• Journal of the Korea Society of Computer and Information
• /
• v.18 no.6
• /
• pp.21-28
• /
• 2013

This paper proposes an effective fire detection approach that includes the following multiple heterogeneous algorithms: moving region detection using grey level histograms, color segmentation using fuzzy c-means clustering (FCM), feature extraction using a grey level co-occurrence matrix (GLCM), and fire classification using support vector machine (SVM). The proposed approach determines the optimal threshold values based on grey level histograms in order to detect moving regions, and then performs color segmentation in the CIE LAB color space by applying the FCM. These steps help to specify candidate regions of fire. We then extract features of fire using the GLCM and these features are used as inputs of SVM to classify fire or non-fire. We evaluate the proposed approach by comparing it with two state-of-the-art fire detection algorithms in terms of the fire detection rate (or percentages of true positive, PTP) and the false fire detection rate (or percentages of true negative, PTN). Experimental results indicated that the proposed approach outperformed conventional fire detection algorithms by yielding 97.94% for PTP and 4.63% for PTN, respectively.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.7-16
• /
• 2009

Some clustering algorithms have a problem that an image is over-segmented since both the spatial information between the segmented regions is not considered and the number of the clusters is defined in advance. Therefore, they are difficult to be applied to the applicable fields. This paper proposes the new post-processing methods, a reclassification of the inhomogeneous clusters and a region merging using Baysian algorithm, that improve the segmentation results of the clustering algorithms. The inhomogeneous cluster is firstly selected based on variance and between-class distance and it is then reclassified into the other clusters in the reclassification step. This reclassification is repeated until the optimal number determined by the minimum average within-class distance. And the similar regions are merged using Baysian algorithm based on Kullbeck-Leibler distance between the adjacent regions. So we can effectively solve the over-segmentation problem and the result can be applied to the applicable fields. Finally, we design a classification system for the segmented regions to validate the proposed method. The segmented regions are classified by SVM(Support Vector Machine) using the principal colors and the texture information of the segmented regions. In experiment, the proposed method showed the validity for various real-images and was effectively applied to the designed classification system.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• The Korean Journal of Applied Statistics
• /
• v.37 no.1
• /
• pp.73-86
• /
• 2024

A radial chart of Excel is very useful graphical method in delivering information for numerical data. However, it is not easy to discriminate or classify many individuals. In this case, after shaping each individual of a radial chart, we need to apply shape analysis. For a radial chart, since landmarks for shaping are formed as many as the number of variables representing the characteristics of the object, we consider a shape that connects them to a line. If the shape becomes complicated due to the large number of variables, it is difficult to easily grasp even if visualized using a radial chart. Principal component analysis (PCA) is performed on variables to create a visually effective shape. The classification table and classification rate are checked by applying the techniques of traditional discriminant analysis, support vector machine (SVM), and artificial neural network (ANN), before and after principal component analysis. In addition, the difference in discrimination between the two coordinates of generalized procrustes analysis (GPA) coordinates and Bookstein coordinates is compared. Bookstein coordinates are obtained by converting the position, rotation, and scale of the shape around the base landmarks, and show higher rate than GPA coordinates for the classification rate.

• The Journal of the Korea Contents Association
• /
• v.9 no.4
• /
• pp.1-11
• /
• 2009

To classifying and filtering of adult images, in recent the computer vision techniques are actively investigated because rapidly increase for the amount of adult images accessible on the Internet. In this paper, we investigate and develop the tool filtering of adult images using skin color model. The tool is consisting of two steps. In the first step, we use a skin color classifier to extract skin color regions from an image. In the nest step, we use a region feature classifier to determine whether an image is an adult image or not an adult image depending on extracted skin color regions. Using histogram color model, a skin color classifier is trained for RGB color values of adult images and not adult images. Using SVM, a region feature classifier is trained for skin color ratio on 29 regions of adult images. Experimental results show that suggested classifier achieve a detection rate of 92.80% with 6.73% false positives.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.6
• /
• pp.1413-1420
• /
• 2015

On the design phase of small size bridge, owing to the lack of related guidelines or standards to determine a superstructure type of bridge, many designers tend to select the type depending on expert's experience and knowledge. Moreover, recently, as types of bridge superstructure become diverse and more conditions need to be considered in the project, the decision makes process become complex. This research covered the selection of a superstructure type of a middle or small size bridge with span length of about 50m, which frequently built for national roadway, selecting type of bridge superstructure more systematic way rather than the existing ways to compare construction methods or to depend on expert's experiences. This study proposes to build a bridge superstructure type selection model using one of the techniques of artificial intelligence techniques SVM by applicability of the model examined through the verification of the actual case.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.1
• /
• pp.25-44
• /
• 2010

With the increasing popularity of mobile devices, it has become necessary to protect private information and content in these devices. Face recognition has been favored over conventional passwords or security keys, because it can be easily implemented using a built-in camera, while providing user convenience. However, because mobile devices can be used both indoors and outdoors, there can be many illumination changes, which can reduce the accuracy of face recognition. Therefore, we propose a new face recognition method on a mobile device robust to illumination variations. This research makes the following four original contributions. First, we compared the performance of face recognition with illumination variations on mobile devices for several illumination normalization procedures suitable for mobile devices with low processing power. These include the Retinex filter, histogram equalization and histogram stretching. Second, we compared the performance for global and local methods of face recognition such as PCA (Principal Component Analysis), LNMF (Local Non-negative Matrix Factorization) and LBP (Local Binary Pattern) using an integer-based kernel suitable for mobile devices having low processing power. Third, the characteristics of each method according to the illumination va iations are analyzed. Fourth, we use two matching scores for several methods of illumination normalization, Retinex and histogram stretching, which show the best and $2^{nd}$ best performances, respectively. These are used as the inputs of an SVM (Support Vector Machine) classifier, which can increase the accuracy of face recognition. Experimental results with two databases (data collected by a mobile device and the AR database) showed that the accuracy of face recognition achieved by the proposed method was superior to that of other methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.12
• /
• pp.5089-5096
• /
• 2010

Text categorization is one of important features in information searching system which classifies documents according to some criteria. The general method of categorization performs the classification of the target documents by eliciting important index words and providing the weight on them. Therefore, the effectiveness of algorithm is so important since performance and correctness of text categorization totally depends on such algorithm. In this paper, an enhanced method for text categorization by improving word weighting technique is introduced. A method called Okapi BM25 has been proved its effectiveness from some information retrieval engines. We applied Okapi BM25 and showed its good performance in the categorization. Various other words weights methods are compared: TF-IDF, TF-ICF and TF-ISF. The target documents used for this experiment is Reuter-21578, and SVM and KNN algorithms are used. Finally, modified Okapi BM25 shows the most excellent performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.10
• /
• pp.3378-3393
• /
• 2014

We have witnessed the rapid development of information technology in recent years. One of the key phenomena is the fast, near-exponential increase of data. Consequently, most of the traditional data classification methods fail to meet the dynamic and real-time demands of today's data processing and analyzing needs--especially for continuous data streams. This paper proposes an improved incremental learning algorithm for a large-scale data stream, which is based on SVM (Support Vector Machine) and is named DS-IILS. The DS-IILS takes the load condition of the entire system and the node performance into consideration to improve efficiency. The threshold of the distance to the optimal separating hyperplane is given in the DS-IILS algorithm. The samples of the history sample set and the incremental sample set that are within the scope of the threshold are all reserved. These reserved samples are treated as the training sample set. To design a more accurate classifier, the effects of the data volumes of the history sample set and the incremental sample set are handled by weighted processing. Finally, the algorithm is implemented in a cloud computing system and is applied to study user behaviors. The results of the experiment are provided and compared with other incremental learning algorithms. The results show that the DS-IILS can improve training efficiency and guarantee relatively high classification accuracy at the same time, which is consistent with the theoretical analysis.

• The Journal of the Korea Contents Association
• /
• v.10 no.8
• /
• pp.11-17
• /
• 2010

In this paper, we propose HMM-based upper-body gesture. First, to recognize gesture of space, division about pose that is composing gesture once should be put priority. In order to divide poses which using interface, we used two IR cameras established on front side and side. So we can divide and acquire in front side pose and side pose about one pose in each IR camera. We divided the acquired IR pose image using SVM's non-linear RBF kernel function. If we use RBF kernel, we can divide misclassification between non-linear classification poses. Like this, sequences of divided poses is recognized by gesture using HMM's state transition matrix. The recognized gesture can apply to existent application to do mapping to OS Value.