• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.15-22
• /
• 2019

Recent technological advances in three-dimensional (3D) sensing devices and machine learning such as deep leaning has enabled data-driven 3D applications. Research on artificial intelligence has developed for the past few years and 3D deep learning has been introduced. This is the result of the availability of high-quality big data, increases in computing power, and development of new algorithms; before the introduction of 3D deep leaning, the main targets for deep learning were one-dimensional (1D) audio files and two-dimensional (2D) images. The research field of deep leaning has extended from discriminative models such as classification/segmentation/reconstruction models to generative models such as those including style transfer and generation of non-existing data. Unlike 2D learning, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become increasingly popular owing to advances in 3D vision technology, the generation/acquisition of 3D data is still very difficult. Even if 3D data can be acquired, post-processing remains a significant problem. Moreover, it is not easy to directly apply existing network models such as convolution networks owing to the various ways in which 3D data is represented. In this paper, we summarize technological trends in AI-based 3D content generation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.798-801
• /
• 2014

Nowadays, the demand for multimedia services has grown with the rapid evolution in the digital era. But due to external causes in the process of processing, transmitting and storing image data, the images are damaged. One of the major causes of such damage is known to be noise. Some of the most commonly used methods for removing noise are CWMF(center weighted median filter), A-TMF(alpha-trimmed mean filter) and AWMF(adaptive weighted median filter). However, these filters all leave a bit to be desired in removing noise in a complex noise environment. Therefore this paper suggest an image restoration filter algorithm that first judges the noise and sets a adjustment weight based on the median value and distance of the mask to remove the complex noise. For an objective analysis, the results were compared against existing methods and the PSNR(peak signal to noise ratio) was used as a reference.

• Korean Journal of Agricultural Science
• /
• v.46 no.2
• /
• pp.381-393
• /
• 2019

A smart farm is a system that combines information and communication technology (ICT), internet of things (IoT), and agricultural technology that enable a farm to operate with minimal labor and to automatically control of a greenhouse environment. Machine learning based on recently data-driven techniques has emerged with big data technologies and high-performance computing to create opportunities to quantify data intensive processes in agricultural operational environments. This paper presents research on the application of machine learning technology to diagnose the growth status of crops and predicting the harvest time of strawberries in a greenhouse according to image processing techniques. To classify the growth stages of the strawberries, we used object inference and detection with machine learning model based on deep learning neural networks and TensorFlow. The classification accuracy was compared based on the training data volume and training epoch. As a result, it was able to classify with an accuracy of over 90% with 200 training images and 8,000 training steps. The detection and classification of the strawberry maturities could be identified with an accuracy of over 90% at the mature and over mature stages of the strawberries. Concurrently, the experimental results are promising, and they show that this approach can be applied to develop a machine learning model for predicting the strawberry harvesting time and can be used to provide key decision support information to both farmers and policy makers about optimal harvest times and harvest planning.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.104-107
• /
• 2019

Modern people have abundant food and various forms of life compared to the past, but they have come to form an unhealthy diet, such as skipping breakfast and not eating in time in a busy life. When these eating habits are maintained for a long time, it leads to digestive trouble. The most easily occurring symptoms are called reflux esophagitis and dysphagia. Among them, dysphagia requires quick and accurate diagnosis as they develop into various forms of complications or are also identified as presymptoms of gastric and laryngeal cancers. The result of the diagnosis is still passively judged by the doctor and each of results are different depending on the doctor. The result of the diagnosis here means the severity. When they identify treatment or complications following the results of the diagnosis, the wrong diagnosis may lead to excessive or insufficient treatment. In this paper, to figure out the severity of dysphagia in the diagnosis of dysphagia, we studied the development of a program using the K-means algorithm in the processing of X-ray images for identifying residual food in epiglottic vallecula and pyriform sinus in the section leading to esophagus.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.301-310
• /
• 2021

The TATI model is a Traffic Accident Text to RGB Image model, which is a methodology proposed in this paper for predicting the severity of traffic accidents. Traffic fatalities are decreasing every year, but they are among the low in the OECD members. Many studies have been conducted to reduce the death rate of traffic accidents, and among them, studies have been steadily conducted to reduce the incidence and mortality rate by predicting the severity of traffic accidents. In this regard, research has recently been active to predict the severity of traffic accidents by utilizing statistical models and deep learning models. In this paper, traffic accident dataset is converted to color images to predict the severity of traffic accidents, and this is done via CNN models. For performance comparison, we experiment that train the same data and compare the prediction results with the proposed model and other models. Through 10 experiments, we compare the accuracy and error range of four deep learning models. Experimental results show that the accuracy of the proposed model was the highest at 0.85, and the second lowest error range at 0.03 was shown to confirm the superiority of the performance.

• Journal of Cadastre & Land InformatiX
• /
• v.51 no.1
• /
• pp.125-136
• /
• 2021

Recently, Unmanned Aerial Vehicle utilization and image processing technology for remote sensing have diversified remarkably with Orthophoto and Digital Surface Model. In particular, It uses more application fields such as spatial information analysis and hazardous areas as well as land surveying. This study analyses the accuracy of the coordinate on Orthophoto and DSM height on slope area with high and low differences by using UAV images. As the result of this study, in the case of GCP on 2D orthophoto, the location error was not produced significantly. The vertical position of the DSM showed the highest accuracy when the height difference between GCPs is under 30m(RMSEZ=0.07m). The location of the GCPs was divided into approximately 10m, 20m, 30m, and 40m with analysis for each of the eight points of GCP and inspection points in general. This study expects that producing both horizontal accuracy of Orthophoto and vertical accuracy of DSM using UAV on the sloped area which similar to this research area will help in spatial information fields.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.9-18
• /
• 2021

Although Generative Adversarial Networks (GANs) have gained great popularity in computer vision and related fields, generating audio signals independently has yet to be presented. Unlike images, an audio signal is a sampled signal consisting of discrete samples, so it is not easy to learn the signals using CNN architectures, which is widely used in image generation tasks. In order to overcome this difficulty, GAN researchers proposed a strategy of applying time-frequency representations of audio to existing image-generating GANs. Following this strategy, we propose an improved method for increasing the fidelity of synthesized audio signals generated by using GANs. Our method is demonstrated on a public speech dataset, and evaluated by Fréchet Inception Distance (FID). When employing our method, the FID showed 10.504, but 11.973 as for the existing state of the art method (lower FID indicates better fidelity).

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.4
• /
• pp.91-103
• /
• 2006

This paper proposes a methodology to evaluate the quality and level of difficulty of fingerprint image databases, which leads to objective evaluation for the performance of fingerprint recognition system. Influencing factors to fingerprint matching are defined and the matching performance between two fingerprint images is evaluated using segmentation and orientation filed. In this study, a hierarchical processing method is proposed to measure an orientation field, which is able to improve the matching speed and accuracy. The results of experiments demonstrate that the defined influencing factors can describe the characteristics of fingerprint databases. Level of difficulty for fingerprint databases enables the performance of fingerprint recognition algorithms to be evaluated and compared even with different databases.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.51-57
• /
• 2021

In this paper, we propose a method to find the DoF(Depth of field) that is blurred in an image by focusing and out-focusing the camera through a efficient convolutional neural network. Our approach uses the RGB channel-based cross-correlation filter to efficiently classify the DoF region from the image and build data for learning in the convolutional neural network. A data pair of the training data is established between the image and the DoF weighted map. Data used for learning uses DoF weight maps extracted by cross-correlation filters, and uses the result of applying the smoothing process to increase the convergence rate in the network learning stage. The DoF weighted image obtained as the test result stably finds the DoF region in the input image. As a result, the proposed method can be used in various places such as NPR(Non-photorealistic rendering) rendering and object detection by using the DoF area as the user's ROI(Region of interest).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.439-445
• /
• 2021

Low-cost, ultra-high-speed cameras, made possible by the development of image sensors and small displays, can be very useful in image processing and pattern recognition. This paper introduces an algorithm that corrects irregular lighting from a high-speed image that is continuously input with a slight time interval, and which then obtains an exposed skin color region that is the area of interest in a person from the corrected image. In this study, the non-uniform lighting effect from a received high-speed image is first corrected using a frame blending technique. Then, the region of interest is robustly obtained from the input high-speed color image by applying an elliptical skin color distribution model generated from iterative learning in advance. Experimental results show that the approach presented in this paper corrects illumination in various types of color images, and then accurately acquires the region of interest. The algorithm proposed in this study is expected to be useful in various types of practical applications related to image recognition, such as face recognition and tracking, lighting correction, and video indexing and retrieval.