• 반도체디스플레이기술학회지
• /
• 제9권3호
• /
• pp.59-63
• /
• 2010

This paper proposes computer visual inspection algorithms for various LCD defects which are found in a manufacturing process. Modular vision processing steps are required in order to detect different types of LCD defects. Those key modules include RGB filtering for pixel defects, gray-scale morphological processing and Hough transform for line defects, and adaptive threshold for spot defects. The proposed algorithms can give users detailed information on the type of defects in the LCD panel, the size of defect, and its location. The machine vision inspection system is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithms are quite successful.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.483-486
• /
• 2020

Age estimation and gender classification for human is a classic problem in computer vision. Almost research focus just only one task and the models are too heavy to run on low-cost system. In our research, we aim to apply multitasking learning to perform both task on a lightweight model which can achieve good precision on embedded system in the real time.

• 제어로봇시스템학회논문지
• /
• 제15권4호
• /
• pp.420-425
• /
• 2009

In this paper, image detection and recognition algorithms are studied with respect to embedded carrier system. There are many suggested techniques to detect and recognize objects. But they have the propensity to need much calculation for high hit rate. Advanced and modified method needs to study for embedded systems that low power consumption and real time response are requested. The proposed methods were implemented using Intel(R) Open Source Computer Vision Library provided by Intel Corporation. And they run and tested on embedded system using a ARM920T processor by cross-compiling. They showed 1.6sec response time and 95% hit rate and supported the automated moving carrier system smoothly.

• 제어로봇시스템학회논문지
• /
• 제20권7호
• /
• pp.741-749
• /
• 2014

This paper proposes a machine vision module for PLCs (Programmable Logic Controllers). PLC is the industrial controller most widely used in factory automation system. However most of the machine vision systems are based on PC (Personal Computer). The machine vision system embedded in PLC is required to reduce the cost and improve the convenience of implementation. In this paper, we newly propose a machine vision module based on PLC. The image processing libraries are implemented and integrated with the PLC programming tool. In order to interface the libraries with ladder programming, the ladder instruction set was also designed for each vision library. By use of the developed system, PLC users can implement vision systems easily by ladder programming. The developed system was applied to sample inspection system to verify the performance. The experimental results show that the proposed system can reduce the cost of installing as well as increase the ease-of-implementation.

• 한국정보통신학회논문지
• /
• 제25권3호
• /
• pp.490-493
• /
• 2021

This paper proposes an embedded system that detects mask and face recognition based on a microprocessor instead of Nvidia Jetson Board what is popular development kit. We use a class of efficient models called Mobilenets for mobile and embedded vision applications. MobileNets are based on a streamlined architechture that uses depthwise separable convolutions to build light weight deep neural networks. The device used a Maix development board with CNN hardware acceleration function, and the training model used MobileNet_V2 based SSD(Single Shot Multibox Detector) optimized for mobile devices. To make training model, 7553 face data from Kaggle are used. As a result of test dataset, the AUC (Area Under The Curve) value is as high as 0.98.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.1040-1043
• /
• 2020

본 논문에서는 골퍼의 자세 교정을 위해 레슨 프로 혹은 코치가 수행하는 교육을 담당하는 시스템을 구현한다. 이 시스템은 골프를 배우고자 하는 골퍼와 자세를 교정하고자 하는 골퍼를 대상으로 한다. 프로 골퍼의 스윙자세 영상을 촬영하고 딥러닝 라이브러리로 관절, 클럽의 위치를 디지털로 식별하여 표준 자세 정보를 입수한다. 그리고 사용자의 영상을 촬영하여 표준자세 정보와 비교 후 올바른 자세를 도표 및 시각적으로 제공 할 수 있도록 한다. 사람이 하는 방식 보다 객관적이고, 센서방식 보다 경제적인 시스템으로 골프교육산업의 활성화에 기여 할 수 있을 것이다.

• 한국정보통신학회논문지
• /
• 제21권7호
• /
• pp.1349-1354
• /
• 2017

본 논문에서는 임베디드 시스템에 활용할 수 있는 고속의 손동작 인식 알고리즘을 제안한다. 기존의 손동작 인식 알고리즘은 손의 윤곽선을 구성하는 모든 점을 추출하는 윤곽선 추적 과정의 계산복잡도가 높기 때문에 임베디드 시스템, 모바일 디바이스와 같은 저성능의 시스템에서의 활용에 어려움이 있었다. 제안하는 알고리즘은 윤곽선 추적 알고리즘을 사용하는 대신 동심원 추적을 응용하여 추상화된 손가락의 윤곽선을 추정한 다음 특징을 추출하여 손동작을 분류한다. 제안된 알고리즘은 평균 인식률은 95%이고 평균 수행시간은 1.29ms로서 기존의 윤곽선 추적 방식을 사용하는 알고리즘에 비해 최대 44%의 성능향상을 보였고 임베디드 시스템, 모바일 디바이스와 같은 저성능의 시스템에서의 활용가능성을 확인하였다.

• 한국위성정보통신학회논문지
• /
• 제10권2호
• /
• pp.70-74
• /
• 2015

본 논문은 위성통신 기반의 위성 영상감시 센서 네트워크 적용을 위한 스마트 비젼 센서에 대해 기술한다. 스마트 비젼센서 단말은 현장에서 산불, 연기, 침입자 움직임 등의 이벤트를 자동감지하면서 높은 성능 신뢰도, 견고한 하드웨어 내구성, 용이한 유지보수, 끊김없는 통신유지 기능들이 요구된다. 이러한 요구사항들을 만족시키기 위하여 스마트 비젼 센서가 내장된 초소형 위성통신 단말을 제안하며 위성 송수신 기능과 더불어 고 신뢰도의 임베디드 영상분석 및 영상압축 기능을 처리한다. 제안하는 비젼 센서 알고리즘의 컴퓨터 시뮬레이션과 비젼 센서 시제품 시험을 통하여 영상감시 성능을 검증하였으며 실용성을 확인하였다.

• 반도체디스플레이기술학회지
• /
• 제10권1호
• /
• pp.113-118
• /
• 2011

This paper proposes computer visual inspection algorithms for PCB defects which are found in a manufacturing process. The proposed method can detect open circuit and short circuit on bare PCB without using any reference images. It performs adaptive threshold processing for the ROI (Region of Interest) of a target image, median filtering to remove noises, and then analyzes connected components of the binary image. In this paper, the connected components of circuit pattern are defined as 6 types. The proposed method classifies the connected components of the target image into 6 types, and determines an unclassified component as a defect of the circuit. The analysis of the original target image detects open circuits, while the analysis of the complement image finds short circuits. The machine vision inspection system is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithms are quite successful.