• Journal of Korea Multimedia Society
• /
• v.14 no.3
• /
• pp.378-391
• /
• 2011

In this paper, we suggest a novel method of selecting visual information based on bottom-up visual attention of human. We propose a new model that improve accuracy of detecting attention region by using depth information in addition to low-level spatial features such as color, lightness, orientation, form and temporal feature such as motion. Motion is important cue when we derive temporal saliency. But noise obtained during the input and computation process deteriorates accuracy of temporal saliency Our system exploited the result of psychological studies in order to remove the noise from motion information. Although typical systems get problems in determining the saliency if several salient regions are partially occluded and/or have almost equal saliency, our system is able to separate the regions with high accuracy. Spatiotemporally separated prominent regions in the first stage are prioritized using depth value one by one in the second stage. Experiment result shows that our system can describe the salient regions with higher accuracy than the previous approaches do.

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.409-416
• /
• 2013

Attention is one of important cognitive functions in human affecting on the selectional concentration of relevant events and ignorance of irrelevant events. The discrimination of attentional and inattentional status is the first step to manage human's attentional capability using computer assisted device. In this paper, we newly combine the non-linear recurrence pattern analysis and spectrum analysis to effectively extract features(total number of 13) from the electroencephalographic signal used in the input to classifiers. The performance of diverse types of attention-inattention classifiers, including supporting vector machine, back-propagation algorithm, linear discrimination, gradient decent, and logistic regression classifiers were evaluated. Among them, the support vector machine classifier shows the best performance with the classification accuracy of 81 %. The use of spectral band feature set alone(accuracy of 76 %) shows better performance than that of non-linear recurrence pattern feature set alone(accuracy of 67 %). The support vector machine classifier with hybrid combination of non-linear and spectral analysis can be used in later designing attention-related devices.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.300-302
• /
• 2022

Palm vein identification has attracted attention due to its distinct characteristics and excellent recognition accuracy. However, many contactless palm vein identification systems suffer from the issue of having low-quality palm images, resulting in degradation of recognition accuracy. This paper proposes the use of U-Net architecture to correctly segment the vascular blood vessel from palm images. Attention gate mechanism and residual block are also utilized to effectively learn the crucial features of a specific segmentation task. The experiments were conducted on CASIA dataset. Hessian-based Jerman filtering method is applied to label the palm vein patterns from the original images, then the network is trained to segment the palm vein features from the background noise. The proposed method has obtained 96.24 IoU coefficient and 98.09 dice coefficient.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.245-265
• /
• 2022

In response to problems such as insufficient extraction information, low detection accuracy, and frequent misdetection in the field of Thangka image defects, this paper proposes a YOLOv5 prediction algorithm fused with the attention mechanism. Firstly, the Backbone network is used for feature extraction, and the attention mechanism is fused to represent different features, so that the network can fully extract the texture and semantic features of the defect area. The extracted features are then weighted and fused, so as to reduce the loss of information. Next, the weighted fused features are transferred to the Neck network, the semantic features and texture features of different layers are fused by FPN, and the defect target is located more accurately by PAN. In the detection network, the CIOU loss function is used to replace the GIOU loss function to locate the image defect area quickly and accurately, generate the bounding box, and predict the defect category. The results show that compared with the original network, YOLOv5-SE and YOLOv5-CBAM achieve an improvement of 8.95% and 12.87% in detection accuracy respectively. The improved networks can identify the location and category of defects more accurately, and greatly improve the accuracy of defect detection of Thangka images.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.98-108
• /
• 2023

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2024

This paper investigates the effect of an artificial intelligence attention redirection compensation strategy system on the data labeling work attention concentration by individuals with developmental disabilities. Task accuracy and task performance for each session were used as measures of attention concentration. As a result of the study, after the intervention was applied, a significant improvement in attention concentration was observed in all study subjects compared to self-serving task. These results mean that artificial intelligence technology can have a positive effect on improving the attention span of people with developmental disabilities during data labeling tasks. This study shows that the application of artificial intelligence technology can improve the quality of learning data by improving the accuracy of data labeling tasks for people with developmental disabilities, and is expected to provide important implications for vocational training programs related to data labeling for people with developmental disabilities.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.10
• /
• pp.131-136
• /
• 2007

In this paper, we estimated the effects of different color stimulation on the cognitive function of human quantitatively. For the stimulations we used color lights with 6 color filters such as red, yellow, green, blue, violet and white. The experiment was performed in a soundproof chamber. 50 young male and female subjects were participated in the experiment. To find the appropriate color cognitive function, the endogenous visuospatial attention task(EVAT) and one back working memory task(OWMT) were performed. The reaction time and accuracy degree were measured. The results showed that the reaction time of EVAT was the fastest and the accuracy degree of attention task was the highest in green environment. The reaction time of OWMT was the fastest in yellow and the accuracy degree of memory task was the highest in blue. For physiological parameters, we measured electrocardiogram(ECG) and HRV spectrum analysis, HF/LF color environment. These results can be used as an indicator in the design of color environment and clinical applications.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.45-51
• /
• 2021

With the development of deep learning, semantic segmentation methods are being studied in various fields. There is a problem that segmenation accuracy drops in fields that require accuracy such as medical image analysis. In this paper, we improved PSPNet, which is a deep learning based segmentation method to minimized the loss of features during semantic segmentation. Conventional deep learning based segmentation methods result in lower resolution and loss of object features during feature extraction and compression. Due to these losses, the edge and the internal information of the object are lost, and there is a problem that the accuracy at the time of object segmentation is lowered. To solve these problems, we improved PSPNet, which is a semantic segmentation model. The multi-scale attention proposed to the conventional PSPNet was added to prevent feature loss of objects. The feature purification process was performed by applying the attention method to the conventional PPM module. By suppressing unnecessary feature information, eadg and texture information was improved. The proposed method trained on the Cityscapes dataset and use the segmentation index MIoU for quantitative evaluation. As a result of the experiment, the segmentation accuracy was improved by about 1.5% compared to the conventional PSPNet.

• Science of Emotion and Sensibility
• /
• v.23 no.4
• /
• pp.3-20
• /
• 2020

The purpose of this study was to investigate the effect of aging on visuo-spatial attention allocation ability and emotional perception bias. We used the useful field of view (UFOV) task to measure the visuo-spatial attention allocation ability and the emotional perception task to measure positive and negative emotional perception bias. A total of 48 participants took part in this study with 23 participants in the senior group and 25 in the junior group. The senior group showed slower response time and lower accuracy than the junior group in the UFOV task, indicating that the senior group had lower visuo-spatial attention allocation ability than the junior group. In the emotional perception task, the senior group showed both positive and negative emotional perception bias more than the junior group. The correlation analysis showed that the negative emotional perception bias for accuracy in the emotional perception task showed a positive correlation with the response time to the stimuli presented in the visual angle 30° in the UFOV task (r=.289). In addition, positive emotional perception bias for the accuracy in the emotional perception task showed a positive correlation with the accuracy of the stimuli presented in the visual angles 10°, 20°, and 30° in the UFOV task (r=.305, r=.322, and r=.299, respectively). However, it showed a negative correlation with the response time of the stimuli presented in the same location in the UFOV task (r=-.345, r=-.295, r=-.308). These results suggest that aging is associated with a decrease in the visuo-spatial attention allocation ability and perceptual bias toward positive and negative emotions. In addition, the positive and negative emotional perception biases associated with aging are potentially related to the reduced visuo-spatial attention allocation ability.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.