• Smart Media Journal
• /
• v.12 no.2
• /
• pp.9-14
• /
• 2023

In this paper, we proposed a face recognition network which attempts to use more facial features awhile using smaller number of training sets. When combining the neural network together for face recognition, we want to use networks that use different part of the facial features. However, the network training chooses randomly where these facial features are obtained. Other hand, the judgment basis of the network model can be expressed as a saliency map through gradCAM. Therefore, in this paper, we use gradCAM to visualize where the trained face recognition model has made a observations and recognition judgments. Thus, the network combination can be constructed based on the different facial features used. Using this approach, we trained a network for small face recognition problem. In an simple toy face recognition example, the recognition network used in this paper improves the accuracy by 1.79% and reduces the equal error rate (EER) by 0.01788 compared to the conventional approach.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.113-127
• /
• 2012

Face detection methods using image processing have been proposed in many different ways. Generally, the most widely used method for face detection is an Adaboost that is proposed by Viola and Jones. This method uses Haar-like feature for image learning, and the detection performance depends on the learned images. It is well performed to detect face images within a certain distance range, but if the image is far away from the camera, face images become so small that may not detect them with the pre-learned Haar-like feature of the face image. In this paper, we propose the far distance face detection method that combine the Aadaboost of Viola-Jones with a saliency map and user's attention information. Saliency Map is used to select the candidate face images in the input image, face images are finally detected among the candidated regions using the Adaboost with Haar-like feature learned in advance. And the user's eye-tracking information is used to select the interest regions. When a subject is so far away from the camera that it is difficult to detect the face image, we expand the small eye gaze spot region using linear interpolation method and reuse that as input image and can increase the face image detection performance. We confirmed the proposed model has better results than the conventional Adaboost in terms of face image detection performance and computational time.

• Journal of Information Processing Systems
• /
• v.13 no.3
• /
• pp.448-463
• /
• 2017

Multimedia is a ubiquitous and indispensable part of our daily life and learning such as audio, image, and video. Objective and subjective quality evaluations play an important role in various multimedia applications. Blind image quality assessment (BIQA) is used to indicate the perceptual quality of a distorted image, while its reference image is not considered and used. Blur is one of the common image distortions. In this paper, we propose a novel BIQA index for Gaussian blur distortion based on the fact that images with different blur degree will have different changes through the same blur. We describe this discrimination from three aspects: color, edge, and structure. For color, we adopt color histogram; for edge, we use edge intensity map, and saliency map is used as the weighting function to be consistent with human visual system (HVS); for structure, we use structure tensor and structural similarity (SSIM) index. Numerous experiments based on four benchmark databases show that our proposed index is highly consistent with the subjective quality assessment.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.3-10
• /
• 2018

Depth map has been utilized in a varity of fields. Recently research on generating depth map by artificial neural network (ANN) has gained much interest. This paper validates the feasibility of implementing the ready-made depth map generation by convolutional neural network (CNN). First, for a given image, a depth map is generated by the weighted average of a saliency map as well as a motion history image. Then CNN network is trained by test images and depth maps. The objective and subjective experiments are performed on the CNN and showed that the CNN can replace the ready-made depth generation method.

• Korean Journal of Adult Nursing
• /
• v.16 no.4
• /
• pp.668-676
• /
• 2004

Purpose: The purpose of this study was to investigate factors determining health behavior for middle-aged adults in relation to stress coping behaviors, cognitive factors, social support, and sociodemographic variables. Method: The questionnaire survey was carried out on a convenience sample of 203 middle aged in a community settings. The data analysis procedure included frequency, t-test, ANOVA, Pearson correlation coefficient, and stepwise multiple regressions using health behavior as dependent variable. Result: Among the sociodemographic variables, factors such as sex, educational and eonomic levels were associated with the health behaviors. There were significant correlations between health behaviors and saliency of health, social support, and positive-stress coping behaviors. Stepwise multiple regression revealed that the factors such as positive-stress coping behaviors, saliency of health, sex, and education turned out to be significant affecting factors. Twenty eight percent of varience in health behavior was explained by these factors. Conclusion: Positive-stress coping methods were turned out to be the most important effective factors in practicing of health behaviors of middle aged. The necessity of an intervention considering the situation related to their stress and coping methods in middle aged so as to promote positive health behaviors was suggested.

• Phonetics and Speech Sciences
• /
• v.1 no.2
• /
• pp.95-103
• /
• 2009

We investigated the perceptual structure of Korean consonants by analyzing the confusion among consonants in various vowel contexts. The 36 CV syllable types combined by 18 consonants and 2 vowels (/i/ and /u/) were presented with masking noises or in degraded intensity. The confusion data were analyzed by the INDSCAL (Individual Difference Scaling), ADCLUS (Additive Clustering) and the probability of the transmitted information. The results were compared with those of a previous study with /a/ vowel context (Bae and Kim, 2002). The overall results showed that the laryngeal features-aspiration, lax and tense-are the most salient features in the perception of Korean consonant regardless of vowel contexts, but the perceptual saliency of place features varies across vowel conditions. In high vowel (front and back vowel) contexts, sibilant consonants were perceptually salient compared to in low vowel contexts. In back vowel contexts, grave (labial and velar) consonants were perceptually salient. These findings imply that place features and vowel features strongly interact in speech perception as well as in speech production. All statistical measures from our confusion data ensured that the perceptual structure of Korean consonants correspond to the hierarchical structure suggested in the feature geometry (Clements, 1991). We discuss the link between speech perception and production as the basis of phonology.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.52 no.6
• /
• pp.254-261
• /
• 2003

This study investigates magnetic circuit design of the Single-phase Line-start Permanent Magnet Synchronous Motor (LSPM) to develop the characteristics in steady state. In this paper, the saliency ratio, that is the ratio of q-axial inductance to d-axial inductance, and the inductance difference between q-axial inductance and d-axial inductance are increased. Design factor is selected permanent magnet position and rotor diameter. The analysis method of the synchronous motor on d-/q- axis coordinates is used for the positive component and the equivalent circuit of the induction motor is applied for the negative component analysis. Back-emf and d-q- axial inductance is analyzed by using 2 dimensional Finite Element Method (FEM). Characteristic analysis results with variation of design factor are reflected magnetic circuit design of LSPM. The characteristics of design model are compared with the characteristic of initial model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2737-2753
• /
• 2013

In this study, we propose a novel salient object detection strategy based on regional contrast and relative spatial compactness. Our algorithm consists of four basic steps. First, we learn color names offline using the probabilistic latent semantic analysis (PLSA) model to find the mapping between basic color names and pixel values. The color names can be used for image segmentation and region description. Second, image pixels are assigned to special color names according to their values, forming different color clusters. The saliency measure for every cluster is evaluated by its spatial compactness relative to other clusters rather than by the intra variance of the cluster alone. Third, every cluster is divided into local regions that are described with color name descriptors. The regional contrast is evaluated by computing the color distance between different regions in the entire image. Last, the final saliency map is constructed by incorporating the color cluster's spatial compactness measure and the corresponding regional contrast. Experiments show that our algorithm outperforms several existing salient object detection methods with higher precision and better recall rates when evaluated using public datasets.

• 한국경영정보학회:학술대회논문집
• /
• 2007.06a
• /
• pp.503-508
• /
• 2007

In order to understand information system post-adoption phenomena, the expectation-confirmation model (ECM) was proposed. Past studies based on the ECM focus on a referent centered on the target IS being studied. The effect of this reference, captured through confirmation, has been strongly shown. However, the saliency of two additional reference effects, captured through self-image congruity and regret, has not been explored. In order to fill this knowledge gap, this paper attempts to develop a research model that extends the ECM by incorporating self-image congruity and regret as well as perceived enjoyment. For this extension, we synthesize the extant literature on continued IS use, self-image congruity, and regret. The analysis results tell us that self-image congruity plays a key role in forming two post-adoption beliefs, perceived usefulness and perceived enjoyment. It is also found that the absolute effect of regret on continuance intention is larger than those of other antecedents identified in IS. Overall, this study preliminarily confirms the saliency of self-image congruity and regret in post-adoption phenomena. Our study results is likely to help the IS community systematically address unexplored effects of self-image congruity and regret.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.123-132
• /
• 2017

Traffic lights contain very important information for safety driving. So, the delivery of the information to drivers in real-time is a very critical issue for advanced driver assistance systems. However, traffic light detection is quite difficult because of the small sized traffic lights and the occlusion in real world. In this paper, a traffic light detection method using modified color based saliency map and morphological information is proposed. It shows 98.14% of precisions and 83.52% of recalls on computer simulations.