We propose a novel approach to Vietnamese word segmentation. Our approach is based on the Single Classification Ripple Down Rules methodology (Compton and Jansen, 1990), where rules are stored in an exception structure and new rules are only added to correct segmentation errors given by existing rules. Experimental results on the benchmark Vietnamese treebank show that our approach outperforms ...

In this work, we focus on a very practical problem: image segmentation under rain conditions. Image deraining is classic low-level restoration task, while typical high-level understanding task. Most of the existing methods intuitively employ bottom-up paradigm by taking as preprocessing step for subsequent segmentation. However, our statistical analysis indicates that not only would benefit (bo...

One way to understand something is to break it up into parts. New research indicates that segmenting ongoing activity into meaningful events is a core component of ongoing perception, with consequences for memory and learning. Behavioral and neuroimaging data suggest that event segmentation is automatic and that people spontaneously segment activity into hierarchically organized parts and sub-p...

Word shape information can be helpful in handwriting recognition. It can be used by a segmentation based recognizer to verify the results of the recognition of individual segmented letters. It is often one of the main features used by wholistic recognizers. This paper describes extraction of the word shape information through identification of the middle zone, then ascenders and descenders. Ext...

A top-down page segmentation technique known as the recursive X-Y cut decomposes a document image recursively into a set of rectanguzar blocks. This paper proposes that the recursive X-Y cut be implemented using bounding bozes of connected components of black pixels instead of using image pizels. The advantage is that great improvement can be achieved in computation. In fact, once bounding boxe...

We report in this paper a robust implementation of document segmentation and classification. In this algorithm, top-down approach is adopted due to its fast processing speed and reliability. In addition, the approach accounts for every portion of the processed page and it is also capable of image display a t different scale and allowing editing of classified blocks such as changing, merging and...

In this paper we present a new approach for segmentation of 3D models. The goal of the proposed approach is the decomposition of a model into large simple and small complex components. The top-down decomposition is achieved through the iterative bisection of the model. The bisection process is represented in the hierarchical tree structure. Further the obtained segments are checked on the possi...

We present an integrated approach combining region and contour–based techniques to enhance both segmentation and recognition processes. This cue integration operates on the level of contour–based groups and complete regions, which are matched to reflect a common cause in the image (and thus in the scene). Additionally, we realize a top–down scheme controlling the segmentation process on the bas...

The use of remote sensing imagery to obtain land cover and land use maps is a common task in GIS applications. Segmentation techniques identify closed regions in images, producing vector datasets composed by polygons. Since segmentation is a bottom-up technique, the resulting vector datasets are often too detailed. Thus, we need to use generalization techniques to reduce data storage and genera...

In this paper, an image segmentation method based on directed image region partitioning is proposed. The method consists of two separate stages: a splitting phase followed by a merging phase. The splitting phase starts with an initial coarse triangulation and employs the incremental Delaunay triangulation as a directed image region splitting technique. The trian-gulation process is accomplished...