• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3172-3193
• /
• 2018

Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.

• The International Journal of Costume Culture
• /
• 제5권1호
• /
• pp.1-13
• /
• 2002

The purpose of this study is to illuminate the relations between Pop Art and pop music, which formed a serious coupling loop in an identical cultural background. Also this study intends to set up a position of visualized sexual identity as it Points out the conceptional characteristics of glam, a subculture outside mainstream, which includes the matters of sexual minorities such as homosexuality and bisexuality under the influence of the aesthetic and philosophical composition by Andy Warhol. In conjunction herewith, we explore the visual representation of glam style focusing on the influence of Warhol. The classification and explanation about the visual representation of glam style under the influence of Warhol are practised by distinguishing as denotative representation and connotative representation. For the denotative representation shown in the glum style, first, the discordant images were put together by bricolage, then adapted into the new dramatic symbol of youth. Second, through a visually androgynous style a subversion of sex for symbols of sexuality and gender was represented. Third, the factitiveness as a weird display and fallacy is shown from boisterous make-up and unisex sかling in theatricality and put-ons, featuring artificiality, assemblage and unnaturality. And the connaotative representation shown in glum inglam style, first, glam style implies its experimental nature which attempts to break down boundaries between masculinity and femininity, homosexuality and heterosex-uality. Second, the bricolage in sequin and other discordant elements have connotative meanings as sensuality and excessiveness. Third, mixing various style as sexual play shows ironic visual images, in accordance with Superior Theory and Discord Theory.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권9호
• /
• pp.4510-4526
• /
• 2017

Most available methods of facial gender recognition work well under a constrained situation, but the performances of these methods have decreased significantly when they are implemented under unconstrained environments. In this paper, a method via low-rank and collaborative representation is proposed for facial gender recognition in the wild. Firstly, the low-rank decomposition is applied to the face image to minimize the negative effect caused by various corruptions and dynamical illuminations in an unconstrained environment. And, we employ the collaborative representation to be as the classifier, which using the much weaker $l_2-norm$ sparsity constraint to achieve similar classification results but with significantly lower complexity. The proposed method combines the low-rank and collaborative representation to an organic whole to solve the task of facial gender recognition under unconstrained environments. Extensive experiments on three benchmarks including AR, CAS-PERL and YouTube are conducted to show the effectiveness of the proposed method. Compared with several state-of-the-art algorithms, our method has overwhelming superiority in the aspects of accuracy and robustness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2709-2729
• /
• 2016

Representation based classification, kernel method and sparse representation have received much attention in the field of face recognition. In this paper, we proposed an improved kernel principal component analysis method based on sparse representation to improve the accuracy and robustness for face recognition. First, the distances between the test sample and all training samples in kernel space are estimated based on collaborative representation. Second, S training samples with the smallest distances are selected, and Kernel Principal Component Analysis (KPCA) is used to extract the features that are exploited for classification. The proposed method implements the sparse representation under ℓ₂ regularization and performs feature extraction twice to improve the robustness. Also, we investigate the relationship between the accuracy and the sparseness coefficient, the relationship between the accuracy and the dimensionality respectively. The comparative experiments are conducted on the ORL, the GT and the UMIST face database. The experimental results show that the proposed method is more effective and robust than several state-of-the-art methods including Sparse Representation based Classification (SRC), Collaborative Representation based Classification (CRC), KCRC and Two Phase Test samples Sparse Representation (TPTSR).

• 대한수학회보
• /
• 제50권2호
• /
• pp.389-398
• /
• 2013

Let R be a ring and $\mathcal{Q}$ be a quiver. In this paper we give another definition of purity in the category of quiver representations. Under such definition we prove that the class of all pure injective representations of $\mathcal{Q}$ by R-modules is preenveloping. In case $\mathcal{Q}$ is a left rooted semi-co-barren quiver and R is left Noetherian, we show that every cotorsion flat representation of $\mathcal{Q}$ is pure injective. If, furthermore, R is $n$-perfect and $\mathcal{F}$ is a flat representation $\mathcal{Q}$, then the pure injective dimension of $\mathcal{F}$ is at most $n$.

• 대한음성학회지:말소리
• /
• 제33_34호
• /
• pp.71-89
• /
• 1997

In the framework of linear representation which allows for no internal structure within features, there is no way to represent nonlinear phonological phenomena such as complex segments. This paper shows how we carl solve some problems of the linear feature theory in relation to the hierarchical feature theory. The purpose of this paper is to explain lateral assimilation under hierarchical feature representation. Although arguments for the position of classes of distinctive features have been made the position of (lateral) remains the issue of debate. Sagey(1988) argues that the feature [lateral] is structurally dependent on the root node. In contrast Rice & Avery (1991) put the feature (lated) under the spontaneous voicing. I have discussed previous studies of feature hierarchy and I propose a revised model of feature representation. Within this model I have shown how well feature geometry describes lateralization as feature spreading.

• 분석과 대안
• /
• 제5권1호
• /
• pp.87-121
• /
• 2021

かつてフェミニズムや男女平等を批判していた安倍晋三首相率いる第二次安倍政権は,2012年以降,女性の社会進出を後押しする政策を積極的に促進し,2015年には女性の職業生活における活躍の推進に関する法律（女性活躍推進法)を成立させている。女性活躍推進法は,女性政策ではなく,女性を利用しようとする経済政策であるとの批判が多いが,一方では女性のための政策としての側面もあるとの指摘もあり,保守政権による女性政策の興味深いケースとなっている。本稿は,女性活躍推進法の審議過程における女性の実質的代表の内実を明らかにすることを目的とする。具体的には,安倍政権による女性政策,また,女性の実質的代表に関する先行研究の知見から導き出した二つのリサーチクエスチョンへの答えを,法案審議での議員発言をデータとして提示することが本稿の課題である。第一に,女性活躍推進法が女性活用の経済政策であるという評価から,審議過程においても,女性の利益や権利を代表する発言よりも,女性を経済成長や少子高齢化社会における資源として活用しようとする発言が多いのかどうかを探る。第二に,女性を実質的に代表する発言があるとすれば,どのような発言内容が見られるのかを明らかにする。特に,保守政党である自由民主党が多数を占めている国会での審議においては,女性の家庭内ケア提供役割を所与とした女性のための発言が大勢を占めているのかに注目する。これらのリサーチクエスチョンに答えることで,女性活躍推進法を巡る女性の実質的代表の有り様,また保守主義と女性の実質的代表の関係を明らかし,女性の実質的代表の研究に貢献することを目指す。分析の結果,女性を活用しようとする発言は,女性を代表する発言,また女性活用の姿勢を批判する発言と比べて数が少なかったこと,議員発言によって多種多様な女性が代表されていることが明らかになった。また,保守系議員による,女性の家庭内ケア提供役割を所与とした保守的な女性の代表発言がある一方で,主に野党議員による,保守的ではない女性の代表発言も多くあったことも示された。これらの分析結果は,保守政権が支配する議会であっても,非保守的な女性の実質的代表が,少なくとも審議過程においては可能であることを示唆している。

• 한국실내디자인학회논문집
• /
• 제18권6호
• /
• pp.133-141
• /
• 2009

Since Adolf Loos' Ornament and Crime was released, ornament had been regarded as a vice in Modern architecture. In Post Modern architecture, the ornamental vocabularies extracted from the classical architecture have been symbolically expressed. As a result, the significance of existence of and the use value of architecture have increased with improved intimacy to the public. However, many studies that have analyzed architecture in terms of semantics and semiotics focusing on communication between architecture and the public have admitted instability in architectural meaning because of the fundamental difference between architecture and language. At the same time, the architectural representation has encountered a lot of limitations along with the deconstruction and non-presentation theory in Post-Structuralism. Even under these circumstances, the ornamental representation can be a critical factor which makes communication possible while expressing spatial identity in this pluralistic contemporary society. Hence, this paper has established logical grounds for research based on theoretical investigation on the concept of representation, semiotics, and ornamental representation, with regard to spatial communication through ornamental representation in commercial space. Based on Peirce's Semiotics which is the typical theoretical science in terms of representation, this paper has analyzed the three kinds of signs (Icon, Index and Symbol) that he proposed. Peirce's classification of signs becomes ideal when the factors are well balanced, with room for combination instead of strict classification. It appears that his theory of signs would be useful in understanding and analyzing ornamental representation. This study on representational ornament could offer a plan for ideal communication and abundant spatial experience in the interior design of commercial space in which the expression of creative space identity is required.

• 한국멀티미디어학회논문지
• /
• 제21권2호
• /
• pp.173-180
• /
• 2018

This paper proposes a method to improve the performance of face recognition via super-resolution method using sparse representation and deep learning from low-resolution facial images. Recently, there have been many researches on ultra-high-resolution images using deep learning techniques, but studies are still under way in real-time face recognition. In this paper, we combine the sparse representation and deep learning to generate super-resolution images to improve the performance of face recognition. We have also improved the processing speed by designing in parallel structure when applying sparse representation. Finally, experimental results show that the proposed method is superior to conventional methods on various images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2748-2766
• /
• 2016

Compared with traditional patch-based sparse representation, recent studies have concluded that group-based sparse representation (GSR) can simultaneously enforce the intrinsic local sparsity and nonlocal self-similarity of images within a unified framework. This article investigates an accelerated split Bregman method (SBM) that is based on GSR which exploits image compressive sensing (CS). The computational efficiency of accelerated SBM for the measurement matrix of a partial Fourier matrix can be further improved by the introduction of a fast Fourier transform (FFT) to derive the enhanced algorithm. In addition, we provide convergence analysis for the proposed method. Experimental results demonstrate that accelerated SBM is potentially faster than some existing image CS reconstruction methods.