In this paper we propose a character segmentation method for multispectral images of ancient documents. Due to the low quality of the images the main idea of this study is to combine the multispectral behavior and con...
详细信息
We review multilevel hierarchies under two special aspects: their potential for abstraction and for storing discrete representations. Motivated by claims to ‘bridge the representational gap between image and model fe...
详细信息
Multi-spectral imaging for the analysis and preservation of ancient documents has gained high attention in recent years. While readability enhancement is based on the multi-spectral image corpus, foreground-background...
详细信息
ISBN:
(纸本)9781605587738
Multi-spectral imaging for the analysis and preservation of ancient documents has gained high attention in recent years. While readability enhancement is based on the multi-spectral image corpus, foreground-background separation still relies mainly on gray level or color images. In this paper we propose a foreground-background separation algorithm designed for multi-spectral images. The main contribution is the simultaneously utilization of spectral and spatial features. While spectral features incorporate the spectral components of the multi-spectral images, the spatial features are based on stroke properties. Higher order Markov Random Fields enables an efficient way to combine both features. To solve higher order energy functions, we introduce a new message update rule in the well known belief propagation algorithm based on a higher order potential function. Copyright 2010 ACM.
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
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
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
This paper proposes a drawing tool recognition method based on features calculated from the shape of stroke endings. The application for this method is to help art historians to identify the drawing tool used for a dr...
In this paper we propose a method for segmenting characters in multispectral images of ancient documents. Due to the low quality of the document images the main idea of our study is to combine the multispectral behavi...
详细信息
Two medieval Slavonic manuscripts are recorded, investigated and analyzed by philologists in collaboration with computer scientists. The aim of the project is to develop algorithms that support the philologists by aut...
详细信息
The human visual system as a functional unit including the eyes, the nervous system, and the corresponding parts of the brain certainly ranks among the most important means of human information processing. The e?cienc...
详细信息
ISBN:
(数字)9780387216430
ISBN:
(纸本)9780387950662;9781475775174
The human visual system as a functional unit including the eyes, the nervous system, and the corresponding parts of the brain certainly ranks among the most important means of human information processing. The e?ciency of the biological systems is beyond the capabilities of today’s technical systems, even with the fastest available computer systems. However, there are areas of application where digital image analysis systems produce acceptable results. Systems in these areas solve very specialized tasks, they operate in a limited environment, and high speed is often not necessary. Several factors determine the economical application of technical vision systems: cost, speed, ?exibility, robu- ness, functionality, and integration with other system components. Many of the recent developments in digital imageprocessing and patternrecognition show some of the required achievements. computer vision enhances the capabilities of computer systems • in autonomously collecting large amounts of data, • in extracting relevant information, • in perceiving its environment, and • in automatic or semiautomatic operation in this environment. The development of computer systems in general shows a steadily increasing need in computational power, which comes with decreasing hardware costs.
暂无评论