• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3364-3382
• /
• 2023

Remote sensing image segmentation plays an important role in realizing intelligent city construction. The current mainstream segmentation networks effectively improve the segmentation effect of remote sensing images by deeply mining the rich texture and semantic features of images. But there are still some problems such as rough results of small target region segmentation and poor edge contour segmentation. To overcome these three challenges, we propose an improved semantic segmentation model, referred to as MRU-Net, which adopts the U-Net architecture as its backbone. Firstly, the convolutional layer is replaced by BasicBlock structure in U-Net network to extract features, then the activation function is replaced to reduce the computational load of model in the network. Secondly, a hybrid multi-scale recognition module is added in the encoder to improve the accuracy of image segmentation of small targets and edge parts. Finally, test on Massachusetts Buildings Dataset and WHU Dataset the experimental results show that compared with the original network the ACC, mIoU and F1 value are improved, and the imposed network shows good robustness and portability in different datasets.

• Journal of Korea Multimedia Society
• /
• v.14 no.9
• /
• pp.1125-1137
• /
• 2011

Recently, there have been previous research about the iris recognition in mobile device to increase portability, whose accuracy is affected by the quality of iris image. Iris image is affected by illumination environment during the image acquisition. The existing system has high accuracy in indoor environment. However the accuracy is degraded in outdoor environment, because the gray levels of iris patterns in image are changed, and ghost and eyelash shading regions are produced by the sunlight of various wavelengths into iris region. To overcome these problems, we propose new mobile iris camera system which uses the near-infrared (NIR) light illuminator of 850 nm and band pass filter (BPF) of 850 nm. To measure the performance of the proposed system, we compared it to the existing one with the iris images captured in indoor and outdoor sunlight environments in terms of the equal error rates (EER) based on false acceptance rate (FAR) and false rejection rate (FRR). The experimental result showed that the proposed system had the lower EERs than those of previous system by 0.96% (with frontal light in indoors), 4.94% (with frontal light in outdoor), 9.24% (with side light in outdoor), and 7% (with back light in outdoor), respectively.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.10
• /
• pp.139-147
• /
• 2015

Steady state visual evoked potential (SSVEP) has been actively studied because of its short training time, relatively higher signal-to-noise ratio, and higher information transfer rate. There are two popular analysis methods for SSVEP signals: power spectral density analysis (PSDA) and canonical correlation analysis (CCA). However, the PSDA is known to be vulnerable to noise due to the use of a single channel. Although conventional CCA is more accurate than PSDA, it may not be appropriate for the real-time SSVEP-based BCI system when it has short time window length because it uses sinusoidal signals as references. Therefore, the two methods are not efficient for the real-time BCI system that requires a short TW and a high recognition accuracy. To overcome this limitation of the conventional methods, this paper proposes a frequency recognition method with a combination of CCA and PSDA using the difference between powers of canonical variables obtained from the results of CCA. Experimental results show that the performance of the combination of CCA and PSDA is better than that of CCA for the case of a short TW.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.3
• /
• pp.747-754
• /
• 2014

In spite of its usefulness for health monitoring of structures on steady external load, the statistical pattern recognition technology (SPRT), based on Mahalanobis distance theory (MDT), is not good enough for the health monitoring of structures on large variability external load like earthquake. Damage is usually determined by the difference between the average measured value of undamaged structure and the measure value of damaged one. So when external variability gets larger, the difference gets bigger along, which is thus easily mistaken for a damage. This paper aims to overcome the problem and develop an improved Mahalanobis distance theory (IMDT), that is, a SPRT with revised MDT in order to decrease external variability so that we will be able to continue to monitor the structure on uncertain external variability. This method is experimentally tested to see if it precisely evaluates the health of a cable-stayed bridge on each general random load and earthquake load. As a result, the IMDT is found to be valid in locating structural damage made by damaged cables by means of data from undamaged cables. So it is proved to be effectively applicable to the health monitoring of bridges on external load of variability.

• Journal of Science Education
• /
• v.41 no.2
• /
• pp.179-194
• /
• 2017

The purpose of this study is to construct two equivalent science relevance recognition test tool after confirming the reliability and validity of the CARS(Changes in Attitude of Relevance to Science) questionnaire to determine the applicability of the items to Korean students and to compare gender and school differences. For this study, 59 items of the CARS scientific relevance test were translated and assigned to 787 middle and high school students (analyed the answer of 300 middle school students and 431 high school students). In order to determine the fit of the CARS question to Korean students and to overcome the limitation of the number of questions, we used the item-linking method of the Rasch model. By analyzing the results of the research, we constructed two equivalent scientific relevance recognition questionnaires of CARS-A and CARS-B with 25 items. The Pearson correlation coefficient of the Rasch scores of the two equivalent test was 0.78. The two types of scientific relevance recognition test tools generated through this study can be used to confirm students' attitude of scientific relevance to daily life, or to confirm the change after a certain class or grade. Through this study, we will discuss the implications of students' perceptions of science associations in science education, and the development and application of tools.

• Journal of the Korean Society of Safety
• /
• v.35 no.5
• /
• pp.74-85
• /
• 2020

Smart phone zombie or Smombie means pedestrians who walk without attention to their surroundings because they are focused upon their smart phone. Because the traffic accidents and injuries caused by Smombie have been increased rapidly in recent years, the social attention and policies are needed to prevent it. This study was conducted to analyze Smombie's current status and some solutions used before and to propose new improved method through the latest ICT trend. In this study, we did the field survey to check Smombies at several places in Seoul through people counting, and found that a lot of pedestrians still use the smart phone while walking. And we analyzed many case studies about some solutions to prevent Smombies previously. The case studies include legal regulations, government policies, smart phone app services and facilities that are used before. We studied them through internet searches and reference studies and we also checked the current operating situation as visiting several places that the solutions actually has been operated. Therefore, we found there are some limitations in previous solutions in terms of effectiveness and management. To consider new solution that can be expected to overcome the limitations, we analyzed the latest ICT trends focused on features to utilize the Smombie prevention, especially video recognition and digital signage. In these days, video recognition has been developed rapidly with assistance of AI technology and it can recognize the specific pedestrian's characteristics such as holding smart phone as well as hair style, clothes, backpack and etc. On the other hands, the digital signage is the convergence device that includes big display, network connection and various IoT sensors. It can be used as public media in many places for public services as well as advertising. Through these analysis results, we show the requirements and the user scenario for the improved method to prevent Smombie. Finally, we propose to develop R&D technology to recognize Smombie exactly as pedestrian attributes and to spread creative contents to increase pedestrian's interest and engagement for Smombie prevention through digital signage.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.385-391
• /
• 2022

Quality evaluation of beef carcasses is an important issue in the livestock industry. Recently, through the AI monitor system based on artificial intelligence, the quality manager can receive help in making accurate decisions based on the analysis of beef carcass images or result information. This artificial intelligence dataset is an important factor in judging performance. Existing datasets may have different surface orientation or resolution. In this paper, we proposed a two-stage classification model that can efficiently manage the grades of beef carcass image using deep learning. And to overcome the problem of the various conditions of the image, a new dataset of 1,300 images was constructed. The recognition rate of deep network for 5-grade classification using the new dataset was 72.5%. Two-stage evaluation is a method to increase reliability by taking advantage of the large difference between grades 1++, 1+, and grades 1 and 2 and 3. With two experiments using the proposed two stage model, the recognition rates of 73.7% and 77.2% were obtained. As this, The proposed method will be an efficient method if we have a dataset with 100% recognition rate in the first stage.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.6
• /
• pp.1-9
• /
• 2007

Recently, as a number of media are fused into a phone, the requirement of security of service provided on a mobile phone is increasing. For this, conventional cryptographic key based on password and security card is used in the mobile phone, but it has the characteristics which is easy to be vulnerable and to be illegally stolen. To overcome such a problem, the researches to generate key based on biometrics have been done. However, it has also the problem that biometric information is susceptible to the variation of environment, whereas conventional cryptographic system should generate invariant cryptographic key at any time. So, we propose new method of producing cryptographic key based on "Biometric matching-based key release" instead of "Biometric-based key generation" by using both face and iris information in order to overcome the unstability of uni-modal biometries. Also, by using mega-pixel camera embedded on mobile phone, we can provide users with convenience that both face and iris recognition is possible at the same time. Experimental results showed that we could obtain the EER(Equal Error Rate) performance of 0.5% when producing cryptographic key. And FAR was shown as about 0.002% in case of FRR of 25%. In addition, our system can provide the functionality of controlling FAR and FRR based on threshold.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.141-146
• /
• 2018

Recently, location recognition technology has attracted much attention, especially for locating people or objects in an indoor environment without being influenced by the surrounding environment GPS technology is widely used as a method of recognizing the position of an object or a person. GPS is a very efficient, but it does not allow the positions of objects or people indoors to be determined. RFID is a technology that identifies the location information of a tagged object or person using radio frequency information. In this study, an RFID system is constructed and the position is measured using tags. At this time, an error occurs between the actual and measured positions. To overcome this problem, a neural network is trained using the measured and actual position data to reduce the error. In this case, since the number of read tags is not constant, they are not suitable as input values for training the neural network, so the neural network is trained by converting them into center-of-gravity inputs and median value inputs. This allows the position error to be reduce by the neural network. In addition, different numbers of trained data are used, viz. 50, 100, 200 and 300, and the correlation between the number of data input values and the error is checked. When the training is performed using the neural network, the errors of the center-of-gravity input and median value input are compared. It was found that the greater the number of trained data, the lower the error, and that the error is lower when the median value input is used than when the center-of-gravity input is used.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.295-302
• /
• 2010

Example-based super resolution(EBSR) is a method to reconstruct high-resolution images by learning patch-wise correspondence between high-resolution and low-resolution images. It can reconstruct a high-resolution from just a single low-resolution image. However, when it is applied to a text image whose font type and size are different from those of training images, it often produces lots of noise. The primary reason is that, in the patch matching step of the reconstruction process, input patches can be inappropriately matched to the high-resolution patches in the patch dictionary. In this paper, we propose a new patch matching method to overcome this problem. Using an image observation model, it preserves the correlation between the input and the output images. Therefore, it effectively suppresses spurious noise caused by inappropriately matched patches. This does not only improve the quality of the output image but also allows the system to use a huge dictionary containing a variety of font types and sizes, which significantly improves the adaptability to variation in font type and size. In experiments, the proposed method outperformed conventional methods in reconstruction of multi-font and multi-size images. Moreover, it improved recognition performance from 88.58% to 93.54%, which confirms the practical effect of the proposed method on recognition performance.