• Journal of Information Processing Systems
• /
• 제15권6호
• /
• pp.1449-1461
• /
• 2019

Face sketch synthesis plays an important role in public security and digital entertainment. In this paper, we present a novel face sketch synthesis method via local similarity and nonlocal similarity regularization terms. The local similarity can overcome the technological bottlenecks of the patch representation scheme in traditional learning-based methods. It improves the quality of synthesized sketches by penalizing the dissimilar training patches (thus have very small weights or are discarded). In addition, taking the redundancy of image patches into account, a global nonlocal similarity regularization is employed to restrain the generation of the noise and maintain primitive facial features during the synthesized process. More robust synthesized results can be obtained. Extensive experiments on the public databases validate the generality, effectiveness, and robustness of the proposed algorithm.

• ETRI Journal
• /
• 제44권5호
• /
• pp.769-779
• /
• 2022

Spectral clustering has become a typical and efficient clustering method used in a variety of applications. The critical step of spectral clustering is the similarity measurement, which largely determines the performance of the spectral clustering method. In this paper, we propose a novel spectral clustering algorithm based on the local similarity measure of shared neighbors. This similarity measurement exploits the local density information between data points based on the weight of the shared neighbors in a directed k-nearest neighbor graph with only one parameter k, that is, the number of nearest neighbors. Numerical experiments on synthetic and real-world datasets demonstrate that our proposed algorithm outperforms other existing spectral clustering algorithms in terms of the clustering performance measured via the normalized mutual information, clustering accuracy, and F-measure. As an example, the proposed method can provide an improvement of 15.82% in the clustering performance for the Soybean dataset.

• 한국정보과학회논문지:시스템및이론
• /
• 제34권5_6호
• /
• pp.187-194
• /
• 2007

Local alignment 알고리즘은 두 문자열을 비교하여 크기가 l, 유사도 점수가 s인 부분 문자열쌍을 찾는다. 크기가 충분히 크고 유사도 점수도 높은 부분 문자열 쌍을 찾기 위해 단위 길이당 유사도 점수 s/l을 최대화하는 정규화 방법이 제안되어있다. 본 논문에서는 증가함수 f, g를 도입하여 f(s)/g(l)을 최대화하는, 함수에 의한 정규화 방법을 제시한다. 여기서 함수 f, g는 DNA 서열을 비교하는 실험을 통해 정한다. 이러한 실험에서 함수에 의한 정규화 방법이 좋은 local alignment를 찾는다. 또한 유사도 점수의 기준으로 longest common subsequence를 채택한 경우, 기존의 정규화 알고리즘을 이용하면 별다른 시간 손실 없이 함수에 의해 정규화된 점수 f(s)/g(l)을 최대화 할 수 있음을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권11호
• /
• pp.4502-4518
• /
• 2015

Fisher linear discriminant analysis (LDA) is one of the most popular projection techniques for feature extraction and has been widely applied in face recognition. However, it cannot be used when encountering the single sample per person problem (SSPP) because the intra-class variations cannot be evaluated. In this paper, we propose a novel method called local similarity based linear discriminant analysis (LS_LDA) to solve this problem. Motivated by the "divide-conquer" strategy, we first divide the face into local blocks, and classify each local block, and then integrate all the classification results to make final decision. To make LDA feasible for SSPP problem, we further divide each block into overlapped patches and assume that these patches are from the same class. To improve the robustness of LS_LDA to outliers, we further propose local similarity based median discriminant analysis (LS_MDA), which uses class median vector to estimate the class population mean in LDA modeling. Experimental results on three popular databases show that our methods not only generalize well SSPP problem but also have strong robustness to expression, illumination, occlusion and time variation.

• Journal of Advanced Marine Engineering and Technology
• /
• 제38권9호
• /
• pp.1112-1118
• /
• 2014

본 논문에서는 지역적인 밝기 변화에 강인한 지역 서술자와 유사도 척도를 제안한다. 제안한 지역 서술자는 Haar 웨이블렛 필터를 이용하여 특징점과 주변의 주파수 특성을 포함한 지역 서술자를 정의하여 지역적으로 불균일한 조명의 영향에도 특징점을 명확히 서술할 수 있다. 제안한 유사도 척도는 기존의 엔트로피 기반의 유사도에 지역 서술자로 계산한 유사도를 결합한 형태이다. 이는 지역적인 조명의 변화가 발생한 영역의 유사도를 정확히 반영할 수 있다. 실험을 통해 제안한 방법의 성능을 검증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권6호
• /
• pp.1627-1648
• /
• 2012

We propose an adaptive method for detecting plagiarized pairs from a large set of source code. This method is adaptive in that it uses an adaptive algorithm and it provides an adaptive threshold for determining plagiarism. Conventional algorithms are based on greedy string tiling or on local alignments of two code strings. However, most of them are not adaptive; they do not consider the characteristics of the program set, thereby causing a problem for a program set in which all the programs are inherently similar. We propose adaptive local alignment-a variant of local alignment that uses an adaptive similarity matrix. Each entry of this matrix is the logarithm of the probabilities of the keywords based on their frequency in a given program set. We also propose an adaptive threshold based on the local outlier factor (LOF), which represents the likelihood of an entity being an outlier. Experimental results indicate that our method is more sensitive than JPlag, which uses greedy string tiling for detecting plagiarism-suspected code pairs. Further, the adaptive threshold based on the LOF is shown to be effective, and the detection performance shows high sensitivity with negligible loss of specificity, compared with that using a fixed threshold.

• 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.

• ETRI Journal
• /
• 제24권1호
• /
• pp.23-30
• /
• 2002

MPEG-7 Visual Standard specifies a set of descriptors that can be used to measure similarity in images or video. Among them, the Edge Histogram Descriptor describes edge distribution with a histogram based on local edge distribution in an image. Since the Edge Histogram Descriptor recommended for the MPEG-7 standard represents only local edge distribution in the image, the matching performance for image retrieval may not be satisfactory. This paper proposes the use of global and semi-local edge histograms generated directly from the local histogram bins to increase the matching performance. Then, the global, semi-global, and local histograms of images are combined to measure the image similarity and are compared with the MPEG-7 descriptor of the local-only histogram. Since we exploit the absolute location of the edge in the image as well as its global composition, the proposed matching method can retrieve semantically similar images. Experiments on MPEG-7 test images show that the proposed method yields better retrieval performance by an amount of 0.04 in ANMRR, which shows a significant difference in visual inspection.

• Journal of Information Processing Systems
• /
• 제11권4호
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• 한국멀티미디어학회논문지
• /
• 제16권9호
• /
• pp.1057-1066
• /
• 2013

손가락 관절문(FKP, finger-knuckle-print)을 이용한 개인 인증은 손가락 관절부에 나타나는 주름의 특징을 이용하는 것으로, 텍스처의 방향 정보가 중요한 특징이 된다. 본 논문에서는 SIFT 알고리즘을 이용하여 특징점들을 추출하고, 벡터 유사도 정합을 통해 FKP를 효과적으로 인증할 수 있는 방법을 제안하다. 벡터는 질의 영상에서 추출한 특징점과 이에 대응되는 참조 영상의 특징점을 연결하는 방향 벡터로 정의된다. 국소적인 특징점 쌍으로부터 방향 벡터를 생성하기 때문에 방향 벡터 자체는 국소적인 특징만을 나타내지만, 두 영상 간에 존재하는 다른 벡터들 간의 유사도를 비교함으로써 전역적인 특징으로 확장되는 장점이 있다. 실험결과 제안하는 방법은 기존의 방향코드를 이용한 다양한 방식에 비하여 우수한 성능을 나타내었다.