• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.2981-2996
• /
• 2020

With the increasing amount of splicing images, many detection schemes of splicing images are proposed. In this paper, a splicing detection scheme for color image based on the quaternion discrete cosine transform (QDCT) is proposed. Firstly, the proposed quaternion Markov features are extracted in QDCT domain. Secondly, the proposed quaternion Markov features consist of global and local quaternion Markov, which utilize both magnitude and three phases to extract Markov features by using two different ways. In total, 2916-D features are extracted. Finally, the support vector machine (SVM) is used to detect the splicing images. In our experiments, the accuracy of the proposed scheme reaches 99.16% and 97.52% in CASIA TIDE v1.0 and CASIA TIDE v2.0, respectively, which exceeds that of the existing schemes.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1083-1094
• /
• 2020

Recognizing plant species based on leaf images is challenging because of the large inter-class variation and inter-class similarities among different plant species. The effective extraction of leaf descriptors constitutes the most important problem in plant leaf recognition. In this paper, a multi-scale angular description method is proposed for fast and accurate leaf recognition and retrieval tasks. The proposed method uses a novel scale-generation rule to develop an angular description of leaf contours. It is parameter-free and can capture leaf features from coarse to fine at multiple scales. A fast Fourier transform is used to make the descriptor compact and is effective in matching samples. Both support vector machine and k-nearest neighbors are used to classify leaves. Leaf recognition and retrieval experiments were conducted on three challenging datasets, namely Swedish leaf, Flavia leaf, and ImageCLEF2012 leaf. The results are evaluated with the widely used standard metrics and compared with several state-of-the-art methods. The results and comparisons show that the proposed method not only requires a low computational time, but also achieves good recognition and retrieval accuracies on challenging datasets.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.154-157
• /
• 2011

인간의 동작 인식은 가상 현실 시스템 및 게임 등에 적용할 수 있는 컴퓨터 비전 분야의 요소 기술 중 하나로써, 최근까지 그 연구과 활발히 진행되고 있다. 본 논문에서는 빠르고 정확한 동작 인식을 위해, 실루엣과 모션 특징이 결합된 방법을 제안한다. 제안하는 방법은 전역 특징을 이용한 후보 동작 선정 및 지역 특징을 이용한 검증 2 단계로 구성된다. 전역 특징은 Motion History Image의 Hu 모멘트를 이용해 계산되며, 후보 동작의 선정은 이들의 통계치를 이용해 결정한다. 한정된 후보 동작들 중 입력 동작을 정확히 인식하기 위해, 공간 및 방향성 비닝 기법으로 추출된 광류와 실루엣 특징을 지역 특징으로 이용한다. 최종 인식 결과는 Hu 모멘트 통계치와의 유사도 및 지역 특징의 학습을 통해 생성된 Support Vector Machine의 결과를 고려하여 결정된다. 제안하는 방법의 성능을 평가하기 위해, 실세계에서 사용 빈도가 높으며 동작의 변화가 큰 13 개의 제스처를 선정하여 데이터 셋을 구성하였다. 실험 결과 제안하는 방법의 연산 시간은 50 ms, 인식 정확도는 95%임을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6009-6027
• /
• 2019

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.11
• /
• pp.4153-4169
• /
• 2014

To recognize F5-like (such as F5 and nsF5) steganographic algorithm from multi-class stego images, a recognition algorithm based on the identifiable statistical feature (IDSF) of F5-like steganography is proposed in this paper. First, this paper analyzes the special modification ways of F5-like steganography to image data, as well as the special changes of statistical properties of image data caused by the modifications. And then, by constructing appropriate feature extraction sources, the IDSF of F5-like steganography distinguished from others is extracted. Lastly, based on the extracted IDSFs and combined with the training of SVM (Support Vector Machine) classifier, a recognition algorithm is presented to recognize F5-like stego images from images set consisting of a large number of multi-class stego images. A series of experimental results based on the detection of five types of typical JPEG steganography (namely F5, nsF5, JSteg, Steghide and Outguess) indicate that, the proposed algorithm can distinguish F5-like stego images reliably from multi-class stego images generated by the steganography mentioned above. Furthermore, even if the types of some detected stego images are unknown, the proposed algorithm can still recognize F5-like stego images correctly with high accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5643-5656
• /
• 2016

The detection accuracy of steganalysis depends on many factors, including the embedding algorithm, the payload size, the steganalysis feature space and the properties of the cover source. In practice, the cover source mismatch (CSM) problem has been recognized as the single most important factor negatively affecting the performance. To address this problem, we propose a new framework for blind, universal steganalysis which uses traditional steganalyst features. Firstly, cover images with the same statistical properties are searched from a reference image database as aided samples. The test image and its aided samples form a whole test set. Then, by assuming that most of the aided samples are innocent, we conduct outlier detection on the test set to judge the test image as cover or stego. In this way, the framework has removed the need for training. Hence, it does not suffer from cover source mismatch. Because it performs anomaly detection rather than classification, this method is totally unsupervised. The results in our study show that this framework works superior than one-class support vector machine and the outlier detector without considering the image retrieval process.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2007.04a
• /
• pp.101-104
• /
• 2007

As the proportion of underground construction increases, the impact of inappropriate selection of a underground construction method for a construction size increases. The purpose of this study is to develop an objective way of selecting an excavation method. There have been several attempts to achieve the same goal using various data mining methods such as the artificial neural network, the support vector machine, and the case-based reasoning. However, they focused only on the selection of a retaining wall construction method out of six types of retaining walls. When we categorized an underground construction work into four groups and added more number of independent variables (i.e., more number of construction methods), the predictability decreased. As an alternative, we developed a decision tree by analyzing 25 earthwork cases with detailed information. We implemented the developed decision tree as a computer-supported program called Dr. underground and are still in the process of validating and revising the decision tree. This study is still in a preliminary stage and will be improved by collecting and analyzing more cases.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.8 no.3
• /
• pp.145-150
• /
• 2014

In this paper, we propose a novel scheme to improve the performance of a voice activity detection(VAD) which is based on the deep belief networks(DBN) with the likelihood ratio(LR). The proposed algorithm applies the DBN learning method which is trained in order to minimize the probability of detection error instead of the conventional decision rule using geometric mean. Experimental results show that the proposed algorithm yields better results compared to the conventional VAD algorithm in various noise environments.

• Nuclear Engineering and Technology
• /
• v.46 no.6
• /
• pp.725-736
• /
• 2014

It is very important to detect and identify small anomalies and component failures for the safe operation of complex and large-scale artifacts such as nuclear power plants. Each diagnostic technique has its own advantages and limitations. These facts inspire us not only to enhance the capability of diagnostic techniques but also to integrate the results of diagnostic subsystems in order to obtain more accurate diagnostic results. The article describes the outline of four diagnostic techniques developed for the condition monitoring of the fast breeder reactor "Monju". The techniques are (1) estimation technique of important state variables based on a physical model of the component, (2) a state identification technique by non-linear discrimination function applying SVM (Support Vector Machine), (3) a diagnostic technique applying WT (Wavelet Transformation) to detect changes in the characteristics of measurement signals, and (4) a state identification technique effectively using past cases. In addition, a hybrid diagnostic system in which a final diagnostic result is given by integrating the results from subsystems is introduced, where two sets of values called confidence values and trust values are used. A technique to determine the trust value is investigated under the condition that the confidence value is determined by each subsystem.

• Journal of Sasang Constitutional Medicine
• /
• v.32 no.2
• /
• pp.10-21
• /
• 2020

Objectives Genome-wide association studies(GWAS) is a useful method to identify genetic associations for various phenotypes. The purpose of this study was to develop predictive models for Sasang constitution types using genetic factors. Methods The genotypes of the 1,999 subjects was performed using Axiom Precision Medicine Research Array (PMRA) by Life Technologies. All participants were prescribed Sasang Constitution-specific herbal remedies for the treatment, and showed improvement of original symptoms as confirmed by Korean medicine doctor. The genotypes were imputed by using the IMPUTE program. Association analysis was conducted using a logistic regression model to discover Single Nucleotide Polymorphism (SNP), adjusting for age, sex, and BMI. Results & Conclusions We developed models to predict Korean medicine constitution types using identified genectic factors and sex, age, BMI using Random Forest (RF), Support Vector Machine (SVM), and Neural Network (NN). Each maximum Area Under the Curve (AUC) of Teaeum, Soeum, Soyang is 0.894, 0.868, 0.767, respectively. Each AUC of the models increased by 6~17% more than that of models except for genetic factors. By developing the predictive models, we confirmed usefulness of genetic factors related with types. It demonstrates a mechanism for more accurate prediction through genetic factors related with type.