Chuanjun Li, G. Pradhan, Si-Qing Zheng, B. Prabhakaran
Haptic data such as 3D motion capture data and sign language animation data are new forms of multimedia data. The motion data is multi-attribute, and indexing of multi-attribute data is important for quickly pruning the majority of irrelevant motions in order to have real-time animation applications. Indexing of multi-attribute data has been attempted for data of a few attributes by using R-tree or its variants after dimensionality reduction. In this paper, we exploit the singular value decomposition (SVD) properties of multi-attribute motion data matrices to obtain one representative vector for each of the motion data matrices of dozens or hundreds of attributes. Based on this representative vector, we propose a simple and efficient interval-tree based index structure for indexing motion data with large amount of attributes. At each tree level, only one component of the query vector needs to be checked during searching, comparing to all the components of the query vector that should get involved if an R-tree or its variants are used for indexing. Searching time is independent of the number of pattern motions indexed by the tree, making the index structure well scalable to large data repositories. Experiments show that up to 91∼93% irrelevant motions can be pruned for a query with no false dismissals, and the query searching time is less than 30 μ s with the existence of motion variations.
{"title":"Indexing of variable length multi-attribute motion data","authors":"Chuanjun Li, G. Pradhan, Si-Qing Zheng, B. Prabhakaran","doi":"10.1145/1032604.1032617","DOIUrl":"https://doi.org/10.1145/1032604.1032617","url":null,"abstract":"Haptic data such as 3D motion capture data and sign language animation data are new forms of multimedia data. The motion data is multi-attribute, and indexing of multi-attribute data is important for quickly pruning the majority of irrelevant motions in order to have real-time animation applications. Indexing of multi-attribute data has been attempted for data of a few attributes by using R-tree or its variants after dimensionality reduction. In this paper, we exploit the singular value decomposition (SVD) properties of multi-attribute motion data matrices to obtain one representative vector for each of the motion data matrices of dozens or hundreds of attributes. Based on this representative vector, we propose a simple and efficient interval-tree based index structure for indexing motion data with large amount of attributes. At each tree level, only one component of the query vector needs to be checked during searching, comparing to all the components of the query vector that should get involved if an R-tree or its variants are used for indexing. Searching time is independent of the number of pattern motions indexed by the tree, making the index structure well scalable to large data repositories. Experiments show that up to 91∼93% irrelevant motions can be pruned for a query with no false dismissals, and the query searching time is less than 30 μ <i>s</i> with the existence of motion variations.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116416536","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}
Recently, various schemes for broadcasting continuous media data such as music or movies have been studied. These schemes reduce the waiting time for playing the data under the continuity condition, i.e., playing continuous media data without any intermittence until the end of the data. These schemes usually employ multiple channels to broadcast the data. However, most clients are not able to receive data from multiple channels concurrently. In this paper, we propose methods for reducing client waiting time for multiple data via a single channel. In our proposed methods, we divide each data into several segments and produce a schedule that includes the first segment of each data more frequent than the rest. By changing the number of segments according to the playback ratio, client waiting time is effectively reduced.
{"title":"Scheduling methods for broadcasting multiple continuous media data","authors":"T. Yoshihisa, M. Tsukamoto, S. Nishio","doi":"10.1145/951676.951685","DOIUrl":"https://doi.org/10.1145/951676.951685","url":null,"abstract":"Recently, various schemes for broadcasting continuous media data such as music or movies have been studied. These schemes reduce the waiting time for playing the data under the continuity condition, i.e., playing continuous media data without any intermittence until the end of the data. These schemes usually employ multiple channels to broadcast the data. However, most clients are not able to receive data from multiple channels concurrently. In this paper, we propose methods for reducing client waiting time for multiple data via a single channel. In our proposed methods, we divide each data into several segments and produce a schedule that includes the first segment of each data more frequent than the rest. By changing the number of segments according to the playback ratio, client waiting time is effectively reduced.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130477607","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 proposes a novel content-based image retrieval scheme for image copy identification. Its goal is to detect matches between a set of doubtful images and the ones stored in the database of the legal holders of the photographies. If an image was stolen and used to create a pirated copy, it tries to identify from which original image that copy was created. The image recognition scheme is based on local differential descriptors. Therefore, the matching process takes into account a large set of variations that might have been applied to stolen images in order to create pirated copies. The high cost and the complexity of this image recognition scheme requires a very efficient retrieval process since many individual queries must be executed before being able to construct the final result. This paper therefore proposes to use a novel search method that trades the precision of each individual search for reduced query execution time. This imprecision has only little impact on the overall recognition performance since the final result is a consolidation of many partial results. However, it dramatically accelerates queries. This result has then been corroborated by a theoretically study. Experiments show the efficiency and the robustness of the proposed scheme.
{"title":"Robust content-based image searches for copyright protection","authors":"Sid-Ahmed Berrani, L. Amsaleg, P. Gros","doi":"10.1145/951676.951690","DOIUrl":"https://doi.org/10.1145/951676.951690","url":null,"abstract":"This paper proposes a novel content-based image retrieval scheme for image copy identification. Its goal is to detect matches between a set of doubtful images and the ones stored in the database of the legal holders of the photographies. If an image was stolen and used to create a pirated copy, it tries to identify from which original image that copy was created. The image recognition scheme is based on local differential descriptors. Therefore, the matching process takes into account a large set of variations that might have been applied to stolen images in order to create pirated copies. The high cost and the complexity of this image recognition scheme requires a very efficient retrieval process since many individual queries must be executed before being able to construct the final result. This paper therefore proposes to use a novel search method that trades the precision of each individual search for reduced query execution time. This imprecision has only little impact on the overall recognition performance since the final result is a consolidation of many partial results. However, it dramatically accelerates queries. This result has then been corroborated by a theoretically study. Experiments show the efficiency and the robustness of the proposed scheme.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131807760","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}
Detection and recognition of semantic events has been a major research challenge for multimedia indexing. An emerging direction in this field has been unsupervised discovery (mining) of patterns in spatial-temporal multimedia data. Patterns are recurrent, predictable occurrences of one or more entities that satisfy associative, statistical, or relational conditions. Patterns at the feature level may signify the occurrence of events (e.g., passing pedestrians). At the event level, patterns may represent multi-event transitions, e.g., play-break alternations in sports. Patterns in an annotated image collection may indicate collocations of related semantic concepts and perceptual clusters.Mining of patterns of different types at different levels offers rich benefits, including automatic discovery of salient events in a new domain, automatic alert generation from massive real-time data (such as surveillance data in a new environment), and discovery of novel event relationships.Many challenging issues emerge. What are the adequate representations and statistical models for patterns that may exist at different levels and different time scales? How to handle patterns that may have relatively sparse occurring frequencies? How do we evaluate the accuracy and quality of mining results given its unsupervised nature?In this talk, we will present results of our preliminary attempts in mining patterns in structured video sequences (such as sports and surveillance video) and large annotated image collections. Specifically, we will discuss the potential of statistical models like Hierarchical HMM for video mining, and the integrative exploration of electronic knowledge (such as WordNet) and statistical clustering for image knowledge mining.
{"title":"Mining spatio-temporal patterns and knowledge structures in multimedia collection","authors":"Shih-Fu Chang","doi":"10.1145/951676.951677","DOIUrl":"https://doi.org/10.1145/951676.951677","url":null,"abstract":"Detection and recognition of semantic events has been a major research challenge for multimedia indexing. An emerging direction in this field has been <u>unsupervised discovery (mining) of patterns</u> in spatial-temporal multimedia data. Patterns are recurrent, predictable occurrences of one or more entities that satisfy associative, statistical, or relational conditions. Patterns at the feature level may signify the occurrence of events (e.g., passing pedestrians). At the event level, patterns may represent multi-event transitions, e.g., play-break alternations in sports. Patterns in an annotated image collection may indicate collocations of related semantic concepts and perceptual clusters.Mining of patterns of different types at different levels offers rich benefits, including automatic discovery of salient events in a new domain, automatic alert generation from massive real-time data (such as surveillance data in a new environment), and discovery of novel event relationships.Many challenging issues emerge. What are the adequate representations and statistical models for patterns that may exist at different levels and different time scales? How to handle patterns that may have relatively sparse occurring frequencies? How do we evaluate the accuracy and quality of mining results given its unsupervised nature?In this talk, we will present results of our preliminary attempts in mining patterns in structured video sequences (such as sports and surveillance video) and large annotated image collections. Specifically, we will discuss the potential of statistical models like Hierarchical HMM for video mining, and the integrative exploration of electronic knowledge (such as WordNet) and statistical clustering for image knowledge mining.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128893297","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}
Weihong Huang, T. Tao, Mohand-Said Hacid, A. Mille
With current multimedia information management techniques, the knowledge communications among users in multimedia e-Learning environments are still limited at a relative low single type media servicing level. New developments in multimedia knowledge discovery, representation and integration are needed to improve the intelligence of the knowledge management and communications at the semantic level. This paper proposes a novel contextual knowledge management framework to improve the current isolated learning information retrieval and communication status, by enabling flexible knowledge representation beyond heterogeneous multimedia learning resources and facilitating multilevel knowledge communications between instructors and learners. Based on knowledge communication model analysis in university e-Learning environments, a contextual knowledge representation model is presented. Corresponding knowledge retrieval techniques are discussed afterwards. To demonstrate the proposed concepts and techniques, a case study in a virtual scenario-based learning environment shows how the presented framework works with existing e-Learning content description standards and multimedia information retrieval techniques, and consequently enables a semantic-based interactive learning environment.
{"title":"Facilitate knowledge communications","authors":"Weihong Huang, T. Tao, Mohand-Said Hacid, A. Mille","doi":"10.1145/951676.951684","DOIUrl":"https://doi.org/10.1145/951676.951684","url":null,"abstract":"With current multimedia information management techniques, the knowledge communications among users in multimedia e-Learning environments are still limited at a relative low single type media servicing level. New developments in multimedia knowledge discovery, representation and integration are needed to improve the intelligence of the knowledge management and communications at the semantic level. This paper proposes a novel contextual knowledge management framework to improve the current isolated learning information retrieval and communication status, by enabling flexible knowledge representation beyond heterogeneous multimedia learning resources and facilitating multilevel knowledge communications between instructors and learners. Based on knowledge communication model analysis in university e-Learning environments, a contextual knowledge representation model is presented. Corresponding knowledge retrieval techniques are discussed afterwards. To demonstrate the proposed concepts and techniques, a case study in a virtual scenario-based learning environment shows how the presented framework works with existing e-Learning content description standards and multimedia information retrieval techniques, and consequently enables a semantic-based interactive learning environment.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123043132","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}
The similarity indexing and searching is well known to be a difficult one for high-dimensional applications such as multimedia databases. Especially, it becomes more difficult when multiple features have to be indexed together. Moreover, few indexing methods are currently available to effectively support disjunctive queries for relevance feedback.In this paper, we propose a novel indexing method that is designed to efficiently handle complex similarity queries as well as relevance feedback in high-dimensional image and video databases. In order to provide the indexing method with the flexibility in control multiple features and multiple query objects, our method treats every dimension independently. The efficiency of our method is realized by a specialized bitmap indexing that represents all objects in a database as a set of bitmaps. The percentage of data accessed in our indexing method is inversely proportional to the overall dimensionality, and thus the performance deterioration with the increasing dimensionality does not occur.Our main contributions are three-fold: (1) We provide a novel way to index high-dimensional data; (2) Our method efficiently handles complex similarity queries; and (3) Disjunctive queries driven by relevance feedback are efficiently treated. Our empirical results demonstrate that our indexing method achieves speedups of 10 to 15 over the linear scan.
{"title":"Bitmap indexing method for complex similarity queries with relevance feedback","authors":"Guang-Ho Cha","doi":"10.1145/951676.951687","DOIUrl":"https://doi.org/10.1145/951676.951687","url":null,"abstract":"The similarity indexing and searching is well known to be a difficult one for high-dimensional applications such as multimedia databases. Especially, it becomes more difficult when multiple features have to be indexed together. Moreover, few indexing methods are currently available to effectively support disjunctive queries for relevance feedback.In this paper, we propose a novel indexing method that is designed to efficiently handle complex similarity queries as well as relevance feedback in high-dimensional image and video databases. In order to provide the indexing method with the flexibility in control multiple features and multiple query objects, our method treats every dimension independently. The efficiency of our method is realized by a specialized bitmap indexing that represents all objects in a database as a set of bitmaps. The percentage of data accessed in our indexing method is inversely proportional to the overall dimensionality, and thus the performance deterioration with the increasing dimensionality does not occur.Our main contributions are three-fold: (1) We provide a novel way to index high-dimensional data; (2) Our method efficiently handles complex similarity queries; and (3) Disjunctive queries driven by relevance feedback are efficiently treated. Our empirical results demonstrate that our indexing method achieves speedups of 10 to 15 over the linear scan.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"361 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132745628","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}
Walid G. Aref, M. Hammad, A. Catlin, I. Ilyas, T. Ghanem, A. Elmagarmid, M. Marzouk
The increased use of video data sets for multimedia-based applications has created a demand for strong video database support, including efficient methods for handling the content-based query and retrieval of video data. Video query processing presents significant research challenges, mainly associated with the size, complexity and unstructured nature of video data. A video query processor must support video operations for search by content and streaming, new query types, and the incorporation of video methods and operators in generating, optimizing and executing query plans. In this paper, we address these query processing issues in two contexts, first as applied to the video data type and then as applied to the stream data type. We first present the query processing functionality of the VDBMS video database management system as a framework designed to support the full range of functionality for video as an abstract data type. We describe two query operators for the video data type which implement the rank-join and stop-after algorithms. As videos may be considered streams of consecutive image frames, video query processing can be expressed as continuous queries over video data streams. The stream data type was therefore introduced into the VDBMS system, and system functionality was extended to support general data streams. From this viewpoint, we present an approach for defining and processing streams, including video, through the query execution engine. We describe the implementation of several algorithms for video query processing expressed as continuous queries over video streams, such as fast forward, region-based blurring and left outer join. We include a description of the window-join algorithm as a core operator for continuous query systems, and discuss shared execution as an optimization approach for stream query processing.
{"title":"Video query processing in the VDBMS testbed for video database research","authors":"Walid G. Aref, M. Hammad, A. Catlin, I. Ilyas, T. Ghanem, A. Elmagarmid, M. Marzouk","doi":"10.1145/951676.951682","DOIUrl":"https://doi.org/10.1145/951676.951682","url":null,"abstract":"The increased use of video data sets for multimedia-based applications has created a demand for strong video database support, including efficient methods for handling the content-based query and retrieval of video data. Video query processing presents significant research challenges, mainly associated with the size, complexity and unstructured nature of video data. A video query processor must support video operations for search by content and streaming, new query types, and the incorporation of video methods and operators in generating, optimizing and executing query plans. In this paper, we address these query processing issues in two contexts, first as applied to the video data type and then as applied to the stream data type. We first present the query processing functionality of the VDBMS video database management system as a framework designed to support the full range of functionality for video as an abstract data type. We describe two query operators for the video data type which implement the rank-join and stop-after algorithms. As videos may be considered streams of consecutive image frames, video query processing can be expressed as continuous queries over video data streams. The stream data type was therefore introduced into the VDBMS system, and system functionality was extended to support general data streams. From this viewpoint, we present an approach for defining and processing streams, including video, through the query execution engine. We describe the implementation of several algorithms for video query processing expressed as continuous queries over video streams, such as fast forward, region-based blurring and left outer join. We include a description of the window-join algorithm as a core operator for continuous query systems, and discuss shared execution as an optimization approach for stream query processing.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127510153","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 deals with the problem of finding images that contain a given query image, the so-called content-based sub-image retrieval. We propose an approach based on a hierarchical tree that encodes the color feature of image tiles which are in turn stored as an index sequence. The index sequences of both candidate images and the query sub-image are then compared in order to rank the database images suitability with respect to the query. In our experiments, using 10,000 images and disk-resident metadata, for 60Σ (80Σ) of the queries the relevant image, i.e., the one where the query sub-image was extracted from, was found among the first 10 (50) retrieved images in about 0.15 sec.
{"title":"Content based sub-image retrieval via hierarchical tree matching","authors":"Jie Luo, M. Nascimento","doi":"10.1145/951676.951689","DOIUrl":"https://doi.org/10.1145/951676.951689","url":null,"abstract":"This paper deals with the problem of finding images that contain a given query image, the so-called content-based sub-image retrieval. We propose an approach based on a hierarchical tree that encodes the color feature of image tiles which are in turn stored as an index sequence. The index sequences of both candidate images and the query sub-image are then compared in order to rank the database images suitability with respect to the query. In our experiments, using 10,000 images and disk-resident metadata, for 60Σ (80Σ) of the queries the relevant image, i.e., the one where the query sub-image was extracted from, was found among the first 10 (50) retrieved images in about 0.15 sec.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133409708","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}
Many data partitioning index methods perform poorly in high dimensional space and do not support relevance feedback retrieval. The vector approximation file (VA-File) approach overcomes some of the difficulties of high dimensional vector spaces, but cannot be applied to relevance feedback retrieval using kernel distances in the data measurement space. This paper introduces a novel KVA-File (kernel VA-File) that extends VA-File to kernel-based retrieval methods. A key observation is that kernel distances may be non-linear in the data measurement space but is still linear in an induced feature space. It is this linear invariance in the induced feature space that enables KVA-File to work with kernel distances. An efficient approach to approximating vectors in an induced feature space is presented with the corresponding upper and lower distance bounds. Thus an effective indexing method is provided for kernel-based relevance feedback image retrieval methods. Experimental results using large image data sets (approximately 100,000 images with 463 dimensions of measurement) validate the efficacy of our method.
{"title":"Kernel VA-files for relevance feedback retrieva","authors":"Douglas R. Heisterkamp, Jing Peng","doi":"10.1145/951676.951686","DOIUrl":"https://doi.org/10.1145/951676.951686","url":null,"abstract":"Many data partitioning index methods perform poorly in high dimensional space and do not support relevance feedback retrieval. The vector approximation file (VA-File) approach overcomes some of the difficulties of high dimensional vector spaces, but cannot be applied to relevance feedback retrieval using kernel distances in the data measurement space. This paper introduces a novel KVA-File (kernel VA-File) that extends VA-File to kernel-based retrieval methods. A key observation is that kernel distances may be non-linear in the data measurement space but is still linear in an induced feature space. It is this linear invariance in the induced feature space that enables KVA-File to work with kernel distances. An efficient approach to approximating vectors in an induced feature space is presented with the corresponding upper and lower distance bounds. Thus an effective indexing method is provided for kernel-based relevance feedback image retrieval methods. Experimental results using large image data sets (approximately 100,000 images with 463 dimensions of measurement) validate the efficacy of our method.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130612575","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}
M. Shyu, Shu‐Ching Chen, Min Chen, Chengcui Zhang, Kanoksri Sarinnapakorn
Recent research effort in Content-Based Image Retrieval (CBIR) focuses on bridging the gap between low-level features and high-level semantic contents of images as this gap has become the bottleneck of CBIR. In this paper, an effective image database retrieval framework using a new mechanism called the Markov Model Mediator (MMM) is presented to meet this demand by taking into consideration not only the low-level image features, but also the high-level concepts learned from the history of user's access pattern and access frequencies on the images in the database. Also, the proposed framework is efficient in two aspects: 1) Overhead for real-time training is avoided in the image retrieval process because the high-level concepts of images are captured in the off-line training process. 2) Before the exact similarity matching process, Principal Component Analysis (PCA) is applied to reduce the image search space. A training subsystem for this framework is implemented and integrated into our system. The experimental results demonstrate that the MMM mechanism can effectively assist in retrieving more accurate results from image databases.
{"title":"Image database retrieval utilizing affinity relationships","authors":"M. Shyu, Shu‐Ching Chen, Min Chen, Chengcui Zhang, Kanoksri Sarinnapakorn","doi":"10.1145/951676.951691","DOIUrl":"https://doi.org/10.1145/951676.951691","url":null,"abstract":"Recent research effort in Content-Based Image Retrieval (CBIR) focuses on bridging the gap between low-level features and high-level semantic contents of images as this gap has become the bottleneck of CBIR. In this paper, an effective image database retrieval framework using a new mechanism called the Markov Model Mediator (MMM) is presented to meet this demand by taking into consideration not only the low-level image features, but also the high-level concepts learned from the history of user's access pattern and access frequencies on the images in the database. Also, the proposed framework is efficient in two aspects: 1) Overhead for real-time training is avoided in the image retrieval process because the high-level concepts of images are captured in the off-line training process. 2) Before the exact similarity matching process, Principal Component Analysis (PCA) is applied to reduce the image search space. A training subsystem for this framework is implemented and integrated into our system. The experimental results demonstrate that the MMM mechanism can effectively assist in retrieving more accurate results from image databases.","PeriodicalId":415406,"journal":{"name":"ACM International Workshop on Multimedia Databases","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130786837","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：