• Journal of Digital Contents Society
• /
• v.13 no.2
• /
• pp.189-195
• /
• 2012

In this paper, face detection method in NIR(Near-InfraRed) images for human recognition is proposed. Edge histogram based on edge intensity and its direction, has been used to detect effectively faces on NIR image. The edge histogram descripts and discriminates face effectively because it is strong in environment of lighting change. SVM(Support Vector Machine) has been used as a classifier to detect face and the proposed method showed better performance with smaller features than in ULBP(Uniform Local Binary Pattern) based method.

• 한국전산유체공학회:학술대회논문집
• /
• 1999.05a
• /
• pp.113-123
• /
• 1999

In this study a pure vector potential method (PVPM) for a three dimensional, unsteady, incompressible flow is proposed. A simplified version for a two dimensional problem is described in detail, and a method to prescribe appropriate boundary conditions is also presented. The resulting numerical algorithm is applied to the cavity flow driven by an impulsively started wall and also to the Stokes' first problem. Some important unsteady/steady features are captured for these two flows, and quantitative agreements of flow variables with available reference database are good.

• ETRI Journal
• /
• v.29 no.5
• /
• pp.700-702
• /
• 2007

We present a relevance feedback approach based on multi-class support vector machine (SVM) learning and cluster-merging which can significantly improve the retrieval performance in region-based image retrieval. Semantically relevant images may exhibit various visual characteristics and may be scattered in several classes in the feature space due to the semantic gap between low-level features and high-level semantics in the user's mind. To find the semantic classes through relevance feedback, the proposed method reduces the burden of completely re-clustering the classes at iterations and classifies multiple classes. Experimental results show that the proposed method is more effective and efficient than the two-class SVM and multi-class relevance feedback methods.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.2
• /
• pp.236-243
• /
• 2016

This paper presents a threat list acquisition method in an engagement area using the support vector machines (SVM). The proposed method consists of track creation, track estimation, track feature extraction, and threat list classification. To classify the threat track robustly, dynamic track estimation and pattern recognition algorithms are used. Dynamic tracks are estimated accurately by approximating a track movement using position, velocity and time. After track estimation, track features are extracted from the track information, and used to classify threat list. Experimental results showed that the threat list acquisition method in the engagement area achieved about 95 % accuracy rate for whole test tracks when using the SVM classifier. In case of improving the real-time process through further studies, it can be expected to apply the fire control systems.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.458-460
• /
• 2000

본 논문에서는 유전자 알고리즘(GA)과 Support Vector Machine(SVM)을 결합하여 사용한 얼굴 인식 시스템을 제안한다. 기존의 SVM을 이용한 얼굴 인식 연구에서는 얼굴 전체 영상을 SVM의 입력벡터로 사용하는데 반해, 본 연구에서는 GA를 이용하여 얼굴 영상 중에서 개인별로 식별 능력이 우수한 특징들만을 선택하여 이를 SVM의 입력벡터로 사용한다. 조명, 표정, 안경 착용 등 다양한 변화가 있는 Yale 얼굴 데이터베이스를 사용하여 실험한 결과, 얼굴 전체 영상을 사용한 경우보다 더 좋은 인식률을 보였다. 또한 제안된 방법에 의한 얼굴 인식 시스템은 각 개인별로 식별력이 우수한 특징들만을 저장하므로, 얼굴인식 시스템을 구성하기 위해 저장될 정보의 양이 현저하게 감소하게 된다.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.93-102
• /
• 2022

Dependency parsing is a decision problem of the syntactic relation between words in a sentence. Recently, deep learning models are used for dependency parsing based on the word representations in a continuous vector space. However, it causes a mislabeled tagging problem for the proper nouns that rarely appear in the training corpus because it is difficult to express out-of-vocabulary (OOV) words in a continuous vector space. To solve the OOV problem in dependency parsing, we explored the proper noun embedding method according to the embedding unit. Before representing words in a continuous vector space, we replace the proper nouns with a special token and train them for the contextual features by using the multi-layer bidirectional LSTM. Two models of the syllable-based and morpheme-based unit are proposed for proper noun embedding and the performance of the dependency parsing is more improved in the ensemble model than each syllable and morpheme embedding model. The experimental results showed that our ensemble model improved 1.69%p in UAS and 2.17%p in LAS than the same arc-eager approach-based Malt parser.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.160-167
• /
• 2014

This paper presents a spliced color image detection method using Benford' Law and color difference. For a suspicious image, after color conversion, the discrete wavelet transform and the discrete cosine transform are performed. We extract the difference between the ideal Benford distribution and the empirical Benford distribution of the suspicious image as features. The difference between Benford distributions for each color component were also used as features. Our method shows superior splicing detection performance using only 13 features. After training the extracted feature vector using SVM classifier, we determine whether the presence of the image splicing forgery. Experimental results show that the proposed method outperforms the existing methods with smaller number of features in terms of splicing detection accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.17-24
• /
• 2014

This paper proposes a fault detection method for low-speed rolling element bearings of an induction motor using acoustic emission signals and histogram modeling. The proposed method performs envelop modeling of the histogram of normalized fault signals. It then extracts and selects significant features of each fault using partial autocorrelation coefficients and distance evaluation technique, respectively. Finally, using the extracted features as inputs, the support vector regression (SVR) classifies bearing's inner, outer, and roller faults. To obtain optimal classification performance, we evaluate the proposed method with varying an adjustable parameter of the Gaussian radial basis function of SVR from 0.01 to 1.0 and the number of features from 2 to 150. Experimental results show that the proposed fault identification method using 0.64-0.65 of the adjustable parameter and 75 features achieves 91% in classification performance and outperforms conventional fault diagnosis methods as well.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1395-1405
• /
• 2017

In this paper, we analyses heart beat data to identify subjects stress state (binary) using heart rate variability (HRV) features extracted from heart beat data of the subjects and implement supervised machine learning techniques to create the mental stress classifier. There are four steps need to be done: data acquisition, data processing (HRV analysis), features selection, and machine learning, before doing performance measurement. There are 56 features generated from the HRV Analysis module with several of them are selected (using own algorithm) after computing the Pearson Correlation Matrix (p-values). The results of the list of selected features compared with all features data are compared by its model error after training using several machine learning techniques: support vector machine, decision tree, and discriminant analysis. SVM model and decision tree model with using selected features shows close results compared to using all recording by only 1% difference. Meanwhile, the discriminant analysis differs about 5%. All the machine learning method used in this works have 90% maximum average accuracy.