• MALSORI
• /
• no.29_30
• /
• pp.43-60
• /
• 1995

Standard generative phonologists assumed that there were no orders or hierarchies among distinctive features. This means that the distinctive features which make up a segment are independent and unordered. The unordered linear matrix cannot explain phonological phenomena such as complex segments as hierarchical representation does neatly. The hierarchical feature representation theory which embodies the concept of multi-tiered phonological representation organizes distinctive features in the appearance of hierarchical dominance. This paper aims to show how we can solve some problems of the linear feature representation. As regard underlying representation the theory of underspecification is discussed. I propose a feature hierarchy similar to that of Sagey(1986) but slightly different. I show English consonantal assimilation in feature hierarchical model compared with that of feature changing theory of linear representation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2390-2406
• /
• 2022

Scene text recognition has important application value and attracted the interest of plenty of researchers. At present, many methods have achieved good results, but most of the existing approaches attempt to improve the performance of scene text recognition from the image level. They have a good effect on reading regular scene texts. However, there are still many obstacles to recognizing text on low-quality images such as curved, occlusion, and blur. This exacerbates the difficulty of feature extraction because the image quality is uneven. In addition, the results of model testing are highly dependent on training data, so there is still room for improvement in scene text recognition methods. In this work, we present a natural scene text recognizer to improve the recognition performance from the feature level, which contains feature representation and feature enhancement. In terms of feature representation, we propose an efficient feature extractor combined with Representative Batch Normalization and ResNet. It reduces the dependence of the model on training data and improves the feature representation ability of different instances. In terms of feature enhancement, we use a feature enhancement network to expand the receptive field of feature maps, so that feature maps contain rich feature information. Enhanced feature representation capability helps to improve the recognition performance of the model. We conducted experiments on 7 benchmarks, which shows that this method is highly competitive in recognizing both regular and irregular texts. The method achieved top1 recognition accuracy on four benchmarks of IC03, IC13, IC15, and SVTP.

• International Journal of CAD/CAM
• /
• v.3 no.1_2
• /
• pp.67-75
• /
• 2003

Viewpoint-dependent feature-based modelling in computer-aided design is developed for the purposes of supporting engineering design representation and automation. The approach of this paper uses a combination of a multi-level modelling approach. This has two stages of mapping between models, and the multi-level model approach is implemented in three-level architecture. Top of this level is a feature-based description for each viewpoint, comprising a combination of form features and other features such as loads and constraints for analysis. The middle level is an executable representation of the feature model. The bottom of this multi-level modelling is a evaluation of a feature-based CAD model obtained by executable feature representations defined in the middle level. The mappings involved in the system comprise firstly, mapping between the top level feature representations associated with different viewpoints, for example for the geometric simplification and addition of boundary conditions associated with moving from a design model to an analysis model, and secondly mapping between the top level and the middle level representations in which the feature model is transformed into the executable representation. Because an executable representation is used as the intermediate layer, the low level evaluation can be active. The example will be implemented with an analysis model which is evaluated and for which results are output. This multi-level modelling approach will be investigated within the framework aimed for the design automation with a feature-based model.

• MALSORI
• /
• no.33_34
• /
• pp.71-89
• /
• 1997

In the framework of linear representation which allows for no internal structure within features, there is no way to represent nonlinear phonological phenomena such as complex segments. This paper shows how we carl solve some problems of the linear feature theory in relation to the hierarchical feature theory. The purpose of this paper is to explain lateral assimilation under hierarchical feature representation. Although arguments for the position of classes of distinctive features have been made the position of (lateral) remains the issue of debate. Sagey(1988) argues that the feature [lateral] is structurally dependent on the root node. In contrast Rice & Avery (1991) put the feature (lated) under the spontaneous voicing. I have discussed previous studies of feature hierarchy and I propose a revised model of feature representation. Within this model I have shown how well feature geometry describes lateralization as feature spreading.

• Korean Journal of Computational Design and Engineering
• /
• v.18 no.1
• /
• pp.71-82
• /
• 2013

To modify product design easily, modern CAD systems adopt the feature-based model as their primary representation. On the other hand, the boundary representation (B-rep) model is used as their secondary representation. IGES and STEP AP203 edition 1 are the representative standard formats for the exchange of CAD files. Unfortunately, both of them only support the B-rep model. As a result, feature data are lost during the CAD file exchange based on these standards. Loss of feature data causes the difficulty of CAD model modification and prevents the transfer of design intent. To resolve this problem, a tool for recognizing design features from a B-rep model and then reconstructing a feature-based model with the recognized features should be developed. As the first part of this research, this paper presents a method for decomposing a B-rep model into simple volumes suitable for design feature recognition. The results of experiments with a prototype system are analyzed. From the analysis, future research issues are suggested.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.11
• /
• pp.148-158
• /
• 1995

This paper describes a hierarchical structure for feature definition and classification, and feature representation method based on frame structure for process planning of prismatic machined components of injection mold. The concept of Volume Removal Directions and Vertical Faces is proposed to develop a method to define and to classify features for components of injection mold systematically. A method for classifying features by the combination of volume removal directions and vertical faces is developed, and also a feature representation method by using frame structure to represent design and manufacturing information is presented.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.4
• /
• pp.240-248
• /
• 2014

We present a robust speaker identification algorithm that uses novel features based on soft bag-of-word representation and a simple Naive Bayes classifier. The bag-of-words (BoW) based histogram feature descriptor is typically constructed by summarizing and identifying representative prototypes from low-level spectral features extracted from training data. In this paper, we define a generalization of the standard BoW. In particular, we define three types of BoW that are based on crisp voting, fuzzy memberships, and possibilistic memberships. We analyze our mapping with three common classifiers: Naive Bayes classifier (NB); K-nearest neighbor classifier (KNN); and support vector machines (SVM). The proposed algorithms are evaluated using large datasets that simulate medical crises. We show that the proposed soft bag-of-words feature representation approach achieves a significant improvement when compared to the state-of-art methods.

• Journal of Computing Science and Engineering
• /
• v.8 no.2
• /
• pp.65-77
• /
• 2014

To address the problem of multi-target retrieval (MTR) of remote sensing images, this study proposes a new object-level feature representation model. The model provides an enhanced application image representation that improves the efficiency of MTR. Generating the model in our scheme includes processes, such as object-oriented image segmentation, feature parameter calculation, and symbolic image database construction. The proposed model uses the spatial representation method of the extended nine-direction lower-triangular (9DLT) matrix to combine spatial relationships among objects, and organizes the image features according to MPEG-7 standards. A similarity metric method is proposed that improves the precision of similarity retrieval. Our method provides a trade-off strategy that supports flexible matching on the target features, or the spatial relationship between the query target and the image database. We implement this retrieval framework on a dataset of remote sensing images. Experimental results show that the proposed model achieves competitive and high-retrieval precision.

• Korean Journal of Computational Design and Engineering
• /
• v.1 no.2
• /
• pp.122-132
• /
• 1996

Features are generic shapes with which engineers associate certain attributes and knowledge useful in reasoning about the product. Feature-based modeling systems support additional levels of information beyond those available in geometric modelers. The objective of this study is to develop a PC level feature-based modeling system which explicitly represents dimensions of the part. The feature-based modeler retains all the benefits of traditional B-rep. solid models, and represents the dimensions at a high level of a abstraction so that dimension driven geometry can be achieved.

• Journal of Computing Science and Engineering
• /
• v.12 no.1
• /
• pp.1-11
• /
• 2018

Human activities recognition is a challenging task due to its complexity of human movements and the variety performed by different subjects for the same action. This paper presents a recognition algorithm by using skeleton information generated from depth maps. Concatenating motion features and temporal constraint feature produces feature vector. Reducing dictionary scale proposes an improved fast classifier based on sparse representation. The developed method is shown to be effective by recognizing different activities on the UTD-MHAD dataset. Comparison results indicate superior performance of our method over some existing methods.