• Journal of Information Processing Systems
• /
• 제2권3호
• /
• pp.178-182
• /
• 2006

Children exhibit different behaviors, skills, and motivations. The main aim of this research was to investigate children's sensibility factors for icons, and to look for the best typeface for application to Web-Based Instruction (WBI) for e-Learning. Three types of icons were used to assess children's sensibilities toward metaphors: text-image, representational, and spatial mapping. Through the factor analysis, we found that children exhibited more diverse reactions to the text-image and representational types of icons than to the spatial mapping type of icons. Children commonly showedn higher sensibilities to the aesthetic-factor than to the familiarity-factor or the brevity-factor. In addition, we propose a collaborative-typeface system, which recommends the best typeface for children regarding the readability and aesthetic factor in WBI. Based on these results, we venture some suggestions on icon design and typeface selection for e-Learning.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.265-271
• /
• 2022

Social media is a form of communication based on the internet to share information through content and images. Their choice of profile images and type of image they post can be closely connected to their personality. The user posted images are designated as personality traits. The objective of this study is to predict five factor model personality dimensions from profile images by using deep learning and neural networks. Developed a deep learning framework-based neural network for personality prediction. The personality types of the Big Five Factor model can be quantified from user profile images. To measure the effectiveness, proposed two models using convolution Neural Networks to classify each personality of the user. Done performance analysis among two different models for efficiently predict personality traits from profile image. It was found that VGG-69 CNN models are best performing models for producing the classification accuracy of 91% to predict user personality traits.

• 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.

• Smart Structures and Systems
• /
• 제28권6호
• /
• pp.799-810
• /
• 2021

When monitoring the structural integrity of a bridge using data collected through accelerometers, identifying the profile of the load exerted on the bridge from the vehicles passing over it becomes a crucial task. In this study, the speed and location of vehicles on the deck of a bridge is reconfigured using real-time video to implicitly associate the load applied to the bridge with the response from the bridge sensors to develop an image-based deep learning network model. Instead of directly measuring the load that a moving vehicle exerts on the bridge, the intention in the proposed method is to replace the correlation between the movement of vehicles from CCTV images and the corresponding response by the bridge with a neural network model. Given the framework of an input-output-based system identification, CCTV images secured from the bridge and the acceleration measurements from a cantilevered beam are combined during the process of training the neural network model. Since in reality, structural damage cannot be induced in a bridge, the focus of the study is on identifying local changes in parameters by adding mass to a cantilevered beam in the laboratory. The study successfully identified the change in the material parameters in the beam by using the deep-learning neural network model. Also, the method correctly predicted the acceleration response of the beam. The proposed approach can be extended to the structural health monitoring of actual bridges, and its sensitivity to damage can also be improved through optimization of the network training.

• 한국지리정보학회지
• /
• 제24권1호
• /
• pp.1-11
• /
• 2021

위성영상을 활용한 하천, 습지, 호수 등 지표수 객체의 탐지는 해당 지역의 수자원 관리 및 조사 업무에 효율적으로 활용될 수 있다. 본 연구에서는 원격탐사 분야에서 물을 탐지하기 위해 제공하는 수분지수(Water Index)와 영상으로부터 객체를 인식하는 데 폭넓게 활용되는 기계학습(Machine learning) 기법을 대구광역시를 촬영한 Landsat-8 위성영상에 개별적으로 적용하여 하천, 호수 등 다양한 지표수 객체를 탐지하고 그 결과를 비교하였다. 우선 Landsat-8 위성영상의 다중분광 밴드로부터 NDWI(Normalized Difference Water Index), MNDWI(Modified Normalized Difference Water Index) 영상을 생성하였고, 임계치를 적용하여 개별 영상으로부터 물과 그 외 지역을 구분할 수 있는 이진 영상(Binary image)을 제작하였다. 그리고 기계학습 기법인 SVM(Support Vector Machine)을 동일 위성영상에 적용하여 토지 피복 영상을 제작하고 이로부터 이진 영상을 제작하였다. 최종적으로 100개의 검사점(Checkpoints)을 사용하여 세 이진 영상으로부터 지표수 탐지를 위한 정확도를 오차 행렬을 활용하여 계산하였다. 그 결과, MNDWI 영상으로부터 제작된 이진 영상의 정확도(84%)가 NDWI 영상으로부터 제작된 이진 영상의 정확도(94%)와 SVM에 의해 제작된 이진 영상의 정확도(96%)에 비해 낮았으며, 모든 이진 영상에서 그림자 등의 원인으로 인해 일부 육지 분류 결과가 지표수 객체로 오분류되었다.

• 반도체디스플레이기술학회지
• /
• 제21권1호
• /
• pp.108-113
• /
• 2022

The deep-learning-based measurement method with the through-focus scanning optical microscopy (TSOM) estimated the size of the object using the classification. However, the measurement performance of the method depends on the number of subdivided classes, and it is practically difficult to prepare data at regular intervals for training each class. We propose an approach to measure the size of an object in the TSOM image using the deep-learning regression model instead of using classification. We attempted our proposed method to estimate the top critical dimension (TCD) of through silicon via (TSV) holes with 2461 TSOM images and the results were compared with the existing method. As a result of our experiment, the average measurement error of our method was within 30 nm (1σ) which is 1/13.5 of the sampling distance of the applied microscope. Measurement errors decreased by 31% compared to the classification result. This result proves that the proposed method is more effective and practical than the classification method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2590-2606
• /
• 2017

Generally, research of classical image classification algorithms assume that training data and testing data are derived from the same domain with the same distribution. Unfortunately, in practical applications, this assumption is rarely met. Aiming at the problem, a domain adaption image classification approach based on multi-sparse representation is proposed in this paper. The existences of intermediate domains are hypothesized between the source and target domains. And each intermediate subspace is modeled through online dictionary learning with target data updating. On the one hand, the reconstruction error of the target data is guaranteed, on the other, the transition from the source domain to the target domain is as smooth as possible. An augmented feature representation produced by invariant sparse codes across the source, intermediate and target domain dictionaries is employed for across domain recognition. Experimental results verify the effectiveness of the proposed algorithm.

• International Journal of Advanced Culture Technology
• /
• 제6권3호
• /
• pp.173-177
• /
• 2018

Masks are generated by adding different fonts of learning data characters in pixel unit, and pixel values belonging to each of the masks are divided into 3 groups. Using the directional expansion operators, we expand the text area of the test data character into 4 diagonal directions in order to create the boundary areas to distinguish it from the background area. A mask with a minimum average discordance is selected as the final recognition result by calculating the degree of discordance between the expanded test data and the masks. Image comparison using directional expansion operations more accurately recognizes test data through 4 subdivided recognition processes. It is also possible to expand the ranges of 3 groups of pixel values of masks more evenly such that new fonts can easily be added to the given learning data.

• 한국컴퓨터정보학회논문지
• /
• 제23권12호
• /
• pp.131-136
• /
• 2018

This paper proposes a computer-aided diagnostic algorithm in a non-invasive way. Currently, clinical diagnosis of jaundice is performed through blood sampling. Unlike the old methods, the non-invasive method will enable parents to measure newborns' jaundice by only using their mobile phones. The proposed algorithm enables high accuracy and quick diagnosis through machine learning. In here, we used the SVM model of machine learning that learned the feature extracted through image preprocessing and we used the international jaundice research data as the test data set. As a result of applying our developed algorithm, it took about 5 seconds to diagnose jaundice and it showed a 93.4% prediction accuracy. The software is real-time diagnosed and it minimizes the infant's pain by non-invasive method and parents can easily and temporarily diagnose newborns' jaundice. In the future, we aim to use the jaundice photograph of the newborn babies' data as our test data set for more accurate results.

• 대한의용생체공학회:의공학회지
• /
• 제44권2호
• /
• pp.118-124
• /
• 2023

Many recent studies have reported that the quality of input learning data was vital to the detection of regions of interest. However, due to a lack of research on the quality of learning data on lesion detetcting using gastroscopy, we aimed to quantify the impact of quality difference in endoscopic images to lesion detection models using Image Quality Assessment (IQA) algorithms. Through IQA methods such as BRISQUE (Blind/Referenceless Image Spatial Quality Evaluation), Laplacian Score, and PSNR (Peak Signal-To-Noise) algorithm on 430 sheets of high quality data (HQD) and 430 sheets of low quality data (PQD), we showed that there were significant differences between high and low quality images in lesion detecting through BRISQUE and Laplacian scores (p<0.05). The PSNR value showed 10.62±1.76 dB on average, illustrating the lower lesion detection performance of PQD than HQD. In addition, F1-Score of HQD showed higher detection performance at 77.42±3.36% while F1-Score of PQD showed 66.82±9.07%. Through this study, we hope to contribute to future gastroscopy lesion detection assistance systems that involve IQA algorithms by emphasizing the importance of using high quality data over lower quality data.