• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.125-131
• /
• 2021

In recent years, Convolutional Neural Networks (CNNs) have achieved outstanding performance in the fields of computer vision such as image classification, object detection, visual quality enhancement, etc. However, as huge amount of computation and memory are required in CNN models, there is a limitation in the application of CNN to low-power environments such as mobile or IoT devices. Therefore, the need for neural network compression to reduce the model size while keeping the task performance as much as possible has been emerging. In this paper, we propose a method to compress CNN models by combining matrix decomposition methods of LR (Low-Rank) approximation and CP (Canonical Polyadic) decomposition. Unlike conventional methods that apply one matrix decomposition method to CNN models, we selectively apply two decomposition methods depending on the layer types of CNN to enhance the compression performance. To evaluate the performance of the proposed method, we use the models for image classification such as VGG-16, RestNet50 and MobileNetV2 models. The experimental results show that the proposed method gives improved classification performance at the same range of 1.5 to 12.1 times compression ratio than the existing method that applies only the LR approximation.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.321-326
• /
• 2019

As AI technology is recently introduced into various fields, it is being applied to the fashion field. This paper proposes a system for recommending cody clothes suitable for a user's selected clothes. The proposed system consists of user app, cody recommendation module, and server interworking of each module and managing database data. Cody recommendation system classifies clothing images into 80 categories composed of feature combinations, selects multiple representative reference images for each category, and selects 3 full body cordy images for each representative reference image. Cody images of the representative reference image were determined by analyzing the user's preference using Google survey app. The proposed algorithm classifies categories the clothing image selected by the user into a category, recognizes the most similar image among the classification category reference images, and transmits the linked cody images to the user's app. The proposed system uses the ResNet-50 model to categorize the input image and measures similarity using ORB and HOG features to select a reference image in the category. We test the proposed algorithm in the Android app, and the result shows that the recommended system runs well.

• Nuclear Engineering and Technology
• /
• v.50 no.2
• /
• pp.280-291
• /
• 2018

In the framework of OECD/NEA Working Group on Fuel Safety, a RIA fuel-rod-code Benchmark Phase I was organized in 2010-2013. It consisted of four experiments on highly irradiated fuel rodlets tested under different experimental conditions. This benchmark revealed the need to better understand the basic models incorporated in each code for realistic simulation of the complicated integral RIA tests with high burnup fuel rods. A second phase of the benchmark (Phase II) was thus launched early in 2014, which has been organized in two complementary activities: (1) comparison of the results of different simulations on simplified cases in order to provide additional bases for understanding the differences in modelling of the concerned phenomena; (2) assessment of the uncertainty of the results. The present paper provides a summary and conclusions of the second activity of the Benchmark Phase II, which is based on the input uncertainty propagation methodology. The main conclusion is that uncertainties cannot fully explain the difference between the code predictions. Finally, based on the RIA benchmark Phase-I and Phase-II conclusions, some recommendations are made.

• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.12-19
• /
• 2022

Artificial intelligence is driving the Fourth Industrial Revolution and is in the spotlight as a general-purpose technology. As the data collection from the battlefield increases rapidly, the need to us artificial intelligence is increasing in the military, but it is still in its early stages. In order to identify maritime targets, Republic of Korea navy acquires images by ISAR(Inverse Synthetic Aperture Radar) of maritime patrol aircraft, and humans make out them. The radar image is displayed by synthesizing signals reflected from the target after radiating radar waves. In addition, day/night and all-weather observations are possible. In this study, an artificial intelligence is used to identify maritime targets based on radar images. Data of radar images of 24 maritime targets in Republic of Korea and North Korea acquired by ISAR were pre-processed, and an artificial intelligence algorithm(ResNet-50) was applied. The accuracy of maritime targets identification showed about 99%. Out of the 81 warship types, 75 types took less than 5 seconds, and 6 types took 15 to 163 seconds.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.75-86
• /
• 2022

The existing image quality assessment (IQA) datasets have a small number of samples. Some methods based on transfer learning or data augmentation cannot make good use of image quality-related features. A No Reference (NR)-IQA method based on multi-task training and quality awareness is proposed. First, single or multiple distortion types and levels are imposed on the original image, and different strategies are used to augment different types of distortion datasets. With the idea of weak supervision, we use the Full Reference (FR)-IQA methods to obtain the pseudo-score label of the generated image. Then, we combine the classification information of the distortion type, level, and the information of the image quality score. The ResNet50 network is trained in the pre-train stage on the augmented dataset to obtain more quality-aware pre-training weights. Finally, the fine-tuning stage training is performed on the target IQA dataset using the quality-aware weights to predicate the final prediction score. Various experiments designed on the synthetic distortions and authentic distortions datasets (LIVE, CSIQ, TID2013, LIVEC, KonIQ-10K) prove that the proposed method can utilize the image quality-related features better than the method using only single-task training. The extracted quality-aware features improve the accuracy of the model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.3
• /
• pp.234-245
• /
• 2023

The Arena Fragmentation Test(AFT) is designed to analyze warhead performance by measuring fragmentation data. In order to evaluate the results of the AFT, a set of AFT images are captured by high-speed cameras. To detect objects in the AFT image set, ResNet-50 based Faster R-CNN is used as a detection model. However, because of the low resolution of the AFT image set, a detection model has shown low performance. To enhance the performance of the detection model, Super-resolution(SR) methods are used to increase the AFT image set resolution. To this end, The Bicubic method and three SR models: ZSSR, EDSR, and SwinIR are used. The use of SR images results in an increase in the performance of the detection model. While the increase in the number of pixels representing a fragment flame in the AFT images improves the Recall performance of the detection model, the number of pixels representing noise also increases, leading to a slight decreases in Precision performance. Consequently, the F1 score is increased by up to 9 %, demonstrating the effectiveness of SR in enhancing the performance of the detection model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.49-52
• /
• 2022

건물 외벽에 발생하는 균열은 시설물 구조 안전에 영향을 미치며 그 크기에 따라 위험도가 달라진다. 이에 따라 전문검사관의 현장 점검을 통해 발생 균열 두께를 정밀하게 측정할 필요가 있고 최근에는 이러한 현장 안전점검에 인공지능을 도입하려는 추세다. 그러나 기존의 균열 데이터셋은 주로 콘크리트에만 한정되어 다양한 외벽에 강인한 모델을 구축하기 어렵고 균열 두께를 측정하기 위해 정확한 마스크(Mask) 정보가 필요하나 이를 만족하는 데이터셋이 부재하다. 본 논문에서는 다양한 외벽에 강인한 균열 구획화 모델을 목적으로 2,744장의 이미지를 촬영하고 매직 완드 기법으로 라벨링을 진행해 데이터셋을 구축 후, 이를 바탕으로 딥러닝 기반 균열 구획화 모델을 개발했다. UNet-ResNet50을 최종모델로 선정 및 개발 결과, 테스트 데이터셋에 대해 81.22%의 class IoU 성능을 보였다. 본 연구의 기술을 바탕으로 균열 두께를 측정하여 건축물 안전점검에 활용될 수 있기를 기대한다.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.6
• /
• pp.15-22
• /
• 2023

In this study, We conduct a comparative study of deep learning-based classification of agricultural field attributes using Tagged Image File (TIF) and Enhanced Compression Wavelet (ECW) images. The goal is to interpret and classify the attributes of agricultural fields by analyzing the differences between these two image formats. "FarmMap," initiated by the Ministry of Agriculture, Food and Rural Affairs in 2014, serves as the first digital map of agricultural land in South Korea. It comprises attributes such as paddy, field, orchard, agricultural facility and ginseng cultivation areas. For the purpose of comparing deep learning-based agricultural attribute classification, we consider the location and class information of objects, as well as the attribute information of FarmMap. We utilize the ResNet-50 instance segmentation model, which is suitable for this task, to conduct simulated experiments. The comparison of agricultural attribute classification between the two images is measured in terms of accuracy. The experimental results indicate that the accuracy of TIF images is 90.44%, while that of ECW images is 91.72%. The ECW image model demonstrates approximately 1.28% higher accuracy. However, statistical validation, specifically Wilcoxon rank-sum tests, did not reveal a significant difference in accuracy between the two images.