In this paper a new method is developed to make a dynamic layout adjustmentand navigation for enterprise Geographic Information System (GIS) based on object mark recognition.The extraction of object mark images is bas...In this paper a new method is developed to make a dynamic layout adjustmentand navigation for enterprise Geographic Information System (GIS) based on object mark recognition.The extraction of object mark images is based on some morphological structural patterns, which aredescribed by morphological structural points, contour property, and other geometrical data in abinary image of enterprise geographic information map. Some pre-processing methods, contour smoothfollowing, linearization and extraction patterns of structural points, are introduced. If anyspecial object is selected to make a decision in a GIS map, the all information around it will beobtained. That is, we need to investigate similar object enterprises around selected region toanalyse whether it is necessary for establishing the object enterprise at that place. To furthernavigate GIS map, we need to move from one region to another. Each time a region is formed anddisplayed based on the user's focus. If a focus point of a map is selected, in terms of extractedobject mark image, a dynamic layout and navigation diagram is constructed. When the user changes thefocus (i. e. click a node in the navigation mode), a new sub-diagram is formed by dropping oldnodes and adding new nodes. The prototype system provides effective interfaces that support GISimage navigation, detailed local image/map viewing, and enterprise information browsing.展开更多
Sound indexing and segmentation of digital documentsespecially in the internet and digital libraries are very useful tosimplify and to accelerate the multimedia document retrieval. Wecan imagine that we can extract mu...Sound indexing and segmentation of digital documentsespecially in the internet and digital libraries are very useful tosimplify and to accelerate the multimedia document retrieval. Wecan imagine that we can extract multimedia files not only bykeywords but also by speech semantic contents. The maindifficulty of this operation is the parameterization and modellingof the sound track and the discrimination of the speech, musicand noise segments. In this paper, we will present aSpeech/Music/Noise indexing interface designed for audiodiscrimination in multimedia documents. The program uses astatistical method based on ANN and HMM classifiers. After preemphasisand segmentation, the audio segments are analysed bythe cepstral acoustic analysis method. The developed system wasevaluated on a database constituted of music songs with Arabicspeech segments under several noisy environments.展开更多
基金an Australian Research Council SPIRT grant(C00107573).
文摘In this paper a new method is developed to make a dynamic layout adjustmentand navigation for enterprise Geographic Information System (GIS) based on object mark recognition.The extraction of object mark images is based on some morphological structural patterns, which aredescribed by morphological structural points, contour property, and other geometrical data in abinary image of enterprise geographic information map. Some pre-processing methods, contour smoothfollowing, linearization and extraction patterns of structural points, are introduced. If anyspecial object is selected to make a decision in a GIS map, the all information around it will beobtained. That is, we need to investigate similar object enterprises around selected region toanalyse whether it is necessary for establishing the object enterprise at that place. To furthernavigate GIS map, we need to move from one region to another. Each time a region is formed anddisplayed based on the user's focus. If a focus point of a map is selected, in terms of extractedobject mark image, a dynamic layout and navigation diagram is constructed. When the user changes thefocus (i. e. click a node in the navigation mode), a new sub-diagram is formed by dropping oldnodes and adding new nodes. The prototype system provides effective interfaces that support GISimage navigation, detailed local image/map viewing, and enterprise information browsing.
文摘Sound indexing and segmentation of digital documentsespecially in the internet and digital libraries are very useful tosimplify and to accelerate the multimedia document retrieval. Wecan imagine that we can extract multimedia files not only bykeywords but also by speech semantic contents. The maindifficulty of this operation is the parameterization and modellingof the sound track and the discrimination of the speech, musicand noise segments. In this paper, we will present aSpeech/Music/Noise indexing interface designed for audiodiscrimination in multimedia documents. The program uses astatistical method based on ANN and HMM classifiers. After preemphasisand segmentation, the audio segments are analysed bythe cepstral acoustic analysis method. The developed system wasevaluated on a database constituted of music songs with Arabicspeech segments under several noisy environments.
