• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1326-1335
• /
• 2021

As part of the cell division method, we proposed a method for segmenting images generated by topography microscopes through deep learning-based feature generation and graph segmentation. Hybrid vector shapes preserve the overall shape and boundary information of cells, so most cell shapes can be captured without any post-processing burden. NIH-3T3 and Hela-S3 cells have satisfactory results in cell description preservation. Compared to other deep learning methods, the proposed cell image segmentation method does not require postprocessing. It is also effective in preserving the overall morphology of cells and has shown better results in terms of cell boundary preservation.

• Journal of Multimedia Information System
• /
• 제8권3호
• /
• pp.183-190
• /
• 2021

In this paper, we implement a system for a fund recommendation based on the investment propensity and for a future fund price prediction. The investment propensity is classified by scoring user responses to series of questions. The proposed system recommends the funds with a suitable risk rating to the investment propensity of the user. The future fund prices are predicted by Prophet model which is one of the machine learning methods for time series data prediction. Prophet model predicts future fund prices by learning the parameters related to trend changes. The prediction by Prophet model is simple and fast because the temporal dependency for predicting the time-series data can be removed. We implement web pages for the fund recommendation and for the future fund price prediction.

• 한국멀티미디어학회논문지
• /
• 제22권4호
• /
• pp.424-431
• /
• 2019

In this paper, we propose a real-time hand gesture recognition algorithm to eliminate the inconvenience of using hand controllers in VR applications. The user's 3D hand coordinate information is detected by leap motion sensor and then the coordinates are generated into two dimensional image. We classify hand gestures in real-time by learning the imaged 3D hand coordinate information through SSD(Single Shot multibox Detector) model which is one of CNN(Convolutional Neural Networks) models. We propose to use all 3 channels rather than only one channel. A sliding window technique is also proposed to recognize the gesture in real time when the user actually makes a gesture. An experiment was conducted to measure the recognition rate and learning performance of the proposed model. Our proposed model showed 99.88% recognition accuracy and showed higher usability than the existing algorithm.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1459-1466
• /
• 2018

Robots which detect human and recognize action are important factors for human interaction, and many researches have been conducted. Recently, deep learning technology has developed and learning based robot's technology is a major research area. These studies require a database to learn and evaluate for intelligent human perception. In this paper, we propose a multi-modal sensor-based image database condition considering the security task by analyzing the image database to detect the person in the outdoor environment and to recognize the behavior during the running of the robot.

• 한국멀티미디어학회논문지
• /
• 제22권6호
• /
• pp.665-675
• /
• 2019

In this paper, we compare and analyze the classification performance of deep learning algorithm Convolutional Neural Network(CNN) ac cording to ensemble generation and combining techniques. We used several CNN models(VGG16, VGG19, DenseNet121, DenseNet169, DenseNet201, ResNet18, ResNet34, ResNet50, ResNet101, ResNet152, GoogLeNet) to create 10 ensemble generation combinations and applied 6 combine techniques(average, weighted average, maximum, minimum, median, product) to the optimal combination. Experimental results, DenseNet169-VGG16-GoogLeNet combination in ensemble generation, and the product rule in ensemble combination showed the best performance. Based on this, it was concluded that ensemble in different models of high benchmarking scores is another way to get good results.

• 한국멀티미디어학회논문지
• /
• 제24권4호
• /
• pp.528-537
• /
• 2021

Face recognition has gained significant notice because of its application in many businesses: security, healthcare, and marketing. In this paper, we will present the recognition method using the combination of correlation filters (CF) and Support Vector Machine (SVM). Firstly, we evaluate the performance and compared four different correlation filters: minimum average correlation energy (MACE), maximum average correlation height (MACH), unconstrained minimum average correlation energy (UMACE), and optimal-tradeoff (OT). Secondly, we propose the machine learning approach by using the OT correlation filter for features extraction and SVM for classification. The numerical results on National Cheng Kung University (NCKU) and Pointing'04 face database show that the proposed method OT-SVM gets higher accuracy in face recognition compared to other machine learning methods. Our approach doesn't require graphics card to train the image. As a result, it could run well on a low hardware system like an embedded system.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.67-74
• /
• 2021

As IoT(Internet Of Things) devices like a smart sensor have constrained power sources, a power strategy is critical in WSN(Wireless Sensor Networks). Therefore, it is necessary to figure out the residual power of each sensor node for managing power strategies in WSN, which, however, requires additional data transmission, leading to more power consumption. In this paper, a residual power estimation method was proposed, which uses ignorantly small amount of power consumption in the resource-constrained wireless networks including WSN. A residual power prediction is possible with the least data transmission by using Machine Learning method with some training data in this proposal. The performance of the proposed scheme was evaluated by machine learning method, simulation, and analysis.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.13-20
• /
• 2021

A Wasserstein GAN(WGAN), optimum in terms of minimizing Wasserstein distance, still suffers from inconsistent convergence or unexpected output due to inherent learning instability. It is widely known some kinds of restriction on the discriminative function should be considered to solve such problems, which implies the importance of Lipschitz continuity. Unfortunately, there are few known methods to satisfactorily maintain the Lipschitz continuity of the discriminative function. In this paper we propose techniques to stably maintain the Lipschitz continuity of the discriminative function by adding effective regularization terms to the objective function, which limit the magnitude of the gradient vectors of the discriminator to one or less. Extensive experiments are conducted to evaluate the performance of the proposed techniques, which shows the single-sided penalty improves convergence compared with the gradient penalty at the early learning process, while the proposed additional penalty increases inception scores by 0.18 after 100,000 number of learning.

• 한국멀티미디어학회논문지
• /
• 제24권3호
• /
• pp.345-354
• /
• 2021

Recently, deep learning-based image recognition systems have been adopted to various surveillance environments, but most of them are still picture-type object recognition methods, which are insufficient for the long term temporal analysis and high-dimensional situation management. Therefore, we propose a method recognizing the specific dangerous situation generated by human in real-time, and utilizing deep learning-based object analysis techniques. The proposed method uses deep learning-based object detection and tracking algorithms in order to recognize the situations such as 'trespassing', 'loitering', and so on. In addition, human's joint pose data are extracted and analyzed for the emergent awareness function such as 'falling down' to notify not only in the security but also in the emergency environmental utilizations.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.769-782
• /
• 2022

A study on agricultural automation became more important. In Korea, sweet persimmon farmers spend a lot of time and effort on classifying profitable persimmons. In this paper, we propose and implement an efficient grading algorithm for persimmons before shipment. We gathered more than 1,750 images of persimmons, and the images were graded and labeled for classifications purpose. Our main algorithm is based on EfficientDet object detection model but we implemented more exquisite method for better classification performance. In order to improve the precision of classification, we adopted a machine learning algorithm, which was proposed by PyCaret machine learning workflow generation library. Finally we acquired an improved classification model with the accuracy score of 81%.