• ETRI Journal
• /
• 제34권4호
• /
• pp.572-582
• /
• 2012

The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the local features of a non-square image. The complete set of non-square image features are then represented by the summation of all MDGHMs. We also propose to apply an accumulated MDGHM using multi-order derivatives to obtain distinguishable feature information in the third stage of the SIFT. Finally, we calculate an MDGHM-based magnitude and an MDGHM-based orientation using the accumulated MDGHM. We carry out experiments using the proposed method with six kinds of deformations. The results show that the proposed method can be applied to non-square images without any image truncation and that it significantly outperforms the matching accuracy of other SIFT algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• pp.3972-3988
• /
• 2020

Existing methods always rely on statistical features to extract local words for microblog user geolocation. There are many non-local words in extracted words, which makes geolocation accuracy lower. Considering the statistical and semantic features of local words, this paper proposes a microblog user geolocation method by extracting local words based on word clustering and wrapper feature selection. First, ordinary words without positional indications are initially filtered based on statistical features. Second, a word clustering algorithm based on word vectors is proposed. The remaining semantically similar words are clustered together based on the distance of word vectors with semantic meanings. Next, a wrapper feature selection algorithm based on sequential backward subset search is proposed. The cluster subset with the best geolocation effect is selected. Words in selected cluster subset are extracted as local words. Finally, the Naive Bayes classifier is trained based on local words to geolocate the microblog user. The proposed method is validated based on two different types of microblog data - Twitter and Weibo. The results show that the proposed method outperforms existing two typical methods based on statistical features in terms of accuracy, precision, recall, and F1-score.

• 한국멀티미디어학회논문지
• /
• 제16권5호
• /
• pp.591-600
• /
• 2013

This paper addresses a feature-based robust watermarking scheme for digital images using a local invariant features of SURF (Speeded-Up Robust Feature) descriptor. In general, the feature invariance is exploited to achieve robustness in watermarking schemes, but the leakage of information about hidden watermarks from publicly known locations and sizes of features are not considered carefully in security perspective. We propose embedding and detection methods where the watermark is bound with circular areas and inserted into extracted circular feature regions. These methods enhance the robustness since the circular watermark is inserted into the selected non-overlapping feature regions instead of entire image contents. The evaluation results for repeatability measures of SURF descriptor and robustness measures present the proposed scheme can tolerate various attacks, including signal processing and geometric distortions.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.303-310
• /
• 2007

Named Entity Recognition (NER) is always limited by its lower recall resulting from the asymmetric data distribution where the NONE class dominates the entity classes. This paper presents an approach that exploits non-local information to improve the NER recall. Several kinds of non-local features encoding entity token occurrence, entity boundary and entity class are explored under Conditional Random Fields (CRFs) framework. Experiments on SIGHAN 2006 MSRA (CityU) corpus indicate that non-local features can effectively enhance the recall of the state-of-the-art NER systems. Incorporating the non-local features into the NER systems using local features alone, our best system achieves a 23.56% (25.26%) relative error reduction on the recall and 17.10% (11.36%) relative error reduction on the F1 score; the improved F1 score 89.38% (90.09%) is significantly superior to the best NER system with F1 of 86.51% (89.03%) participated in the closed track.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.402-410
• /
• 2017

For many years, researchers in face description area have been representing and recognizing faces based on different methods that include subspace discriminant analysis, statistical learning and non-statistics based approach etc. But still automatic face recognition remains an interesting but challenging problem. This paper presents a novel and efficient face image representation method based on Optimized Local Ternary Pattern (OLTP) texture features. The face image is divided into several regions from which the OLTP texture feature distributions are extracted and concatenated into a feature vector that can act as face descriptor. The recognition is performed using nearest neighbor classification method with Chi-square distance as a similarity measure. Extensive experimental results on Yale B, ORL and AR face databases show that OLTP consistently performs much better than other well recognized texture models for face recognition.

• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1659-1668
• /
• 2016

Understanding 3D structure of scenes is of a great interest in various vision-related tasks. In this paper, we present a unified approach for estimating depth from a single monocular image. The key idea of our approach is to take advantages both of parametric learning and non-parametric sampling method. Using a parametric convolutional network, our approach learns the relation of various monocular cues, which make a coarse global prediction. We also leverage the local prediction to refine the global prediction. It is practically estimated in a non-parametric framework. The integration of local and global predictions is accomplished by concatenating the feature maps of the global prediction with those from local ones. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively.

• 한국멀티미디어학회논문지
• /
• 제18권10호
• /
• pp.1197-1204
• /
• 2015

Smoke detection plays an important role for the early detection of fire. In this paper, we suggest a newly developed method that generated LBPV(Local Binary Pattern Variance)s as special feature vectors from RGB contrast images can be applied to detect smoke using SVM(Support Vector Machine). The proposed method rearranges mean value of the block from each R, G, B channel and its intensity of the mean value. Additionally, it generates RGB contrast image which indicates each RGB channel’s contrast via smoke’s achromatic color. Uniform LBPV, Rotation-Invariance LBPV, Rotation-Invariance Uniform LBPV are applied to RGB Contrast images so that it could generate feature vector from the form of LBP. It helps to distinguish between smoke and non smoke area through SVM. Experimental results show that true positive detection rate is similar but false positive detection rate has been improved, although the proposed method reduced numbers of feature vector in half comparing with the existing method with LBP and LBPV.

• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1108-1118
• /
• 2019

Non-local means (NLM) algorithm is an effective and successful denoising method, but it is computationally heavy. To deal with this obstacle, we propose a novel NLM algorithm with fuzzy metric (FM-NLM) for image denoising in this paper. A new feature metric of visual features with fuzzy metric is utilized to measure the similarity between image pixels in the presence of Gaussian noise. Similarity measures of luminance and structure information are calculated using a fuzzy metric. A smooth kernel is constructed with the proposed fuzzy metric instead of the Gaussian weighted L2 norm kernel. The fuzzy metric and smooth kernel computationally simplify the NLM algorithm and avoid the filter parameters. Meanwhile, the proposed FM-NLM using visual structure preferably preserves the original undistorted image structures. The performance of the improved method is visually and quantitatively comparable with or better than that of the current state-of-the-art NLM-based denoising algorithms.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.235-236
• /
• 2006

IEEE 802.16 networks support mobile stations (MSs) to access broadband wireless networks while moving at a vehicular speed. However, IEEE 802.16 networks do not provide link layer native multicast capability because of point-to-multipoint connection characteristic. Due to this feature, it is not easy to adopt protocols or applications which need native link layer multicast capability. In order to solve the multicast support problem, we use the built-in LAN emulation feature of IEEE 802.16 which is based on Convergence Sublayer (CS). Our proposed operational procedures support not only the delivery of link local scope multicast packets, but also the delivery of non-link local scope multicast packets such as site local or global scope multicast packets. We also present the method of forming multicast Connection Identifier (CID) which is used to transport IP packets over IEEE 802.16 networks.

• 대한전자공학회논문지SP
• /
• 제45권5호
• /
• pp.103-110
• /
• 2008

산업용 방사선영상으로부터 신뢰할만한 용접부위를 추출하는 것은 용접부의 결함을 검출하기 이전에 수행해야할 선행과제이다. 이 논문은 강판튜브 CR영상으로부터 용접특징 부위의 검출과 추출을 시도한다. 먼저 용접부위와 비용접부위로 구분된 샘플영상 160(개)를 통계 분석하여 두 부류 사이의 차이를 식별한다. 그 후 군집화 파라미터 결정을 위한 패턴분류 작업을 실시한다. 이 파라미터들은 간격, 함수부합정도 및 연속성이다. 관측된 용접영상을 선(線)별로 처리하되 각 선데이터군(群)에 가변 이동창을 적용하여 구역을 선점한다. 각 창을 구성하는 데이터의 직접 및 비용접부위 귀속여부는 국부확률선군집화 방식을 적용하여 분류한다. 순차적 과정을 거쳐 매 단계마다의 경계치 산출에 의해 두 영역 사이의 경계선을 추적하며 그 결과 용접 특징부위를 추출한다. 그리고 CR용접영상 실험을 통해 그 효과를 입증한다.