this paper presents a new method for structuring and tracking of objects in video sequences. Our approach is based on image moments and the bsp-tree data structure. We use invariant properties of these moments to cons...
详细信息
ISBN:
(纸本)076951846X
this paper presents a new method for structuring and tracking of objects in video sequences. Our approach is based on image moments and the bsp-tree data structure. We use invariant properties of these moments to construct a bsp-tree and determine an ellipsis that approximates the object's shape. then, we employ this information to track objects frame by frame through the image sequence. the method works well for segmented images with a single object and we assume that the motion will not change abruptly.
this work presents the prototype system for a color-based retrieval of images collected on the Web. the images collected are classified in two semantic classes (photographs and graphics) but only photographs are index...
详细信息
ISBN:
(纸本)076951846X
this work presents the prototype system for a color-based retrieval of images collected on the Web. the images collected are classified in two semantic classes (photographs and graphics) but only photographs are indexed. It basically stores information about regions withthe same color in the image (chromatic regions), such as size, position and boundaries with another regions. this data representation is made using histogram variations of the image as graphs: the Modified Color Adjacency Graph (MCAG) and the Variance Graph (SVG). image retrieval is done by applying a similar metric based on the comparison of the graphs mentioned here.
this work presents a simple method to obtain fingerprint classification via directional map smoothing. the program was developed in C++ language, using statistical techniques. that strategy allows to extract attribute...
详细信息
ISBN:
(纸本)076951846X
this work presents a simple method to obtain fingerprint classification via directional map smoothing. the program was developed in C++ language, using statistical techniques. that strategy allows to extract attributes of an image and to increase the quality of the process due reduction of the noise, if compared withthe result obtained by mean other method exposed in literature. the experimental results, obtained by this technique, demonstrate that a better directional map is arranged.
Many intrinsically 2-dimensional visual signals can be effectively encoded in a I-D form. this simpler representation is well-suited to both pattern recognition and image retrieval tasks. this poster deals with contou...
详细信息
ISBN:
(纸本)076951846X
Many intrinsically 2-dimensional visual signals can be effectively encoded in a I-D form. this simpler representation is well-suited to both pattern recognition and image retrieval tasks. this poster deals with contour and texture, combined together in order to obtain an effective technique for content based image indexing. the data used for experimentally assessing CONTEXT were contours and textures from various application domains. the experiments reveal a high discriminating power which in turn yields a high perceived quality of the retrieval results.
We describe ongoing research on the development of a functional system for diagnosing and measuring ocular refractive errors in the human eye (astigmatism, hypermetropia and myopia) by automatically analyzing images o...
详细信息
ISBN:
(纸本)076951846X
We describe ongoing research on the development of a functional system for diagnosing and measuring ocular refractive errors in the human eye (astigmatism, hypermetropia and myopia) by automatically analyzing images of the human ocular globe acquired withthe Hartmann-Shack (H-S) technique. H-S images are to be input into a system capable of recognizing the presence of a refractive error and outputting a measurement of such an error. Because the H-S technique provides images rich with information on the human eye, we believe this system may provide a framework that can be extended to get additional information on the health of imaged ocular globes.
作者：
Ye, BPeng, JXHuazhong Univ Sci & Technol
Inst Pattern Recognit & Artificial Intelligence State Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China
An improved Zernike moment using as a region-based shape descriptor is presented the improved Zernike moment not only has rotation invariance, but also has scale invariance that the unimproved Zernike moment does not ...
详细信息
ISBN:
(纸本)076951846X
An improved Zernike moment using as a region-based shape descriptor is presented the improved Zernike moment not only has rotation invariance, but also has scale invariance that the unimproved Zernike moment does not have. the experimental results show that the improved Zernike moment has better invariant properties than unimproved Zernike moment using as region-based shape descriptor.
the problem of image data fusion includes several techniques for data integration from different sensors about a given object. the process can be divided in two stages: (a) pixel interpolation on each observed image t...
详细信息
ISBN:
(纸本)076951846X
the problem of image data fusion includes several techniques for data integration from different sensors about a given object. the process can be divided in two stages: (a) pixel interpolation on each observed image to equalize their resolutions;and (b) synthesis of the fused image using the interpolated images. this work proposes the use of projection onto convex sets (POCS) techniques in both stages of the image data fusion process: on the interpolation stage, by creating intermediate pixels more adapted to the local characteristics of the observed images;and on the synthesis stage, by generating a final multispectral imagethat incorporates the best spatial and spectral characteristics of the initial images. As an example, the algorithm is applied to Spot satellite images.
Boolean expansion of binary functions has been used in the representation of binary image operators. this representation scheme induced the creation of imageprocessing architectures based on decision diagrams. In som...
详细信息
ISBN:
(纸本)076951846X
Boolean expansion of binary functions has been used in the representation of binary image operators. this representation scheme induced the creation of imageprocessing architectures based on decision diagrams. In some situations, the application of this graph-based operator over the input images is faster than the corresponding conventional approach, in that the operators are constructively described by means of basic operators and set operations. However, when the conventional architecture exploits the bit parallelism of the microprocessor logical instructions, its performance often surpasses that of the graph-based system. this article proposes a novel approach, in which the decision diagrams guide the actions of the underlying conventional architecture, taking advantage of its parallelism, so that faster imageprocessing can be achieved.
A new three-dimensional reconstruction technique is presented that uses an integer control parameter, denoted beta, to produce a family of models from a given set of planar cross-sections. Parameter beta supports mult...
详细信息
ISBN:
(纸本)076951846X
A new three-dimensional reconstruction technique is presented that uses an integer control parameter, denoted beta, to produce a family of models from a given set of planar cross-sections. Parameter beta supports multiple choices for solving the correspondence problem, i.e., the problem of deciding which regions from two consecutive cross-sections must be connected into a single component. thus, unlike current reconstruction methods, the beta-connection algorithm enables the consideration of multiple alternatives when establishing region correspondence. In addition to this flexibility, which is useful in creating models with complex topologies, the algorithm produces PL-manifolds and respects the re-sampling condition, thus providing an interesting reconstruction solution for many practical visualization and numerical simulation applications.
Texture information is useful for image data browsing and retrieval. the goal of this paper is to present a texture classification system for remote sensing images addressed to the administration of great collections ...
详细信息
ISBN:
(纸本)076951846X
Texture information is useful for image data browsing and retrieval. the goal of this paper is to present a texture classification system for remote sensing images addressed to the administration of great collections of those images. the proposed classifier is a hybrid system composed by an unsupervised neural network and a supervised one. Starting from a small portion of the image (pattern) the system should recognize the most similar class to a pattern in a database as well as to identify the images that contain similar patterns. the texture feature vectors used to characterize the patterns are obtained from the images processed by a bank of Gabor Filters. Some experimental results using textures of the Brodatz album, multi-spectral and radar images are presented here.
暂无评论