• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.79-89
• /
• 2004

Since the amount of E-mail messages has increased , we need a new technique for efficient e-mail classification. E-mail classifications are grouped into two classes: binary classification, multi-classification. The current binary classification methods are mostly spm mail classification methods which are based on rule driven, bayesian, SVM, etc. The current multi- classification methods are based on clustering which groups e-mails by similarity. In this paper, we propose a novel method for e-mail classification. It combines the automatic category generation method based on the vector model and the dynamic category hierarchy construction method. This method can multi-classify e-mail automatically and manage a large amount of e-mail efficiently. In addition, this method increases the search accuracy by dynamic reclassification of e-mails.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.67-73
• /
• 2010

In this paper, a new face detection method that is more accurate than the conventional methods is proposed. This method utilizes a hybrid of Hausdorff distance based on the geometric similarity between the two sets of points and the LBP distance based on the distribution of local micro texture of an image. The parameters for normalization and the optimal blending factor of the two different metrics were calculated from training sample images. Popularly used face database was used to show that the proposed method is more effective and robust to the variation of the pose, illumination, and back ground than the methods based on the Hausdorff distance or LBP distance. In the particular case, the average error distance between the detected and the true face location was reduced to 47.9% of the result of LBP method, and 22.8% of the result of Hausdorff method.

• Journal of Korea Multimedia Society
• /
• v.9 no.11
• /
• pp.1465-1473
• /
• 2006

In this paper, we present an approach for facial expression recognition using Active Shape Models(ASM) and a state-based model in image sequences. Given an image frame, we use ASM to obtain the shape parameter vector of the model while we locate facial feature points. Then, we can obtain the shape parameter vector set for all the frames of an image sequence. This vector set is converted into a state vector which is one of the three states by the state-based model. In the classification step, we use the k-NN with the proposed similarity measure that is motivated on the observation that the variation-regions of an expression sequence are different from those of other expression sequences. In the experiment with the public database KCFD, we demonstrate that the proposed measure slightly outperforms the binary measure in which the recognition performance of the k-NN with the proposed measure and the existing binary measure show 89.1% and 86.2% respectively when k is 1.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.692-702
• /
• 2017

Face detection using the LBP based feature descriptor has issues in that it can not represent spatial information between facial shape and facial components such as eyes, nose and mouth. To address these issues, in previous research, a facial image was divided into a number of square sub-regions. However, since the sub-regions are divided into different numbers and sizes, the division criteria of the sub-region suitable for the database used in the experiment is ambiguous, the dimension of the LBP histogram increases in proportion to the number of sub-regions and as the number of sub-regions increases, the sensitivity to facial orientation rotation increases significantly. In this paper, we present a novel facial region segmentation method that can solve in-plane rotation issues associated with LBP based feature descriptors and the number of dimensions of feature descriptors. As a result, the proposed method showed detection accuracy of 99.0278% from a single facial image rotated in orientation.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.5
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1013-1021
• /
• 2020

Malware Authorship Attribution is a research field for identifying malware by comparing the author characteristics of unknown malware with the characteristics of known malware authors. The authorship attribution method using binaries has the advantage that it is easy to collect and analyze targeted malicious codes, but the scope of using features is limited compared to the method using source code. This limitation has the disadvantage that accuracy decreases for a large number of authors. This study proposes a method of 'Defining semantic features from binaries' and 'Defining allowable ranges for redundant features using the concept of survival network' to complement the limitations in the identification of binary authors. The proposed method defines Opcode-based graph features from binary information, and defines the allowable range for selecting unique features for each author using the concept of a survival network. Through this, it was possible to define the feature definition and feature selection method for each author as a single technology, and through the experiment, it was confirmed that it was possible to derive the same level of accuracy as the source code-based analysis with an improvement of 5.0% accuracy compared to the previous study.

• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.134-142
• /
• 2006

In this paper, we investigate a Hausdorff distance, which is used for the measurement of image similarity, to see whether it is also effective for document retrieval. The proposed method uses a local crowdedness and a Hausdorff distance to locate text images by determining whether a pair of images scanned at different time comes from the same text or not. To reduce the processing time, which is one of the disadvantages of a Hausdorff distance algorithm, we adopt a local crowdedness for feature point extraction. We apply the proposed method to 190 pairs of the same class and 190 pairs of the different class collected from postal envelop images. The results show that the modified Hausdorff distance proposed in this paper performed well in locating the tort region and calculating the degree of similarity between two images. An improvement of accuracy by 2.7% and 9.0% has been obtained, compared to a binary correlation method and the original Hausdorff distance method, respectively.

• Journal of Computing Science and Engineering
• /
• v.6 no.1
• /
• pp.1-11
• /
• 2012

Computed tomography (CT) images are widely used for the analysis of the temporal evaluation or monitoring of the progression of a disease. The follow-up examinations of CT scan images of the same patient require a 3D registration technique. In this paper, an automatic and robust registration is proposed for the rigid registration of 3D CT images. The proposed method involves two steps. Firstly, the two CT volumes are aligned based on their principal axes, and then, the alignment from the previous step is refined by the optimization of the similarity score of the image's voxel. Normalized cross correlation (NCC) is used as a similarity metric and a downhill simplex method is employed to find out the optimal score. The performance of the algorithm is evaluated on phantom images and knee synthetic CT images. By the extraction of the initial transformation parameters with principal axis of the binary volumes, the searching space to find out the parameters is reduced in the optimization step. Thus, the overall registration time is algorithmically decreased without the deterioration of the accuracy. The preliminary experimental results of the study demonstrate that the proposed method can be applied to rigid registration problems of real patient images.

• Journal of Software Assessment and Valuation
• /
• v.16 no.1
• /
• pp.37-44
• /
• 2020

The similarity of the software is extracted by the verification of comparing with the source code. The source code is the intellectual copyright of the developer written in the programming language. And the source code written in text format contains the contents of the developer's expertise and ideas. The verification for judging the illegal use of software copyright is performed by comparing the structure and contents of files with the source code of the original and the illegal copy. However, there is hard to do the one-to-one comparison in practice. Cause the suspected source code do not submitted Intentionally or unconsciously. It is now increasing practically. In this case, the comparative evaluation with execution code should be performed, and indirect methods such as reverse assembling method, reverse engineering technique, and sequence analysis of function execution are applied. In this paper, we analyzed the effectiveness of indirect comparison results by practical evaluation . It also proposes a method to utilize to the system and executable code files as a verification results.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.125-134
• /
• 2004

This paper proposes a method for recognition of traffic signs using wavelet transform and shape information from the segmented traffic sign regions. It first segments traffic sign candidate regions by connected component algorithm from binary images, obtained by utilizing the RGB color ratio of each pixel in the image, and then extracts actual traffic sign regions based on their symmetries on X- and Y-axes. In the recognition stage, it utilizes shape information including moment edge correlogram and the number of crossings which concentric circular patterns from region center intersects with frequency information extracted by wavelet transform It finally performs recognition by measuring similarity with the templates in the database. The experimental results show the validity of the proposed method from geometric transformations and environmental factors.