• Journal of Korea Multimedia Society
• /
• v.23 no.1
• /
• pp.1-7
• /
• 2020

Clustering methods essentially take a two-step approach; extracting feature vectors for dimensionality reduction and then employing clustering algorithm on the extracted feature vectors. However, for clustering images, the traditional clustering methods such as stacked auto-encoder based k-means are not effective since they tend to ignore the local information. In this paper, we propose a method first to effectively reduce data dimensionality using convolutional auto-encoder to capture and reflect the local information and then to accurately cluster similar data samples by using a hierarchical clustering approach. The experimental results confirm that the clustering results are improved by using the proposed model in terms of clustering accuracy and normalized mutual information.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.129-137
• /
• 1994

In this paper, a new texture feature extraction method for texture image classification is proposed. The proposed method is a modified texture spectrum method. It uses local weighting averaged texture unit, that is, the neighbor pixels are weithted and averaged in 4-direction and the calculated values are compared with center pixel to find texture units. The proposed method has only 81 texture units and these units are really good features for texture classification. The proposed method is applied to vegetable images and Blodatz album images and compared with several conventional methods for the feature extraction time and the recognition rate.

• International Journal of Contents
• /
• v.8 no.1
• /
• pp.30-38
• /
• 2012

Text extraction and binarization are the important pre-processing steps for text recognition. The performance of text binarization strongly related to the accuracy of recognition stage. In our proposed method, the first stage based on line detection and shape feature analysis applied to locate the position of a business card and detect the shape from the complex environment. In the second stage, several local regions contained the possible text components are separated based on the projection histogram. In each local region, the pixels grouped into several connected components based on the connected component labeling and projection histogram. Then, classify each connect component into text region and reject the non-text region based on the feature information analysis such as size of connected component and stroke width estimation.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1211-1219
• /
• 2015

In a hidden Markov model-based speech synthesis system using a two-band excitation model, a maximum voiced frequency (MVF) is the most important feature as an excitation parameter because the synthetic speech quality depends on the MVF. This paper proposes an enhanced MVF estimation scheme based on a peak picking method. In the proposed scheme, both local peaks and peak lobes are picked from the spectrum of a linear predictive residual signal. The average of the normalized distances of local peaks and peak lobes is calculated and utilized as a feature to estimate an MVF. Experimental results of both objective and subjective tests show that the proposed scheme improves the synthetic speech quality compared with that of a conventional one in a mobile device as well as a PC environment.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2634-2636
• /
• 2001

This paper proposes a new method of retrieving images from large image databases. The method is based on VQ(Vector Quantization) of local texture information at interest points automatically detected in an image. The texture features are extracted by Gabor wavelet filter bank, and rearranged for rotation. These features are classified by VQ and then construct a pattern histogram. Retrievals are performed by just comparing pattern histograms between images. Experimental results have shown the robustness of the proposed method to image rotation, small scale change, noise addition and brightness change and also shown the possibility of the retrieval by a partial image.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2420-2422
• /
• 2003

In this paper, two Fuzzy Logics for path planning of an autonomous mobile robot are proposed. If a target point is given, such problems regarding the velocity and object recognition are closely related with path to which the mobile robot navigates. Therefore, to ensure safety navigation of the mobile robot for two fuzzy logic parts, path planning considering the surrounding environment was performed in this paper. First, feature points for local and global path are determined by utilizing Cell Decomposition off-line computation. Second, the on-line robot using two Fuzzy Logics navigates around path when it tracks the feature points. We demonstrated optimized path planning only for local path using object recognition fuzzy logic corresponds to domestic situation. Furthermore, when navigating, the robot uses fuzzy logic for velocity and target angle. The proposed algorithms for path planning has been implemented and tested with pioneer-dxe mobile robot.

• Journal of Information Processing Systems
• /
• v.11 no.4
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• Proceedings of the KIEE Conference
• /
• 2004.11b
• /
• pp.258-260
• /
• 2004

This paper analyse a operating characteristics when the Community Energy System (CES) is operated islanding mode. In the near future, CES might be one of major energy supply structures. The basic concept of CES is that it supplies electrical and thermal energy to the local customer loads through the islanded power network separated from the grid. The CES must be supplying local load with stable energy on the islanding mode, analysing necessary to thoroughly the operation feature. In order to show them, in this paper, we model the CES with 2.34 MVA DG and simulate the operating feature on the islanding mode of CES. The simulation results show that, in order to stability operate, the CES need the efficient load management and generation control schemes during the transition periods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.5
• /
• pp.11-17
• /
• 2010

In this parer, face recognition method which can be applied to ITCS (interactive TV control system) is proposed. We extracted ULBP(uniform local binary pattern) histogram feature from infra-red images, and we detected left-right eyes and face region by using SVM classifier. Then, We implemented face recognition system which is using Gabor transform and ULBP histogram feature and applied to personal verification for ITCS.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.1
• /
• pp.31-37
• /
• 2001

Human psychovisual phenomena involved in extracting features is more sensitive in dark regions than in bright regions Therefore, feature extracting operators should be considered local intensities in order to perceive objects analogous to human vision system. Generally, conventional feature extracting operators have some handicaps like an computational complexity or multivariable needs. In this paper a novel feature extracting operator is proposed to overcome these demerits. This operator could be implemented very simply and be proved good performances through experiments applied to synthetic and real images.