• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.8
• /
• pp.335-343
• /
• 2002

A segment matching algorithm in stereo vision via the fusion of multiple features on long edge segments is proposed. One problem of the previous segment matching algorithm is the similarity among the segments caused from its short length. In the proposed algorithm, edges are composed of longer segments which are obtained by breaking the edges only at the locations with distinguished changes of the shape. Such long segments can contain extra features such as curvature ratio and length of segments which could not be included in shorter ones. Use of such additional features enhances the matching accuracy significantly To fuse multiple features for matching, weighting value determination algorithm which is computed according to the degree of the contribution of each factor is proposed. The stereo matching simulations with the proposed algorithm are done about various images and their results are included.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.138.1-138
• /
• 2001

Usually, when we take a conversation with another, we can know his emotion as well as his idea. Recently, some applications using speech recognition comes out , however, those can recognize only context of various informations which he(she) gave. In the future, machine familiar to human will be a requirement for more convenient life. Therefore, we need to get emotion features. In this paper, we´ll collect a multiplicity of reference data which represent emotion features from the speech signal. As our final target is to recognize emotion from a stream of speech, as such, we must be able to understand features that represent emotion. There are much emotions human can show. the delicate difference of emotions makes this recognition problem difficult.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4534-4555
• /
• 2015

We propose a robust object cataloging method using multiple locally distinct heterogeneous features for aiding image retrieval. Due to challenges such as variations in object size, orientation, illumination etc. object recognition is extraordinarily challenging problem. In these circumstances, we adapt local interest point detection method which locates prototypical local components in object imageries. In each local component, we exploit heterogeneous features such as gradient-weighted orientation histogram, sum of wavelet responses, histograms using different color spaces etc. and combine these features together to describe each component divergently. A global signature is formed by adapting the concept of bag of feature model which counts frequencies of its local components with respect to words in a dictionary. The proposed method demonstrates its excellence in classifying objects in various complex backgrounds. Our proposed local feature shows classification accuracy of 98% while SURF,SIFT, BRISK and FREAK get 81%, 88%, 84% and 87% respectively.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.295-296
• /
• 2007

Fake fingersubmission to the sensor is a major problem in fingerprint recognition systems. In this paper, we introduce a novel liveness detection method using multi-static features. For convenience and usefulness of field application, static features are only considered to detect 'live' and 'fake' fingerprint images. Individual pore spacing, noise of image and first order statistics of image are analyzed as our static features to reflect the Physiological and statistical characteristics of live and fake fingerprint.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.156-156
• /
• 2002

We apply independent component analysis (ICA) for extracting an optimal basis to the problem of finding efficient features for representing speech signals of a given speaker The speech segments are assumed to be generated by a linear combination of the basis functions, thus the distribution of speech segments of a speaker is modeled by adapting the basis functions so that each source component is statistically independent. The learned basis functions are oriented and localized in both space and frequency, bearing a resemblance to Gabor wavelets. These features are speaker dependent characteristics and to assess their efficiency we performed speaker identification experiments and compared our results with the conventional Fourier-basis. Our results show that the proposed method is more efficient than the conventional Fourier-based features in that they can obtain a higher speaker identification rate.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.1-12
• /
• 2021

In this paper, we present a new architecture for semantic segmentation. Semantic segmentation aims at a pixel-wise classification which is important to fully understand images. Previous semantic segmentation networks use features of multi-layers in the encoder to predict final results. However, they do not contain various receptive fields in the multi-layers features, which easily lead to inaccurate results for boundaries between different classes and small objects. To solve this problem, we propose a multi-path feature fusion module that allows for features of each layers to contain various receptive fields by use of a set of dilated convolutions with different dilatation rates. Various experiments demonstrate that our method outperforms previous methods in terms of mean intersection over unit (mIoU).

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.20 no.2
• /
• pp.1-10
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis, a model can be constructed with various machine learning algorithms, including decision tree. And feature importance has been utilized in selecting better input features that can improve performance of data analysis models for several application areas. In this paper, a method of utilizing feature importance calculated from the MDI method and its effects are investigated in the credit card customer churn prediction problem with classification trees. Compared with several random feature selections from case data, a set of input features selected from higher value of feature importance shows higher predictive power. It can be an efficient method for classifying and choosing input features necessary for improving prediction performance. The method organized in this paper can be an alternative to the selection of input features using feature importance in composing and using classification trees, including credit card customer churn prediction.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.476-479
• /
• 2003

The Rough transform (HT) is often used for extracting global features in binary images, for example curve and line segments, from local features such as single pixels. The HT is useful due to its insensitivity to missing edge points and occlusions, and robustness in noisy images. However, it possesses some disadvantages, such as time and memory consumption due to the number of input data and the selection of an optimal and efficient resolution of the accumulator space can be difficult. Another problem of the HT is in the difficulty of peak detection due to the discrete nature of the image space and the round off in estimation. In order to resolve the problem mentioned above, a possibilistic C-means approach to clustering [1] is used to cluster neighboring peaks. Several experimental results are given.

• ETRI Journal
• /
• v.42 no.3
• /
• pp.420-432
• /
• 2020

The reconstruction of archaeological fragments in 3D geometry is an important problem in pattern recognition and computer vision. Therefore, we implement an algorithm with the help of a 3D model to perform reconstruction from the real datasets using the slope features. This approach avoids the problem of gaps created through the loss of parts of the artifacts. Therefore, the aim of this study is to assemble the object without previous knowledge about the form of the original object. We utilize the edges of the fragments as an important feature in reconstructing the objects and apply multiple procedures to extract the 3D edge points. In order to assign the positions of the unknown parts that are supposed to match, the contour must be divided into four parts. Furthermore, to classify the fragments under reconstruction, we apply a backpropagation neural network. We test the algorithm on several models of ceramic fragments. It achieves highly accurate results in reconstructing the objects into their original forms, in spite of absent pieces.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.3
• /
• pp.372-379
• /
• 2014

This paper surveys past and state-of-the-art SLAM technologies. The standard methods for solving the SLAM problem are the Kalman filter, particle filter, graph, and bundle adjustment-based methods. Kalman filters such as EKF (Extended Kalman Filter) and UKF (Unscented Kalman Filter) have provided successful results for estimating the state of nonlinear systems and integrating various sensor information. However, traditional EKF-based methods suffer from the increase of computation burden as the number of features increases. To cope with this problem, particle filter-based SLAM approaches such as FastSLAM have been widely used. While particle filter-based methods can deal with a large number of features, the computation time still increases as the map grows. Graph-based SLAM methods have recently received considerable attention, and they can provide successful real-time SLAM results in large urban environments.