• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.6
• /
• pp.806-813
• /
• 2010

Human facial expression shows human's emotion most exactly, so it can be used as the most efficient tool for delivering human's intention to computer. For fast and exact recognition of human's facial expression on a 2D image, this paper proposes a new method which integrates an Discrete Adaboost classification algorithm and a neural network based recognition algorithm. In the first step, Adaboost algorithm finds the position and size of a face in the input image. Second, input detected face image into 5 Adaboost strong classifiers which have been trained for each facial expressions. Finally, neural network based recognition algorithm which has been trained with the outputs of Adaboost strong classifiers determines final facial expression result. The proposed algorithm guarantees the realtime and enhanced accuracy by utilizing fastness and accuracy of Adaboost classification algorithm and reliability of neural network based recognition algorithm. In this paper, the proposed algorithm recognizes five facial expressions such as neutral, happiness, sadness, anger and surprise and achieves 86~95% of accuracy depending on the expression types in real time.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.10a
• /
• pp.303-310
• /
• 2002

Overbreak occurred inevitably in a tunnel excavation, Is the main factor for increasing cost and time in tunnel projects. Furthermore the damage to the remained rock mass related to the overbreak can give rise to a serious safety problem in tunnels. As a rule of thumb, causes for the overbreak are inaccuracy in drilling, the wrong design of blasting and selection of explosives, and heterogeneity in rock mass. Specially, the geological features of the rock mass around periphery of an excavation are very important factors, so a lot of researches have been conducted to describe these phenomena. But the quantitative geological classification of the rock mass for the overbreak and the method for decreasing the amount of the overbreak have not been established. Besides, the technical improvement of the charge method is requested as explosives for the smooth blasting have not functioned efficiently. In this study, the working face around periphery of an excavation has been continuously sectionalized to 5∼6 parts, and the new Blastability Index for the overbreak based on 6 factors of RMD(Rock Mass Description), UCS(Uniaxial Compressive Strength) JPS(Joint Plane Spacing), JPO(Joint Plane Orientation), JPA(Joint Plane Aperture) and FM(Filling Material) is proposed to classify sections of the working face. On the basis of this classification, the distance between contour holes and the charging density are determined to minimize the overbreak. For controlling the charging density and improving the function of explosives, the New Deck Charge(N.D.C) method utilizing the deck charge method and detonation transmission in hole has been developed.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.3
• /
• pp.25-35
• /
• 2014

This paper proposes a method of boosting-based classification for the purpose of real-time face detection. The proposed method uses depth images to ensure strong performance of face detection in response to changes in lighting and face size, and uses the depth difference feature to conduct learning and recognition through the I-MCTBoost classifier. I-MCTBoost performs recognition by connecting the strong classifiers that are constituted from weak classifiers. The learning process for the weak classifiers is as follows: first, depth difference features are generated, and eight of these features are combined to form the weak classifier, and each feature is expressed as a binary bit. Strong classifiers undergo learning through the process of repeatedly selecting a specified number of weak classifiers, and become capable of strong classification through a learning process in which the weight of the learning samples are renewed and learning data is added. This paper explains depth difference features and proposes a learning method for the weak classifiers and strong classifiers of I-MCTBoost. Lastly, the paper presents comparisons of the proposed classifiers and the classifiers using conventional MCT through qualitative and quantitative analyses to establish the feasibility and efficiency of the proposed classifiers.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.3
• /
• pp.239-248
• /
• 2020

Exact rock classification helps suitable support patterns to be installed. Face mapping is usually conducted to classify the rock mass using RMR (Rock Mass Ration) or Q values. There have been several attempts to predict the grade of rock mass using mechanical data of jumbo drills or probe drills and photographs of excavation surfaces by using deep learning. However, they took long time, or had a limitation that it is impossible to grasp the rock grade in ahead of the tunnel surface. In this study, a method to predict the Q value ahead of excavation surface is developed using recurrent neural network (RNN) technique and it is compared with the Q values from face mapping for verification. Among Q values from over 4,600 tunnel faces, 70% of data was used for learning, and the rests were used for verification. Repeated learnings were performed in different number of learning and number of previous excavation surfaces utilized for learning. The coincidence between the predicted and actual Q values was compared with the root mean square error (RMSE). RMSE value from 600 times repeated learning with 2 prior excavation faces gives a lowest values. The results from this study can vary with the input data sets, the results can help to understand how the past ground conditions affect the future ground conditions and to predict the Q value ahead of the tunnel excavation face.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.539-544
• /
• 2023

The subject of this study is the Maae Buddha statue in granodiorite of the Mesozoic Cretaceous period, which is concerned about stability as a standing stone cultural property located in ◯◯-dong, Gyeongsangbuk-do. For stability analysis, three-dimensional face mapping, geological properties of joints, three-dimensional scanning, ultrasonic velocity, polarization microscopy, electron microscopy analysis and XRD analysis were performed. In addition, the safety factor of the Maaebul was calculated by analyzing the damage status investigation, stereographic projection analysis, rock classification, and limit equilibrium analysis. The types and scales of damage and possible collapse by section depend on the degree of weathering of the rock and the orientation and characteristics of the joints, but wedge-failure and toppling-failure are expected to be small-scale. The safety factor of Maaebul in dry and wet conditions is less than 1.2, so stability is concerned. The types of damage were mainly observed, such as exfoliation, cracking, granular decomposition, and vegetation growth. The Maaebul rock is granodiorite, and the surface discoloration materials are K, Fe, and Mg. The 4 sets of joints are developed, J1 is tensile joint and the others are shear joint. The uniaxial compressive strength estimated by ultrasonic exploration is 514kgf/cm2, which corresponds to most soft rocks and some weathered rocks. Rock classification(RMR) is estimated to be grade 5, very poor rock mass. These technique along with the existing methods of safety diagnosis of cultural properties are expected to be a reasonable tool for objective interpretation and stability review of stone cultural properties.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.3
• /
• pp.203-216
• /
• 2003

In this paper a new feature extraction and target classification method is proposed for the recognition part of FLIR(Forwar Looking Infrared)-image-based ATR system. Proposed feature extraction method is "cluster(=set of classes)-based"version of previous fisherfaces method that is known by its robustness to illumination changes in face recognition. Expecially introduced class clustering and cluster-based projection method maximizes the performance of fisherfaces method. Proposed target image classification method is based on the mixture of experts model which consists of RBF-type experts and MLP-type gating networks. Mixture of experts model is well-suited with ATR system because it should recognizee various targets in complexed feature space by variously mixed conditions. In proposed classification method, one expert takes charge of one cluster and the separated structure with experts reduces the complexity of feature space and achieves more accurate local discrimination between classes. Proposed feature extraction and classification method showed distinguished performances in recognition test with customized. FLIR-vehicle-image database. Expecially robustness to pixelwise sensor noise and un-wanted intensity variations was verified by simulation.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.173-180
• /
• 2022

In the naked eye observation, the health of livestock can be controlled by the range of activity, temperature, pulse, cough, snot, eye excrement, ears and feces. In order to confirm the health of livestock, this paper uses calf face image data to classify the health status by image shape, color and texture. A series of images that have been processed in advance and can judge the health status of calves were used in the study, including 177 images of normal calves and 130 images of abnormal calves. We used GLCM calculation and Convolutional Neural Networks to extract 6 texture attributes of GLCM from the dataset containing the health status of calves by detecting the image of calves and learning the composite image of Convolutional Neural Networks. In the research, the classification ability of GLCM-CNN shows a classification rate of 91.3%, and the subsequent research will be further applied to the texture attributes of GLCM. It is hoped that this study can help us master the health status of livestock that cannot be observed by the naked eye.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• 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 Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2388-2398
• /
• 2017

In this study, we propose a robust face recognition system to pose variations based on automatic pose estimation. Radial basis function neural network is applied as one of the functional components of the overall face recognition system. The proposed system consists of preprocessing and recognition modules to provide a solution to pose variation and high-dimensional pattern recognition problems. In the preprocessing part, principal component analysis (PCA) and 2-dimensional 2-directional PCA ($(2D)^2$ PCA) are applied. These functional modules are useful in reducing dimensionality of the feature space. The proposed RBFNNs architecture consists of three functional modules such as condition, conclusion and inference phase realized in terms of fuzzy "if-then" rules. In the condition phase of fuzzy rules, the input space is partitioned with the use of fuzzy clustering realized by the Fuzzy C-Means (FCM) algorithm. In conclusion phase of rules, the connections (weights) are realized through four types of polynomials such as constant, linear, quadratic and modified quadratic. The coefficients of the RBFNNs model are obtained by fuzzy inference method constituting the inference phase of fuzzy rules. The essential design parameters (such as the number of nodes, and fuzzification coefficient) of the networks are optimized with the aid of Particle Swarm Optimization (PSO). Experimental results completed on standard face database -Honda/UCSD, Cambridge Head pose, and IC&CI databases demonstrate the effectiveness and efficiency of face recognition system compared with other studies.