• 한국인터넷방송통신학회논문지
• /
• 제18권6호
• /
• pp.269-276
• /
• 2018

OCR(광학문자인식)은 컴퓨터 분야에 적용된 지 20년의 역사가 되었고, 자동차 번호판 인식을 통한 주차관리 등 여러 분야에서 응용되어왔다. 본 OCR 기반 스마트 가계부 앱 개발연구에서도 이 기술을 이용하였다. 스마트폰 기반 가계부에서 구매 내역을 수기로 일일이 기입하는 불편을 개선하고자 카메라로 영수증을 촬영해서 구입 목록을 자동으로 정리할 수 있도록 하였다. 이 과정에서 기존의 OCR 기술만으로 영수증의 이미지 문자를 판독하면 인식률이 떨어져서 영상처리기술을 이용하여 영수증 사진의 대비를 조절하는 방법으로 영수증의 문자 인식률을 89%에서 92.5%로 향상하였다.

• 드라이브 ㆍ 컨트롤
• /
• 제18권4호
• /
• pp.9-18
• /
• 2021

This study proposes a method for creating learning datasets to recognize obstacles using deep learning algorithms in automated construction machinery or an autonomous vehicle. Recently, many researchers and engineers have developed various recognition algorithms based on deep learning following an increase in computing power. In particular, the image classification technology and image segmentation technology represent deep learning recognition algorithms. They are used to identify obstacles that interfere with the driving situation of an autonomous vehicle. Therefore, various organizations and companies have started distributing open datasets, but there is a remote possibility that they will perfectly match the user's desired environment. In this study, we created an interface of the virtual simulator such that users can easily create their desired training dataset. In addition, the customized dataset was further advanced by using the RDBMS system, and the recognition rate was improved.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.505-507
• /
• 2021

영상 인식 기술은 인공지능 기술을 기반으로 인식하고자하는 객체의 형상, 객체 주변의 환경변화 및 객체 회전에 의한 인식 능력 저하를 보완할 수 있는 객체특징점 및 특징 기술자를 생성하고, 생성된 특징 기술자를 이용하여, 영상 객체를 인식하는 기술로, 일반적으로 영상에 나타난 객체를 인식하는 기술을 뜻한다. 스마트 안전 축사에서 전력소비 및 화재 발생 복합 환경 분석을 위해 설치되는 전력화재 관리 디바이스를 통합 관리함으로써 축사 전력 사용의 효율성 향상 및 전기 사용의 과부화로 발생할 수 있는 사고를 방지하여 축산 농가의 이익 증대 및 피해를 최소화하고 안전하고 최적화된 지능형 스마트 안전 축사를 개발하여 보급하는데 요구되는 전력 관리 프레임워크를 구현하는데 목적이 있다.

• 문화기술의 융합
• /
• 제10권3호
• /
• pp.909-914
• /
• 2024

본 연구에서는 로봇 비전용 영상 인식을 비롯한 다양한 AI 분야에서 널리 활용되는 전이학습에 대한 정량적 평가를 제시하였다. 전이학습을 적용한 연구 결과에 대한 정량적, 정성적 분석은 제시되나, 전이학습 자체에 대해서는 논의되지 않는다. 따라서 본 연구에서는 전이학습 자체에 대한 정량적 평가를 숫자 손글씨 데이터베이스인 MNIST를 기반으로 제안한다. 기준 네트워크를 대상으로 전이학습 동결층의 깊이 및 전이학습 데이터와 사전 학습 데이터의 비율에 따른 정확도 변화를 추적하였다. 이를 통해 첫번째 레이어까지 동결할 때 전이학습 데이터의 비율이 3% 이상일 경우, 90% 이상의 정확도를 안정적으로 유지할 수 있음이 확인되었다. 본 연구의 전이학습 정량 평가 방법은 향후 네트워크 구조와 데이터의 종류에 따라 최적화된 전이학습을 구현하는데 활용 가능하며, 다양한 환경에서 로봇 비전 및 이미지 분석 AI의 활용 범위를 확대할 것이다.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.107-109
• /
• 2004

In this paper, authors propose the sensor fusion system that can recognize multiple 3D objects from 2D projection images and tactile information. The proposed system focuses on improving recognition performance of 3D object. Unlike the conventional object recognition system that uses image sensor alone, the proposed method uses tactual sensors in addition to visual sensor. Neural network is used to fuse these informations. Tactual signals are obtained from the reaction force by the pressure sensors at the fingertips when unknown objects are grasped by four-fingered robot hand. The experiment evaluates the recognition rate and the number of teaming iterations of various objects. The merits of the proposed systems are not only the high performance of the learning ability but also the reliability of the system with tactual information for recognizing various objects even though visual information has a defect. The experimental results show that the proposed system can improve recognition rate and reduce learning time. These results verify the effectiveness of the proposed sensor fusion system as recognition scheme of 3D object.

• 대한인간공학회지
• /
• 제30권1호
• /
• pp.195-202
• /
• 2011

Objective: The aim of this study is to investigate and review the previous researches about objective measuring fatigue caused by visual stimuli. Also, we analyze possibility of alternative visual fatigue measurement methods using facial expression recognition and gesture recognition. Background: In most previous researches, visual fatigue is commonly measured by survey or interview based subjective method. However, the subjective evaluation methods can be affected by individual feeling's variation or other kinds of stimuli. To solve these problems, signal and image processing based visual fatigue measurement methods have been widely researched. Method: To analyze the signal and image processing based methods, we categorized previous works into three groups such as bio-signal, brainwave, and eye image based methods. Also, the possibility of adopting facial expression or gesture recognition to measure visual fatigue is analyzed. Results: Bio-signal and brainwave based methods have problems because they can be degraded by not only visual stimuli but also the other kinds of external stimuli caused by other sense organs. In eye image based methods, using only single feature such as blink frequency or pupil size also has problem because the single feature can be easily degraded by other kinds of emotions. Conclusion: Multi-modal measurement method is required by fusing several features which are extracted from the bio-signal and image. Also, alternative method using facial expression or gesture recognition can be considered. Application: The objective visual fatigue measurement method can be applied into the fields of quantitative and comparative measurement of visual fatigue of next generation display devices in terms of human factor.

• 한국생산제조학회지
• /
• 제9권2호
• /
• pp.144-150
• /
• 2000

Surface roughness is one of the most important parameters to estimate quality of products. As this reason so many studies were car-ried out through various attempts that were contact or non-contact using computer vision. Even through these efforts there were few good results in this research., however texture analysis making a important role to solve these problems in various fields including universe aviation living thing and fibers. In this study feature value of co-occurrence matrix was calculated by statistic method and roughness value of worked surface was classified, of it. Experiment was carried out using input vector of neural network with characteristic value of texture calculated from worked surface image. It's found that recognition rate of 74% was obtained when adapting texture features. In order to enhance recogni-tion rate combination type in characteristics value of texture was changed into input vector. As a result high recognition rate of 92.6% was obtained through these processes.

• 반도체디스플레이기술학회지
• /
• 제13권1호
• /
• pp.57-62
• /
• 2014

This paper proposes a new optical recognition method of credit card numbers. Firstly, the proposed method segments numbers from the input image of a credit card. It uses the significant differences of standard deviations between the foreground numbers and the background. Secondly, the method extracts gradient features from the segmented numbers. The gradient features are defined as four directions of grayscale pixels for 16 regions of an input number. Finally, it utilizes an artificial neural network classifier that uses an error back-propagation algorithm. The proposed method is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiments were conducted by using real credit card images. The results show that the proposed algorithm is quite successful for most credit cards. However, the method fails in some credit cards with strong background patterns.

• 반도체디스플레이기술학회지
• /
• 제16권4호
• /
• pp.79-85
• /
• 2017

Understanding of human emotion has a high importance in interaction between human and machine communications systems. The most expressive and valuable way to extract and recognize the human's emotion is by facial expression analysis. This paper presents and implements an automatic extraction and recognition scheme of facial expression and emotion through still image. This method has three main steps to recognize the facial emotion: (1) Detection of facial areas with skin-color method and feature maps, (2) Creation of the Bezier curve on eyemap and mouthmap, and (3) Classification and distinguish the emotion of characteristic with Hausdorff distance. To estimate the performance of the implemented system, we evaluate a success-ratio with emotional face image database, which is commonly used in the field of facial analysis. The experimental result shows average 76.1% of success to classify and distinguish the facial expression and emotion.