A concept relating story-board description of video sequences with spatio-temporal hierarchies build by local contraction processes of spatio-temporal relations is presented. Object trajectories are curves in which th...
详细信息
Two segmentation methods based on the minimum spanning tree principle are evaluated with respect to each other. The hierarchical minimum spanning tree method is also evaluated with respect to human segmentations. Disc...
详细信息
Motivated by claims to 'bridge the representational gap between image and model features' and by the growing importance of topological properties we discuss several extensions to dual graph pyramids: structura...
详细信息
The trained Gaussian mixture model is used to make skincolour segmentation for the input image sequences. The hand gesture region is extracted, and the relative normalization images are obtained by interpolation opera...
详细信息
The trained Gaussian mixture model is used to make skincolour segmentation for the input image sequences. The hand gesture region is extracted, and the relative normalization images are obtained by interpolation operation. To solve the proem of hand gesture recognition, Fuzzy-Rough based nearest neighbour（RNN） algorithm is applied for classification. For avoiding the costly compute, an improved nearest neighbour classification algorithm based on fuzzy-rough set theory （FRNNC） is proposed. The algorithm employs the represented cluster points instead of the whole training samples, and takes the hand gesture data＇s fuzziness and the roughness into account, so the campute spending is decreased and the recognition rate is increased. The 30 gestures in Chinese sign language alphabet are used for approving the effectiveness of the proposed algorithm. The recognition rate is 94.96%, which is better than that of KNN （K nearest neighbor）and Fuzzy- KNN （Fuzzy K nearest neighbor）.
The scope of this paper is the challenging task of classifying terrestrial images of buildings, automatically. Straight line segments and their connectivity incorporate significant information about object shapes. Man...
详细信息
Thousands of fragments of ceramics (called sherds for short) are found at archaeological excavation sites. One of these excavations sites is Tel Dor in Israel. The excavators in Dor use hand drawings and a profilograp...
详细信息
Thousands of fragments of ceramics (called sherds for short) are found at archaeological excavation sites. One of these excavations sites is Tel Dor in Israel. The excavators in Dor use hand drawings and a profilograph for documentation of sherds. Both techniques acquire a cross-section of the sherd, the so called profile line, which is used for classification and statistical analysis about the ancient population of Dor. As proposed in previous work we are developing a fully automated system for documentation of sherds by 3D-acquisition based on structured light and extraction of the profile line. Consequently we joined the field trip to Tel Dor in July, 2004 to compare in-situ the accuracy and performance of the traditional hand drawings, the profilograph and our system. We therefore alos measured the time for each step of documentation in-situ to find bottle-necks in documented sherds per hour. Based on these results we could propose an improvement to increase the throughput of our system by a factor of 5. The results of the comparison of all three techniques of documentation of sherds, the improvement for our system and a methodological experiment for future work are shown in this report.
Fast radial symmetry transform can fast detect points of interest and is the improvement of generalized symmetry transform. Firstly, the location of eyebrows is estimated. According to the location of eyebrows, in cer...
详细信息
Fast radial symmetry transform can fast detect points of interest and is the improvement of generalized symmetry transform. Firstly, the location of eyebrows is estimated. According to the location of eyebrows, in certain range that possibly includes eyes, fast radial symmetry transform is used to detect black points of interest. After rectifying a deviation and according to the geometrical features, the eyes candidates are selected and the precise location can be decided by pupil model. The experiments in ORL and SJTU-IPPR fact database show the algorithm is effective and can be used in real-time system.
image segmentation is a key technology to image analysis and processing. How to segment portrait fast and robust from the background is a difficult problem. With revising histogram segmentation by threshold in blue to...
详细信息
ISBN:
(纸本)9781932415643
image segmentation is a key technology to image analysis and processing. How to segment portrait fast and robust from the background is a difficult problem. With revising histogram segmentation by threshold in blue tone space, we present an adaptable quantum evolution threshold-searching algorithm to segment portrait fast and robust. Experiments and detail comparison analysis are provided to demonstrate effects.
Radar scene matching technique has been widely found in many application fields such as remote sensing, navigation, terrain-map match, scenery variance analysis and so on. Radar image geometry is quite different from ...
详细信息
Radar scene matching technique has been widely found in many application fields such as remote sensing, navigation, terrain-map match, scenery variance analysis and so on. Radar image geometry is quite different from that of optical satellite imagery, whose imaging is a slanting imaging of electromagnetic microwave reflection. The different characters between radar image and optical satellite images are very distinct, such as the layover distortion of ground-truth and speckle noise, which degrades the image to such an extent that the features are very unclear and difficult to be extracted. So the factors such as the hypsography, ground truth, sensor altitude and imaging time should be taken into account for radar image and optical image matching. In this paper, we develop an image match algorithm based on reference map multi-area selection using fuzzy sets. image matching is generally a procedure that calculates the similarity measurement between sensed image and the corresponding intercepted image in reference map and it searches the maximum position in the correlation map. Our method adopts a converse matching strategy which selects multi-areas in optical reference map using fuzzy sets as model images, then match them on the sensed image respectively by normalized cross correlation matching algorithm and fuse the match results to get the optimum registered position. Multi-areas selection mainly considers two influence factors such as ground-truth texture features and the hypsography (DEM) of imaging region, which will suppress the influence of great variance imaging region. Experiment results show the method is effective in registering performance and reducing the calculation.
In this paper, we propose a novel automatic object extraction algorithm, named the Template Guided Live Wire, based on the popularly used live-wire techniques. We discuss in details the novel method’s applications on...
详细信息
In this paper, we propose a novel automatic object extraction algorithm, named the Template Guided Live Wire, based on the popularly used live-wire techniques. We discuss in details the novel method’s applications on tongue extraction in digital images. With the guides of a given template curve which approximates the tongue’s shape, our method can finish the extraction of tongue without any human intervention. In the paper, we also discussed in details how the template guides the live wire, and why our method functions more effectively than other boundary based segmentation methods especially the snake algorithm. Experimental results on some tongue images are as well provided to show our method’s better accuracy and robustness than the snake algorithm.
暂无评论