• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.19-26
• /
• 2009

This paper studies on the recognition rate change with respect to illumination variance and the confidence level of PCA(Principal Component Analysis) based face recognition by measuring the cumulative match score of CMC(Cumulative Match Characteristic). We studied on the confidence level of the algorithm under illumination changes and selection of training images not only by testing multiple training images per person with illumination variance and single training image and but also by changing the illumination conditions of testing images. The experiment shows that the recognition rate drops for multiple training image case compared to single training image case. We, however, confirmed the confidence level of the algorithm under illumination variance by the fact that the training image which corresponds to the identity of testing image belongs to upper similarity lists regardless of illumination changes and the number of training images.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.3
• /
• pp.886-904
• /
• 2018

The 3D(dimension) vritual reality(VR) has already been used in various sports fields, especially in the training of elite athletes. It is mainly used to maximize the effectiveness of image training, and the use of VR-based image training has received special attention as evidence-based pratices for its feasibility, practicality, and appropriateness. However, in recent years, the use of VR is no longer used only for the training of elite athletes, but is widely used in social sports. This is because, the advantage of exercise in VR is that it is highly stable and has fewer restrictions from the external environment. Considering these advantages, it can be used for the elderly physical activity. This study identifies and reviews studies applying VR-based image training. Several recommendations for the future study on VR-based image training for the older such as interdisciplinary approach to VR-based image training, support needs regarding characteristics of the older, and generalization and maintenance of acquired technology were discussed.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.395-407
• /
• 2023

Super-resolution (SR) has great significance in image processing because it enables downstream vision tasks with high spatial resolution. Recently, SR studies have adopted deep learning networks and achieved remarkable SR performance compared to conventional example-based methods. Deep-learning-based SR models generally require low-resolution (LR) images and the corresponding high-resolution (HR) images as training dataset. Due to the difficulties in obtaining real-world LR-HR datasets, most SR models have used only HR images and generated LR images with predefined degradation such as bicubic downsampling. However, SR models trained on simple image degradation do not reflect the properties of the images and often result in deteriorated SR qualities when applied to real-world images. In this study, we propose an image degradation model for HR satellite images based on the modulation transfer function (MTF) of an imaging sensor. Because the proposed method determines the image degradation based on the sensor properties, it is more suitable for training SR models on remote sensing images. Experimental results on HR satellite image datasets demonstrated the effectiveness of applying MTF-based filters to construct a more realistic LR-HR training dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.167-174
• /
• 2023

This paper attempted to improve the accuracy of the colorectal cancer diagnosis model using image data augmentation in convolutional neural network. Image data augmentation was performed by flipping, rotation, translation, shearing and zooming with basic image manipulation method. This study split 4000 training data and 1000 test data for 5000 image data held, the model is learned by adding 4000 and 8000 images by image data augmentation technique to 4000 training data. The evaluation results showed that the clasification accuracy for 4000, 8000, and 12,000 training data were 85.1%, 87.0%, and 90.2%, respectively, and the improvement effect depending on the increase of image data was confirmed.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.137-145
• /
• 2014

This paper suggests an LDA-based long distance face recognition algorithm for intelligent surveillance system. The existing face recognition algorithm using single distance face image as training images caused a problem that face recognition rate is decreased with increasing distance. The face recognition algorithm using face images by actual distance as training images showed good performance. However, this also causes user inconvenience as it requires the user to move one to five meters in person to acquire face images for initial user registration. In this paper, proposed method is used for training images by using single distance face image to automatically create face images by various distances. The test result showed that the proposed face recognition technique generated better performance by average 16.3% in short distance and 18.0% in long distance than the technique using the existing single distance face image as training. When it was compared with the technique that used face images by distance as training, the performance fell 4.3% on average at a close distance and remained the same at a long distance.

• Journal of Biomedical Engineering Research
• /
• v.15 no.1
• /
• pp.83-88
• /
• 1994

The transform trellis code is an optimal source code as a block size and the constraint length of a shift register go to infinite for stationary Gaussian sources with the squared-error distortion measure. However to implement this code, we have to choose the finite block size and constraint length. Moreover real-world sources are inherently non stationary. To overcome these difficulties, we developed a training algorithm for the transform trellis code. The trained transform trellis code which uses the same rates to each block led to a variation in the resulting distortion from one block to another. To alleviate this non-uniformity in the encoded image, we constructed clusters from the variance of the training data and assigned different rates for each cluster.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.151-152
• /
• 2019

In this paper, we propose an improved learning method based on a small data set for animal image classification. First, CNN creates a training model for a small data set and uses the data set to expand the data set of the training set Second, a bottleneck of a small data set is extracted using a pre-trained network for a large data set such as VGG16 and stored in two NumPy files as a new training data set and a test data set, finally, learn the fully connected network as a new data set.

• The Journal of Korean Physical Therapy
• /
• v.32 no.3
• /
• pp.185-190
• /
• 2020

Purpose: Gait and cognitive impairment in stroke patients exacerbate fall risk and mobility difficulties during multi-task walking. Virtual reality can provide interesting and challenging training in a community setting. This study evaluated the effect of community-based virtual reality gait training (VRGT) using a 360-degree image on the gait ability of chronic stroke patients. Methods: Forty-five chronic stroke patients who were admitted to a rehabilitation hospital participated in this study. Patients meeting the selection criteria were randomly divided into a VRGT group (n=23) and a control group (n=22). Both these groups received general rehabilitation. The VRGT group was evaluated using a 360-degree image that was recorded for 50 minutes a day, 5 days per week for a total of 6 weeks after their training. The control group received general treadmill training for the same amount of time as that of the VRGT group. The improvement in the spatiotemporal parameters of gait was evaluated using a gait analyzer system before and after training. Results: The spatiotemporal gait parameters showed significant improvements in both groups compare with the baseline measurements (p<0.05), and the VRGT group showed more improvement than the control group (p<0.05). Conclusion: Community-based VRGT has been shown to improve the walking ability of chronic stroke patients and is expected to be used in rehabilitation of stroke patients in the future.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.31-37
• /
• 2004

Wavelet transform is a useful tool for analysis and process of image. This showed good performance in image compression and noise reduction. Wavelet coefficients can be effectively modeled by hidden Markov tree(HMT) model. However, in application of HMT model to image interpolation, training procedure is needed. Moreover, the parameters obtained from training procedure do not match input image well. In this paper, the structure of HMT is used for image interpolation, and the parameters of HMT are obtained from statistical characteristics across wavelet subbands without training procedure. In the proposed method, wavelet coefficient is modeled as Gaussian mixture model(GMM). In GMM, state transition probabilities are determined from statistical transition characteristic of coefficient across subbands, and the variance of each state is estimated using the property of exponential decay of wavelet coefficient. In simulation, the proposed method shows improvement of performance compared with conventional bicubic method and the method using HMT model with training.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1624-1631
• /
• 2021

With the continued development of image processing technology, we live in a time when it is difficult to visually discriminate processed (or tampered) images from real images. However, as the risk of fake images being misused for crime increases, the importance of image forensic science for identifying fake images is emerging. Currently, various deep learning-based identifiers have been studied, but there are still many problems to be used in real situations. Due to the inherent characteristics of deep learning that strongly relies on given training data, it is very vulnerable to evaluating data that has never been viewed. Therefore, we try to find a way to improve generalization ability of deep learning-based fake image identifiers. First, images with various contents were added to the training dataset to resolve the over-fitting problem that the identifier can only classify real and fake images with specific contents but fails for those with other contents. Next, color spaces other than RGB were exploited. That is, fake image identification was attempted on color spaces not considered when creating fake images, such as HSV and YCbCr. Finally, dropout, which is commonly used for generalization of neural networks, was used. Through experimental results, it has been confirmed that the color space conversion to HSV is the best solution and its combination with the approach of increasing the training dataset significantly can greatly improve the accuracy and generalization ability of deep learning-based identifiers in identifying fake images that have never been seen before.