• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2547-2567
• /
• 2021

It has been widely acknowledged that occlusion impairments adversely distress many face recognition algorithms' performance. Therefore, it is crucial to solving the problem of face image occlusion in face recognition. To solve the image occlusion problem in face recognition, this paper aims to automatically de-occlude the human face majority or discriminative regions to improve face recognition performance. To achieve this, we decompose the generative process into two key stages and employ a separate generative adversarial network (GAN)-based network in both stages. The first stage generates an initial coarse face image without an occlusion mask. The second stage refines the result from the first stage by forcing it closer to real face images or ground truth. To increase the performance and minimize the artifacts in the generated result, a new refine loss (e.g., reconstruction loss, perceptual loss, and adversarial loss) is used to determine all differences between the generated de-occluded face image and ground truth. Furthermore, we build occluded face images and corresponding occlusion-free face images dataset. We trained our model on this new dataset and later tested it on real-world face images. The experiment results (qualitative and quantitative) and the comparative study confirm the robustness and effectiveness of the proposed work in removing challenging occlusion masks with various structures, sizes, shapes, types, and positions.

• 한국정보컨버전스학회:학술대회논문집
• /
• 2008.06a
• /
• pp.53-56
• /
• 2008

This paper reports on the ACQA(Animated agent for Conversational Question Answering) project conducted at LIMSI. The aim is to design an expressive animated conversational agent(ACA) for conducting research along two main lines: 1/ perceptual experiments(eg perception of expressivity and 3D movements in both audio and visual channels): 2/ design of human-computer interfaces requiring head models at different resolutions and the integration of the talking head in virtual scenes. The target application of this expressive ACA is a real-time question and answer speech based system developed at LIMSI(RITEL). The architecture of the system is based on distributed modules exchanging messages through a network protocol. The main components of the system are: RITEL a question and answer system searching raw text, which is able to produce a text(the answer) and attitudinal information; this attitudinal information is then processed for delivering expressive tags; the text is converted into phoneme, viseme, and prosodic descriptions. Audio speech is generated by the LIMSI selection-concatenation text-to-speech engine. Visual speech is using MPEG4 keypoint-based animation, and is rendered in real-time by Virtual Choreographer (VirChor), a GPU-based 3D engine. Finally, visual and audio speech is played in a 3D audio and visual scene. The project also puts a lot of effort for realistic visual and audio 3D rendering. A new model of phoneme-dependant human radiation patterns is included in the speech synthesis system, so that the ACA can move in the virtual scene with realistic 3D visual and audio rendering.

• Journal of Korean Academy of Nursing
• /
• v.26 no.3
• /
• pp.632-652
• /
• 1996

It has been noted that a genetic alteration of cells influenced by unhealthy lifestyle in addition to a series of other carcinogens increases the incidence of various neoplasmic diseases. Therefore the importance of a lifestyle that minimizes such an impact on health should be emphasized. Since stomach cancer, the most common neoplasmic disease in Korea, is related to personal lifestyle and as there is a possibility of its recurrence, patients with stomach cancer need to lead a healthy lifestyle. Also the quality of life which patients experience is negatively affected by the side effects of treatments and the possibility of recurrence. Therefore an effective nursing intervention to enhance quality of life and encourage healthy lifestyle is needed. The purpose of this study is to provide a basis for nursing intervention strategies to promote health and thus enhance quality of life. A hypothetical model for this purpose was constructed based on Pender's Health Promotion Model and Becker's Health Belief Model, with the inclusion of some influential factors such as hope for quality of life and health promoting behavior. The aims of study were to : 1) evaluate the effectiveness of patient's cognitive-perceptual factors on health promoting behaviors and quality of life ; 2) examine the causal relationships among perceived benefit, perceived barrier, perceived susceptibility and severity, internal locus of control, perceived health status, hope, health concept, self efficacy, self esteem health promoting behaviors & quality of life ; 3) build and test a global hypothetical model. The subjects for this study were 164 patients who were being treated for stomach cancer were approached in the outpatient clinic on a University Hospital. The data from the completed questionnaires were analyzed using Linear Structural Relationships (LISREL). The results of research are as follows : 1) Hypothetical model and the modified model showed a good fit to the empirical data, revealing considerable explanational power for health promoting behaviors(54.9%) and quality of life(87.6%) 2) Self efficacy and hope had significant effects on health promoting behaviors. Of these, hope was affected indirectly through self efficacy and self esteem. 3) Perceived health status, hope and self esteem had significant direct effect on the quality of life. Of these variables, perceived health status was the most essential factor affecting general satisfaction in life. 4) Self-efficacy, as a mediating variable, was positively affected by perceived benefit and hope. 5) Self-esteem, as a mediating variable, was positively affected by perceived health status and hope. 6) Hope was the main variable affecting self efficacy, self esteem, health promoting behaviors and quality of life. The derived model in this study could effectively be used as a reference model for further study and could suggests a direction for nursing practices

• Journal of the Korean Society of Earth Science Education
• /
• v.7 no.1
• /
• pp.43-53
• /
• 2014

The purpose of this study is to analyze the conceptual simulation observed when students are thinking about the causes of the seasonal change, identifying how students come up with the explanation. For this study, a framework for conceptual simulation process and strategy based on literary research was developed and its validity was proved by four experts in the field of science education. The results were as in the following: First, through the process of explaining the causes for seasonal change, students usually base their explanation on perceptual experience learned from model experiments from a science class. Besides, construct of thought experiment using the familiar object or analogize of the familiar perceptual experience. These all contributed to on explanation firmly. Second, errors from mental simulation were found in the statement of initial representation and running imagistic simulation. It happened when statement of initial representation is not in a complete and secure state or when participants think of an inappropriate situation during running imagistic simulation. Third, the study identified that the use of strategies like 'removal' and 'replace' was shown to enhance the effects of conceptual simulation particularly in regard with solar attitude at meridian passage.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.8C
• /
• pp.822-829
• /
• 2009

This paper proposes a new method of improving the quality of High Efficiency Advanced Audio Coding (HE-AAC). HE-AAC encodes input source by allocating bits for each scalefactor bands appropriately according to human ear's psychoacoustic property. As a result, insufficient bits are assigned to the bands which have relatively low energy. This imbalance between different energy bands can cause decreasing of sound quality like musical noise. In the proposed system, a Linear Prediction (LP) module is combined with HE-AAC as a pre-processor to improve sound quality by even bits distribution. To apply accurate human being's psychoacoustic property, the psychoacoustic model uses Fast Fourier Transform (FFT) spectrum of original input signal to make masking threshold. In its implementation, masking threshold of psychoacoustic model is normalized using the LP spectral envelope in prior to quantization of the LP residual. Experimental result shows that, the proposed algorithm allocates bits appropriately for insufficient bits condition and improves the performance of HE-AAC.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.2
• /
• pp.157-166
• /
• 2013

This paper proposes a non-intrusive speech quality estimation method considering the effects of packet loss to perceptual quality. Packet loss is a major reason of quality degradation in a packet based speech communications network, whose effects are different according to the input speech characteristics or the performance of the embedded packet loss concealment (PLC) algorithm. For the quality estimation system that involves packet loss effects, we first observe the packet loss of G.729 codec which is one of narrowband codec in VoIP system. In order to quantify the lost packet affects, we design a classification algorithm only using speech parameters of G.729 decoder. Then, the degradation values of each class are iteratively selected that maximizes the correlation with the degradation PESQ-LQ scores, and total quality degradation is modeled by the weighted sum. From analyzing the correlation measures, we obtained correlation values of 0.8950 for the intrusive model and 0.8911 for the non-intrusive method.

• Journal of Intelligence and Information Systems
• /
• v.14 no.3
• /
• pp.41-57
• /
• 2008

U-Publication, the Tag-Embedded publication, is one of U-Media. U-Media is defined as a media where human creates and consumes content through not only human cognitive and perceptual processes but also through the interactions between surrounding digital systems. U-Media provides information by generating, collecting, and attaching the content itself and the related information based on the interaction of the bio-systems incorporating digital information and devices embedded in humans, and surrounding objects including external digital devices. Using U-Publication, readers consume its content not only in offline but also online through a mobile RFID reader which touches and connects the URLs embedded in the RFID tags attached to it. Readers can consume the additional content though the hyperlinks attached to U-Publication and perform commercial activity as well as consumer the printed content. This paper defines the RFID-Tagged publication, proposes its related business models, and evaluates the alternative business models through a simulation study.

• The KIPS Transactions:PartD
• /
• v.17D no.6
• /
• pp.471-480
• /
• 2010

The purpose of this study is to explore determinants which affect the significant increase in the user acceptance of smart phone. This study also analyzes the effect of each variable on the actual acceptance by empirical methods. In this study, first, the system quality and the service quality are defined as independent variables based on developed IS success model of DeLone & McLean(2003). Second, we proposed the research model by providing trust and perceptual immersion as intermediate variables, and user satisfaction and actual use as dependent variables by the proceeding research for accepting information technology and new service. Third, the statistical analysis is conducted by surveying to 200 smart phone users for verifying a validity of research models and hypotheses. As a result, almost hypotheses are accepted in confidence interval except for the hypothesis between security and trust variable.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.5
• /
• pp.75-83
• /
• 2019

Direct volume rendering is a widely used method for visualizing three-dimensional volume data such as medical images. This paper proposes a method for applying depth-of-field effects to volume ray-casting to enable more realistic depth-of-filed rendering in direct volume rendering. The proposed method exploits a camera model based on the human perceptual model and can obtain realistic images with a limited number of rays using jittered lens sampling. It also enables interactive exploration of volume data by on-the-fly calculating depth-of-field in the GPU pipeline without preprocessing. In the experiment with various data including medical images, we demonstrated that depth-of-field images with better depth perception were generated 2.6 to 4 times faster than the conventional method.