Cross Stage Partial Dilated Convolution Network for License Plate Recognition

Qingwang Wang,Haochen Song,Tao Shen,Zhiyi Liu,Zhimin Tao 제어·로봇·시스템학회 2024 International Journal of Control, Automation, and Vol.22 No.6

License plate recognition (LPR) is a crucial task in traffic management, but traditional methods face limitations in accuracy and speed that are mutually constraining. In this paper, we propose an efficient license plate recognition system that achieves high recognition accuracy while ensuring real-time recognition. In order to achieve high detection accuracy while minimizing computational effort in the license plate detection stage, we propose a lightweight cross stage partial dilated convolution (CSPDC) network. Firstly, we propose a lightweight downsampling design that reduces the computational effort of downsampling while retaining important feature information. Secondly, we introduce a lightweight feature extraction network that reduces computational effort and parameter count while maintaining the network’s feature extraction capability. Finally, to prevent a decrease in detection performance after lightweight processing, we propose a cross stage partial dilated block that expands the receptive field of feature extraction to enhance the network’s learning capability. Experimental results on the CCPD dataset demonstrate that our proposed system achieves a tradeoff between computational effort and accuracy, with an ACC of 99.3% and a detection speed of 89 FPS. We further deployed and tested our algorithm on the Huawei M6 tablet, and the test results shows the practical value of our proposed method.

End-to-end recognition of slab identification numbers using a deep convolutional neural network

Lee, Sang Jun,Yun, Jong Pil,Koo, Gyogwon,Kim, Sang Woo Elsevier 2017 Knowledge-based systems Vol.132 No.-

<P><B>Abstract</B></P> <P>This paper proposes a novel algorithm for the end-to-end recognition of slab identification numbers (SINs). In the steel industry, automatic recognition of an individual product information is important for production management. The recognition of SINs in actual factory scenes is a challenging problem due to complicated background and low-quality of characters. Conventional rule-based algorithms were developed to extract information of SINs, but these methods require engineering knowledge and tedious work for parameter tuning. The proposed algorithm employs a data-driven method to overcome these limitations and to handle the challenges for the recognition of SINs. This paper proposes accumulated response map and model-based score function to effectively use the outputs of a deep convolutional neural network. Experiments were thoroughly conducted for industrial data collected from an actual steelworks to verify the effectiveness of the proposed algorithm. Experiment results demonstrate that simultaneous recognition of entire characters in a SIN by optimizing the model-based score function is more effective for the robust performance compared to separated recognition of individual characters.</P>

4차 산업혁명 기술에 기반한 농업 기상 정보 시스템의 요구도 분석

김광수,유병현,현신우,강대균 한국농림기상학회 2019 한국농림기상학회지 Vol.21 No.3

Efforts have been made to introduce the climate smart agriculture (CSA) for adaptation to future climate conditions, which would require collection and management of site specific meteorological data. The objectives of this study were to identify requirements for construction of agricultural meteorology information service system (AMISS) using technologies that lead to the fourth industrial revolution, e.g., internet of things (IoT), artificial intelligence, and cloud computing. The IoT sensors that require low cost and low operating current would be useful to organize wireless sensor network (WSN) for collection and analysis of weather measurement data, which would help assessment of productivity for an agricultural ecosystem. It would be recommended to extend the spatial extent of the WSN to a rural community, which would benefit a greater number of farms. It is preferred to create the big data for agricultural meteorology in order to produce and evaluate the site specific data in rural areas. The digital climate map can be improved using artificial intelligence such as deep neural networks. Furthermore, cloud computing and fog computing would help reduce costs and enhance the user experience of the AMISS. In addition, it would be advantageous to combine environmental data and farm management data, e.g., price data for the produce of interest. It would also be needed to develop a mobile application whose user interface could meet the needs of stakeholders. These fourth industrial revolution technologies would facilitate the development of the AMISS and wide application of the CSA. 기상 및 기후 정보를 활용하여 기후변화에 대응하기 위한 기후 스마트 농업을 도입하기 위한 노력이 진행되어 왔다. 기후 스마트 농업을 실현하기 위해 농가별 기상자료 수집 및 관리가 요구된다. 4차 산업혁명 시대의 주요한 기술인 IoT, 인공지능, 및 클라우드 컴퓨팅 기술들이 농가 단위의 기상정보 생산에 적극적으로 활용될 수 있다. 저비용과 저전력 특성을 가진 IoT 센서들로 무선 센서 네트워크를 구축할 경우, 농가나 농촌 공동체 수준에서 농업 생태계의 생산성을 파악할 수 있는 기상관측자료의 수집 및 분석이 가능하다. 무선 센서 네트워크를 통해 자료가 수집될 수 있는 공간적인 범위를 특정 농가보다는 농촌 공동체 수준으로 확대하여 IoT 기술의 수혜 농가를 확대하고, 아울러 상세기상정보의 생산 및 검증에 활용가능한 농업기상 빅데이터 구축이 필요하다. 기존에 개발되어 보급되고 있는 전자기후도를 활용하여, 농가 단위의 기상 추정 자료가 제공되고 있다. 이들 자료의 신뢰성을 향상시키고, 기존의 서비스 체계에서 제공되지 않고 있는 기상 변수들을 지원하기 위해 심층신경망과 같은 인공지능 기술들이 도입되어야 할 것이다. 시스템 구축의 비용 절감 및 활용성 증대를 위해 클라우드 및 포그 컴퓨팅 기술을 도입하여 농업 기상 정보 서비스 시스템이 설계되어야 한다. 또한, 기상자료와 농산물 가격 정보와 같은 환경자료와 경영정보를 동시에 제공할 수 있는 정보 시스템을 구축하여 활용도가 높은 농업 기상 서비스 시스템이 구축되어야 할 것이다. 이와 함께, 농업인 뿐만 아니라 소비자까지도 고려된 모바일 어플리케이션의 설계 및 개발을 통해, 4차 산업혁명의 주요 기술들이 농업 분야에서 확산될 수 있도록 지속적인 노력이 필요하다. 이러한 정보 시스템은 농업 분야 이해당사자에게 수요자 맞춤형 농림기상정보를 제공하여 기후스마트 농업 관련 기술의 개발과 도입을 촉진시킬 수 있을 것이다.

순환신경망을 이용한 한글 필기체 인식

김병희(Byoung-Hee Kim),장병탁(Byoung-Tak Zhang) 한국정보과학회 2017 정보과학회 컴퓨팅의 실제 논문지 Vol.23 No.5

온라인 방식의 한글 필기체 인식 문제를 분석하고 순환신경망 기반의 해법을 모색한다. 한글 낱글자 인식 문제를 순서데이터 레이블링의 관점에서 서열 분류, 구간 분류, 시간별 분류의 세 단계로 구분하여 각각에 대한 해법을 살펴보며, 한글의 구성 원리를 고려한 해결 방안을 정리한다. 한글 2350글자에 대한 온라인 필기체 데이터에 GRU(gated recurrent unit)의 다층 구조를 가지는 서열 분류모델을 적용한 결과, 낱글자 인식 정확도는 86.2%, 초・중・종성 구성에 따른 6가지 유형 분류 정확도는 98.2%로 측정되었다. 유형 분류 모델로 획의 진행에 따른 유형 변화 역시 높은 정확도로 인식하는 결과를 통해, 순환신경망을 이용하여 순서 데이터에서 한글의 구조와 같은 고차원적 지식을 학습할 수 있음을 확인하였다. We analyze the online Hangul handwriting recognition problem (HHR) and present solutions based on recurrent neural networks. The solutions are organized according to the three kinds of sequence labeling problem - sequence classifications, segment classification, and temporal classification, with additional consideration of the structural constitution of Hangul characters. We present a stacked gated recurrent unit (GRU) based model as the natural HHR solution in the sequence classification level. The proposed model shows 86.2% accuracy for recognizing 2350 Hangul characters and 98.2% accuracy for recognizing the six types of Hangul characters. We show that the type recognizing model successfully follows the type change as strokes are sequentially written. These results show the potential for RNN models to learn high-level structural information from sequential data.

Review on the Recent Welding Research with Application of CNN-Based Deep Learning Part I: Models and Applications

Kidong Lee(이기동),Sung Yi(이성),Soongkeun Hyun(현승균),Cheolhee Kim(김철희) 대한용접·접합학회 2021 대한용접·접합학회지 Vol.39 No.1

During machine learning algorithms, deep learning refers to a neural network containing multiple hidden layers. Welding research based upon deep learning has been increasing due to advances in algorithms and computer hardwares. Among the deep learning algorithms, the convolutional neural network (CNN) has recently received the spotlight for performing classification or regression based on image input. CNNs enables end-to-end learning without feature extraction and in-situ estimation of the process outputs. In this paper, 18 recent papers were reviewed to investigate how to apply CNN models to welding. The papers was classified into 5 groups: four for supervised learning models and one for unsupervised learning models. The classification of supervised learning groups was based on the application of transfer learning and data augmentation. For each paper, the structure and performance of its CNN model were described, and also its application in welding was explained.

안드로이드 악성코드 탐지를 위한 머신러닝 기술 활용 동향 및 권한정보를 활용한 악성코드 탐지

김기윤,김소람,전용진,김종성 한국디지털포렌식학회 2020 디지털 포렌식 연구 Vol.14 No.3

With the recent increase in the smartphone market, the number of detections of infringement accidents against mobile malwares continues to increase. In addition to the purpose of stealing personal information, malwares for occupying resources of smartphones are emerging, and accordingly, techniques for detecting various types of malwares are required. However, unlike PC, mobile has various limitations. This makes it difficult for malwares to act and detection, thus efficient malware detection techniques using limited resources are being developed. The malware detection techniques include signature-based and cloud server-based methods. However, such a malware detection has a limitation in that it is difficult to quickly detect variants of known malwares or new ones, and there is a risk of interfering with or removing the detection method through an elevation attack. In addition, a result in incorrect analysis may be received due to a network communication problem. For this reason, research on next-generation heuristic detection techniques based on machine learning is increasing in recent years. This paper introduces various Android-based malware detection techniques developed from 2012 to 2020, and analyzes the trend of changes in algorithms used for detection. In addition, it classifies the data used for learning in machine learning, organizes the features of algorithms suitable for learning, and finally presents the result of detecting malwares using a deep artificial neural network and authority. 최근 스마트폰 시장이 증가함에 따라 모바일 악성코드에 대한 침해사고 탐지 건수가 지속해서 증가하고 있다. 사용자의 개인정보 탈취 목적 외에도 고도화된 스마트폰의 자원 점유를 목적으로 하는 악성코드가 출현하고 있으며 이에 따라 다양한 종류의 악성코드를 탐지하기 위한 기법이 요구되고 있다. 하지만 PC와 달리 모바일은 다양한 제약이 존재한다. 이는 악성코드가 활동하기 힘들게 만듦과 동시에 탐지 또한 어려워짐에 따라 한정된 자원을 사용한 효율적인 악성코드 탐지 기법이 개발되고 있다. 주된 악성코드 탐지 기법에는 시그니처 기반과 빅데이터를 기반으로 하는 클라우드 서버 기반의 탐지 방법이 존재한다. 하지만 이러한 악성코드 탐지 기법은 신종 및 변종 악성코드에 대한 신속한 대응이 어렵다는 한계점이 존재하며 권한 상승 공격을 통해 탐지 기법을 방해하거나 제거해버릴 위험성이 존재한다. 또한, 네트워크 통신의 문제로 잘못된 분석 결과를 응답받을 수도 있다. 이러한 이유로 최근에는 머신러닝 기반의 차세대 휴리스틱 탐지 기법에 대한 연구가 증가하고 있다. 본 논문에서는 2012년~2020년에 개발된 다양한 안드로이드 기반 악성코드 탐지 기법을 소개하며, 탐지에 사용한 알고리즘의 변화추세를 분석한다. 또한, 머신러닝에 학습을 위해 사용하는 데이터를 분류하고, 학습에 적합한 알고리즘들에 대한 특징을 정리하였으며 마지막으로 심층 인공신경망 및 권한 기반을 활용해 악성코드를 탐지한 결과를 제시한다.

딥러닝 알고리즘을 이용한 토마토에서 발생하는 여러가지 병해충의 탐지와 식별에 대한 웹응용 플렛폼의 구축

나명환 ( Na¸ Myung Hwan ),조완현 ( Cho¸ Wanhyun ),김상균 ( Kim¸ Sangkyoon ) 한국품질경영학회 2020 품질경영학회지 Vol.48 No.4

Purpose: purpose of this study was to propose the web application platform which can be to detect and discriminate various diseases and pest of tomato plant based on the large amount of disease image data observed in the facility or the open field. Methods: The deep learning algorithms uesed at the web applivation platform are consisted as the combining form of Faster R-CNN with the pre-trained convolution neural network (CNN) models such as SSD_mobilenet v1, Inception v2, Resnet50 and Resnet101 models. To evaluate the superiority of the newly proposed web application platform, we collected 850 images of four diseases such as Bacterial cankers, Late blight, Leaf miners, and Powdery mildew that occur the most frequent in tomato plants. Of these, 750 were used to learn the algorithm, and the remaining 100 images were used to evaluate the algorithm. Results: From the experiments, the deep learning algorithm combining Faster R-CNN with SSD_mobilnet v1, Inception v2, Resnet50, and Restnet101 showed detection accuracy of 31.0%, 87.7%, 84.4%, and 90.8% respectively. Finally, we constructed a web application platform that can detect and discriminate various tomato deseases using best deep learning algorithm. If farmers uploaded image captured by their digital cameras such as smart phone camera or DSLR (Digital Single Lens Reflex) camera, then they can receive an information for detection, identification and disease control about captured tomato disease through the proposed web application platform. Conclusion: Incheon Port needs to act actively paying

The role of artificial neural network and machine learning in utilizing spatial information

Akash Goel,Amit Kumar Goel,Adesh Kumar 대한공간정보학회 2023 Spatial Information Research Vol.31 No.3

In this age of the fourth industrial revolution 4.0, the digital world has a plethora of data, including the internet of things, mobile, cybersecurity, social media, forecasts, health data, and so on. The expertise of machine learning and artificial intelligence (AI) is required to soundly evaluate the data and develop related smart and automated applications, These fields use a variety of machine learning techniques including supervised, unsupervised, and reinforcement learning. The objective of the study is to present the role of artificial neural networks and machine learning in utilizing spatial information. Machine learning and AI play an increasingly important role in disaster risk reduction from hazard mapping and forecasting severe occurrences to real-time event detection, situational awareness, and decision assistance. Some of the applications employed in the study to analyze the various ANN domains included weather forecasting, medical diagnosis, aerospace, facial recognition, stock market, social media, signature verification, forensics, robotics, electronics hardware, defense, and seismic data gathering. Machine learning determines the many prediction models for problems involving classification, regression, and clustering using known variables and locations from the training dataset, spatial data that is based on tabular data creates different observations that are geographically related to one another for unknown factors and places. The study presents that the Recurrent neural network and convolutional neural network are the best method in spatial information processing, healthcare, and weather forecasting with greater than 90% accuracy.

CNN을 이용한 익형의 공력 성능 예측

강종현(Jonghyeon Kang),이재국(JaeGook Lee),이해찬(Haechan Lee),안존(Jon Ahn) 한국항공우주학회 2019 한국항공우주학회 학술발표회 논문집 Vol.2019 No.11

제조분야 자동 품질 검사를 위한 딥러닝 기반 대형 이미지 분류시스템 개발 및 구축

김진호,권준우,황보유정,이경전 한국지능정보시스템학회 2018 한국지능정보시스템학회 학술대회논문집 Vol.2018 No.11