• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.99-104
• /
• 2022

Artificial intelligence is getting a crucial part of our lives with its incredible benefits. Machines outperform humans in recognizing objects in images, particularly in classifying people into correct age and gender groups. In this respect, age and gender classification has been one of the hot topics among computer vision researchers in recent decades. Deployment of deep Convolutional Neural Network(: CNN) models achieved state-of-the-art performance. However, the most of CNN based architectures are very complex with several dozens of training parameters so they require much computation time and resources. For this reason, we propose a new CNN-based classification algorithm with significantly fewer training parameters and training time compared to the existing methods. Despite its less complexity, our model shows better accuracy of age and gender classification on the UTKFace dataset.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.200-207
• /
• 2020

Recently, deep neural networks such as CNN are showing excellent performance in various fields such as image classification, object recognition, visual quality enhancement, etc. However, as the model size and computational complexity of deep learning models for most applications increases, it is hard to apply neural networks to IoT and mobile environments. Therefore, neural network compression algorithms for reducing the model size while keeping the performance have been being studied. In this paper, we apply few compression methods to CNN models and evaluate their performances in the embedded environment. For evaluate the performance, the classification performance and inference time of the original CNN models and the compressed CNN models on the image inputted by the camera are evaluated in the embedded board equipped with QCS605, which is a customized AI chip. In this paper, a few CNN models of MobileNetV2, ResNet50, and VGG-16 are compressed by applying the methods of pruning and matrix decomposition. The experimental results show that the compressed models give not only the model size reduction of 1.3~11.2 times at a classification performance loss of less than 2% compared to the original model, but also the inference time reduction of 1.2~2.21 times, and the memory reduction of 1.2~3.8 times in the embedded board.

• Electronics and Telecommunications Trends
• /
• v.31 no.3
• /
• pp.131-141
• /
• 2016

최근 알파고를 통해 인공지능 기술이 전 세계인의 이목을 집중시켰던 반면, 인공지능 연구자들은 인공지능 부활에 결정적 역할을 한 딥러닝 기술에 주목하고 있다. 딥러닝은 다계층 인공신경망 기반의 기계학습 기술로서 최근 컴퓨터 비전, 음성인식, 자연어 처리 분야에서 인식 성능을 높이는 데 중요한 역할을 하고 있다. 딥러닝 기술을 이용하여 기계가 수천만장의 이미지를 학습하여 객체를 인식하게 하고, 수천 시간의 음성 데이터를 학습하여 사람의 말을 알아듣게 처리하는 데에는 다수의 고성능 컴퓨터가 필요하다. 따라서 딥러닝에는 다수의 컴퓨터를 효율적으로 이용하기 위한 분산처리 기술이 필수적이며 관련 연구들이 활발히 진행되고 있다. 이에 본고는 다중 컴퓨터 노드들에서 딥러닝 모델을 분산처리할 수 있는 기존의 프레임워크들을 비교 분석하고 딥러닝 분산처리 기술에 대한 발전 방향을 전망한다.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.7
• /
• pp.31-37
• /
• 2023

Since tunnels are built underground, it is impossible to check visually the location and degree of deterioration of steel ribs. Therefore, in tunnel maintenance, GPR images are generally used to detect steel ribs. While research on GPR image analysis employing artificial neural networks has primarily focused on detecting underground pipes and road damage, there have been limited applications for analyzing tunnel GPR data, specifically for steel rib detection, both internationally and domestically. In this study, a one-step object detection algorithm called YOLO, based on a convolutional neural network, was utilized to automate the localization of steel ribs using GPR data. The performance of the algorithm is then analyzed. Two datasets were employed for the analysis. A dataset comprising 512 original images and another dataset consisting of 2,048 augmented images. The omission rate, which represents the ratio of undetected steel ribs to the total number of steel ribs, was 0.38% for the model using the augmented data, whereas the omission rate for the model using only the original data was 7.18%. Thus, from an automation standpoint, it is more practical to employ an augmented dataset.

• Management & Information Systems Review
• /
• v.38 no.3
• /
• pp.55-80
• /
• 2019

Recently, many companies improving their management performance by building a powerful brand value which is recognized for trademark rights. However, as growing up the size of online commerce market, the infringement of trademark rights is increasing. According to various studies and reports, cases of foreign and domestic companies infringing on their trademark rights are increased. As the manpower and the cost required for the protection of trademark are enormous, small and medium enterprises(SMEs) could not conduct preliminary investigations to protect their trademark rights. Besides, due to the trademark image search service does not exist, many domestic companies have a problem that investigating huge amounts of trademarks manually when conducting preliminary investigations to protect their rights of trademark. Therefore, we develop an intelligent similar trademark search model to reduce the manpower and cost for preliminary investigation. To measure the performance of the model which is developed in this study, test data selected by intellectual property experts was used, and the performance of ResNet V1 101 was the highest. The significance of this study is as follows. The experimental results empirically demonstrate that the image classification algorithm shows high performance not only object recognition but also image retrieval. Since the model that developed in this study was learned through actual trademark image data, it is expected that it can be applied in the real industrial environment.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.129-143
• /
• 2023

In the era of big data, the field of artificial intelligence is showing remarkable growth, and in particular, the image classification learning methods by deep learning are becoming an important area. Various studies have been actively conducted to further improve the performance of CNNs, which have been widely used in image classification, among which a representative method is the Convolutional Recurrent Neural Network (CRNN) algorithm. The CRNN algorithm consists of a combination of CNN for image classification and RNNs for recognizing time series elements. However, since the inputs used in the RNN area of CRNN are the flatten values extracted by applying the convolution and pooling technique to the image, pixel values in the same phase in the image appear in different order. And this makes it difficult to properly learn the sequence of arrangements in the image intended by the RNN. Therefore, this study aims to improve image classification performance by proposing a novel hybrid method of CNN and RNN applying the concepts of encoder and decoder. In this study, the effectiveness of the new hybrid method was verified through various experiments. This study has academic implications in that it broadens the applicability of encoder and decoder concepts, and the proposed method has advantages in terms of model learning time and infrastructure construction costs as it does not significantly increase complexity compared to conventional hybrid methods. In addition, this study has practical implications in that it presents the possibility of improving the quality of services provided in various fields that require accurate image classification.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.420-422
• /
• 2022

인공지능 기술이 문서 분류, 얼굴 인식, 자율 주행 등 실생활 전반에 걸쳐 다양한 분야에 적용됨에 따라, 인공지능 모델에 대한 취약점을 미리 파악하고 대비하는 기술의 중요성이 높아지고 있다. 이미지 영역에서는 입력 데이터에 작은 섭동을 추가해 신경망을 속이는 방법인 적대적 공격 연구가 활발하게 이루어졌지만, 텍스트 영역에서는 텍스트 데이터의 이산적인 특징으로 인해 연구에 어려움이 존재한다. 본 논문은 텍스트 분야 인공지능 기술에 대한 적대적 공격 기법을 분석하고 연구의 필요성을 살펴보고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.727-730
• /
• 2016

TSC means classifying time series data based on pattern. Time series data is quite common data type and it has high potential in many fields, so data mining and machine learning have paid attention for long time. In traditional approach, distance and dictionary based methods are quite popular. but due to time scale and random noise problems, it has clear limitation. In this paper, we propose a novel approach to deal with these problems with CNN and data mutation. CNN is regarded as proven neural network model in image recognition, and could be applied to time series pattern recognition by extracting pattern. Data mutation is a way to generate mutated data with different methods to make CNN more robust and solid. The proposed method shows better performance than traditional approach.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.545-559
• /
• 2020

In this paper, we propose a content creation framework that enables users without programming experience to easily create interactive media content that responds to user gestures. In the proposed framework, users define the gestures they use and the media effects that respond to them by numbers, and link them in a text-based configuration file. In the proposed framework, the interactive media content that responds to the user's gesture is linked with the dynamic projection mapping module to track the user's location and project the media effects onto the user. To reduce the processing speed and memory burden of the gesture recognition, the user's movement is expressed as a gray scale motion history image. We designed a convolutional neural network model for gesture recognition using motion history images as input data. The number of network layers and hyperparameters of the convolutional neural network model were determined through experiments that recognize five gestures, and applied to the proposed framework. In the gesture recognition experiment, we obtained a recognition accuracy of 97.96% and a processing speed of 12.04 FPS. In the experiment connected with the three media effects, we confirmed that the intended media effect was appropriately displayed in real-time according to the user's gesture.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.149-162
• /
• 2005

This paper suggest a way to detect a specific wanted figure in public places such as subway stations and banks by comparing color face images extracted from the real time CCTV with the face images of designated specific figures. Assuming that the characteristic of the surveillance camera allows the face information in screens to change arbitrarily and to contain information on numerous faces, the accurate detection of the face area was focused. To solve this problem, the normalization work using subsampling with $20{\times}20$ pixels on arbitrary face images, which is based on the Perceptron Neural Network model suggested by R. Rosenblatt, created the effect of recogning the whole face. The optimal linear filter and the histogram shaper technique were employed to minimize the outside interference such as lightings and light. The addition operation of the egg-shaped masks was added to the pre-treatment process to minimize unnecessary work. The images finished with the pre-treatment process were divided into three reception fields and the information on the specific location of eyes, nose, and mouths was determined through the neural network. Furthermore, the precision of results was improved by constructing the three single-set network system with different initial values in a row.