with Deep Learning","authors":"N. Capece, U. Erra, A. Ciliberto","doi":"10.1109/SITIS.2016.37","DOIUrl":"https://doi.org/10.1109/SITIS.2016.37","url":null,"abstract":"This paper examines the application of a deep learning approach to automatic coin recognition, via a mobile device and client-server architecture. We show that a convolutional neural network is effective for coin identification. During the training phase, we determine the optimum size of the training dataset necessary to achieve high classification accuracy with low variance. In addition, we propose a client-server architecture that enables a user to identify coins by photographing it with a smartphone. The image provided by the user is matched with the neural network on a remote server. A high correlation suggests that the image is a match. The application is a first step towards the automatic identification of coins and may help coin experts in their study of coins and reduce the associated expense of numismatic applications.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130925479","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}
Yukiko Yamamoto, S. Tsuruta, Syoji Kobashi, Yoshitaka Sakurai, R. Knauf
Aiming at application to automated recognition of knee bone magnetic resonance (MR) images, an evolutional classification method called CBGA-LDIC is proposed. CBGA-LDIC finds an appropriate cell set towards efficient image segmentation. This method uses location-dependent image classification (LDIC), which is integrated by genetic algorithm (GA) combined with case based reasoning (CB). LDIC introduces a new but local heuristics for image segmentation, and defines multiple classifiers dependent on location. Each classifier is trained by Gaussian mixture model. CBGA-LDIC decomposes the whole image into some cells, makes a set of cells, and then trains classifiers. Since the knee bones and/or their formations are similar in their location, good combinations of cells seem useful for other clients and are stored in case bases. Thus this method is expected to produce the better results when good combinations of cells are selected from cases as initial individuals of GA, especially through its repetition on restarting GA. This is verified by some experimentations shown in this paper.
{"title":"An Efficient Classification Method for Knee MR Image Segmentation","authors":"Yukiko Yamamoto, S. Tsuruta, Syoji Kobashi, Yoshitaka Sakurai, R. Knauf","doi":"10.1109/SITIS.2016.15","DOIUrl":"https://doi.org/10.1109/SITIS.2016.15","url":null,"abstract":"Aiming at application to automated recognition of knee bone magnetic resonance (MR) images, an evolutional classification method called CBGA-LDIC is proposed. CBGA-LDIC finds an appropriate cell set towards efficient image segmentation. This method uses location-dependent image classification (LDIC), which is integrated by genetic algorithm (GA) combined with case based reasoning (CB). LDIC introduces a new but local heuristics for image segmentation, and defines multiple classifiers dependent on location. Each classifier is trained by Gaussian mixture model. CBGA-LDIC decomposes the whole image into some cells, makes a set of cells, and then trains classifiers. Since the knee bones and/or their formations are similar in their location, good combinations of cells seem useful for other clients and are stored in case bases. Thus this method is expected to produce the better results when good combinations of cells are selected from cases as initial individuals of GA, especially through its repetition on restarting GA. This is verified by some experimentations shown in this paper.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126711601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose an efficient algorithm for facial image recognition using multiple histogram features from spatial and frequency domains, respectively. In spatial domain, we utilize Local Binary Pattern (LBP) histogram due to its excellent robustness and strong discriminative power. In frequency domain, we utilize two types of histogram named binary vector quantization (BVQ) histogram and energy histogram extracted from low-frequency DCT domain. The former histogram feature is essential for utilizing the phase information of DCT coefficients by applying binary vector quantization (BVQ) on DCT coefficient blocks. The latter is energy histogram which can be considered to add magnitude information of DCT coefficients. These two histograms then contain both phase and magnitude information of a DCT transformed facial image. These 3 types of histograms described above, which contain both spatial and frequency domain information of a facial image, are utilized as a very effective personal feature. Publicly available AT&T database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. Experimental results demonstrated that face recognition using multiple histogram features can achieve higher recognition rate.
{"title":"Face Recognition Using Multiple Histogram Features in Spatial and Frequency Domains","authors":"Qiu Chen, K. Kotani, Feifei Lee","doi":"10.1109/SITIS.2016.40","DOIUrl":"https://doi.org/10.1109/SITIS.2016.40","url":null,"abstract":"In this paper, we propose an efficient algorithm for facial image recognition using multiple histogram features from spatial and frequency domains, respectively. In spatial domain, we utilize Local Binary Pattern (LBP) histogram due to its excellent robustness and strong discriminative power. In frequency domain, we utilize two types of histogram named binary vector quantization (BVQ) histogram and energy histogram extracted from low-frequency DCT domain. The former histogram feature is essential for utilizing the phase information of DCT coefficients by applying binary vector quantization (BVQ) on DCT coefficient blocks. The latter is energy histogram which can be considered to add magnitude information of DCT coefficients. These two histograms then contain both phase and magnitude information of a DCT transformed facial image. These 3 types of histograms described above, which contain both spatial and frequency domain information of a facial image, are utilized as a very effective personal feature. Publicly available AT&T database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. Experimental results demonstrated that face recognition using multiple histogram features can achieve higher recognition rate.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121705237","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}
Data have a compositional nature when the information content to be extracted and analyzed is conveyed into the ratio of parts, instead of the absolute amount. When the data are compositional, they need to be scaled so that subsequent analysis are scale-invariant, and geometrically this means to force them into the open Simplex. A common practice to analyze compositional data is to map bijectively compositions into the ordinary euclidean space through a suitable transformation, so that standard multivariate analysis techniques can be used. In this paper, the stability analysis of the Centered Log-Ratio (clr) transformation is performed. The purpose is to isolate areas of the Simplex where the clr transformation is ill conditioned and to highlight values for which the clr transformation cannot be accurately computed. Results show that the mapping accuracy is strongly affected by the closeness of the values to their geometric mean, and that in the worst case the clr can amplify the errors by an unbounded factor.
{"title":"Numerical Stability Analysis of the Centered Log-Ratio Transformation","authors":"A. Galletti, A. Maratea","doi":"10.1109/SITIS.2016.119","DOIUrl":"https://doi.org/10.1109/SITIS.2016.119","url":null,"abstract":"Data have a compositional nature when the information content to be extracted and analyzed is conveyed into the ratio of parts, instead of the absolute amount. When the data are compositional, they need to be scaled so that subsequent analysis are scale-invariant, and geometrically this means to force them into the open Simplex. A common practice to analyze compositional data is to map bijectively compositions into the ordinary euclidean space through a suitable transformation, so that standard multivariate analysis techniques can be used. In this paper, the stability analysis of the Centered Log-Ratio (clr) transformation is performed. The purpose is to isolate areas of the Simplex where the clr transformation is ill conditioned and to highlight values for which the clr transformation cannot be accurately computed. Results show that the mapping accuracy is strongly affected by the closeness of the values to their geometric mean, and that in the worst case the clr can amplify the errors by an unbounded factor.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116781166","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}
Narumol Chumuang, Sattarpoom Thaiparnit, M. Ketcham
Plant leaves are very important for their respiration and photosynthesis. The two processes are significant factors for their growth. Measuring leave dimension is very important in studying and analyzing the photosynthesis of plants. Leaf dimension assessment with image evaluation is the most widely technique used for presenting. This paper proposed the algorithm of image segmentation to classify image elements and calculate leaf surface with a threshold segmentation technique by using the constant threshold in gray color model and calculating the degree of green color in the HSV models. Segmentation technique is used to separate good surface out of defective surface of leaf image. Moreover, this paper also proposed leaf area estimation with linear regression analysis with the pixel value on the leaf surface. Further to sixty experiments, they showed the accuracy to separate elements of good surface and defective surface are 98.72% and 96.47% respectively.
{"title":"Algorithm Design in Leaf Surface Separation by Degree in HSV Color Model and Estimation of Leaf Area by Linear Regression","authors":"Narumol Chumuang, Sattarpoom Thaiparnit, M. Ketcham","doi":"10.1109/SITIS.2016.104","DOIUrl":"https://doi.org/10.1109/SITIS.2016.104","url":null,"abstract":"Plant leaves are very important for their respiration and photosynthesis. The two processes are significant factors for their growth. Measuring leave dimension is very important in studying and analyzing the photosynthesis of plants. Leaf dimension assessment with image evaluation is the most widely technique used for presenting. This paper proposed the algorithm of image segmentation to classify image elements and calculate leaf surface with a threshold segmentation technique by using the constant threshold in gray color model and calculating the degree of green color in the HSV models. Segmentation technique is used to separate good surface out of defective surface of leaf image. Moreover, this paper also proposed leaf area estimation with linear regression analysis with the pixel value on the leaf surface. Further to sixty experiments, they showed the accuracy to separate elements of good surface and defective surface are 98.72% and 96.47% respectively.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115600540","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}
Filippo Vella, A. Augello, U. Maniscalco, Vincenzo Bentivenga, S. Gaglio
The raising number of elderly people urges the research of systems able to monitor and support people inside their domestic environment. An automatic system capturing data about the position of a person in the house, through accelerometers and RGBd cameras can monitor the person activities and produce outputs associating the movements to a given tasks or predicting the set of activities that will be executes. We considered, for the task the classification of the activities a Deep Convolutional Neural Network. We compared two different deep network and analyzed their outputs.
{"title":"Classification of Indoor Actions through Deep Neural Networks","authors":"Filippo Vella, A. Augello, U. Maniscalco, Vincenzo Bentivenga, S. Gaglio","doi":"10.1109/SITIS.2016.22","DOIUrl":"https://doi.org/10.1109/SITIS.2016.22","url":null,"abstract":"The raising number of elderly people urges the research of systems able to monitor and support people inside their domestic environment. An automatic system capturing data about the position of a person in the house, through accelerometers and RGBd cameras can monitor the person activities and produce outputs associating the movements to a given tasks or predicting the set of activities that will be executes. We considered, for the task the classification of the activities a Deep Convolutional Neural Network. We compared two different deep network and analyzed their outputs.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122705265","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}
Automated image retargeting techniques are becoming important with the proliferation of different display units, such as cell phones, notebooks, televisions etc. Scale-and-stretch techniques have been successfully used for resizing images into different aspect ratios, while also preserving the most prominent visual features. The main idea of scale-and-stretch techniques is to utilize a single grid with predefined resolution, and map onto it the single significance map. The problem of image resizing is subsequently formulated as an optimization problem, which determines the optimal deformation for every local region of the image based on their underling significance. The use, however, of a single grid with specific distribution is not robust with respect to the size of the significant regions that exist in the image. In this respect, this paper extents the scale-and-stretch techniques with the use of a hierarchical grid that incorporates the significance maps of different grid resolutions in a single grid. The proposed hierarchical approach surpasses current methods and manages to efficiently identify significant regions and achieve better results.
{"title":"A Hierarchical Scale-and-Stretch Approach for Image Retargeting","authors":"Stavros Papadopoulos, A. Drosou, D. Tzovaras","doi":"10.1109/SITIS.2016.11","DOIUrl":"https://doi.org/10.1109/SITIS.2016.11","url":null,"abstract":"Automated image retargeting techniques are becoming important with the proliferation of different display units, such as cell phones, notebooks, televisions etc. Scale-and-stretch techniques have been successfully used for resizing images into different aspect ratios, while also preserving the most prominent visual features. The main idea of scale-and-stretch techniques is to utilize a single grid with predefined resolution, and map onto it the single significance map. The problem of image resizing is subsequently formulated as an optimization problem, which determines the optimal deformation for every local region of the image based on their underling significance. The use, however, of a single grid with specific distribution is not robust with respect to the size of the significant regions that exist in the image. In this respect, this paper extents the scale-and-stretch techniques with the use of a hierarchical grid that incorporates the significance maps of different grid resolutions in a single grid. The proposed hierarchical approach surpasses current methods and manages to efficiently identify significant regions and achieve better results.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122770543","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}
Aly Ngoné Ngom, Papa Fary Diallo, Fatou Kamara-Sangaré, Moussa Lo
This paper presents a method to validate the insertion of a new concept in an ontology. This method is based on our previous works which add new concepts in a basic ontology using a general ontology (genaral ontology contains all the concepts of the basic ontology). To verify the semantic relevance of an ontology, we have proposed a method with three steps. First, we have found the neighborhood of the concept C in the basic ontology Ob and we store their semantic similarity values in a stack. The neighbourhood represents the concepts which are more similar to C in Ob. Secondly, we have assessed in the general ontology Og the semantic similarity between C and its neighbourhood found in the first step. Finally, we have evaluated the correlation between values found in the previous steps. We have considered the basic ontology as ontology with which we work and the general ontology as ontology used to align concepts with the basic ontology. The result obtained thanks to the method is a validated ontology after an update by adding a new concept. To illustrate our method, we have used the whole WordNet as the reference ontology and a branch of WordNet as basic ontology.
{"title":"A Method to Validate the Insertion of a New Concept in an Ontology","authors":"Aly Ngoné Ngom, Papa Fary Diallo, Fatou Kamara-Sangaré, Moussa Lo","doi":"10.1109/SITIS.2016.52","DOIUrl":"https://doi.org/10.1109/SITIS.2016.52","url":null,"abstract":"This paper presents a method to validate the insertion of a new concept in an ontology. This method is based on our previous works which add new concepts in a basic ontology using a general ontology (genaral ontology contains all the concepts of the basic ontology). To verify the semantic relevance of an ontology, we have proposed a method with three steps. First, we have found the neighborhood of the concept C in the basic ontology Ob and we store their semantic similarity values in a stack. The neighbourhood represents the concepts which are more similar to C in Ob. Secondly, we have assessed in the general ontology Og the semantic similarity between C and its neighbourhood found in the first step. Finally, we have evaluated the correlation between values found in the previous steps. We have considered the basic ontology as ontology with which we work and the general ontology as ontology used to align concepts with the basic ontology. The result obtained thanks to the method is a validated ontology after an update by adding a new concept. To illustrate our method, we have used the whole WordNet as the reference ontology and a branch of WordNet as basic ontology.","PeriodicalId":403704,"journal":{"name":"2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128352498","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：