• 한국정보통신학회논문지
• /
• 제24권3호
• /
• pp.341-348
• /
• 2020

인간의 눈과 같이 이미지에서 유용한 정보를 추출하는 기능은 인공지능 컴퓨터 구현에 필수적인 인터페이스 기술이다. 이미지에서 건물을 인식하여 추론하는 기술은 다양한 형태의 건물 외관, 계절에 따른 주변 잡음 이미지의 변화, 각도 및 거리에 따른 왜곡 등으로 다른 이미지 인식 기술 보다 인식률이 떨어진다. 지금까지 제시된 컴퓨터 비전(Computer Vision) 기반의 건물 인식 알고리즘들은 건물 특성을 수작업으로 정의하기 때문에 분별력과 확장성에 한계가 있다. 본 논문은 최근 이미지 인식에 유용한 딥러닝의 CNN(Convolutional Neural Network) 모델을 활용하는데 건물 외관에 나타나는 변화, 즉 계절, 조도, 각도 및 원근에 의해 떨어지는 인식률을 향상시키는 새로운 방법을 제안한다. 건물 전체 이미지와 함께 건물의 특징을 나타내는 부분 이미지들, 즉 창문이나 벽재 이미지의 데이터 세트를 함께 학습시키고 건물 인식에 활용함으로써 일반 CNN 모델 보다 건물 인식률을 약 14% 향상됨을 실험으로 증명하였다.

• 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.

• 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.

• Journal of Information Processing Systems
• /
• 제7권3호
• /
• pp.425-434
• /
• 2011

The success of iris recognition depends mainly on two factors: image acquisition and an iris recognition algorithm. In this study, we present a system that considers both factors and focuses on the latter. The proposed algorithm aims to find out the most efficient wavelet family and its coefficients for encoding the iris template of the experiment samples. The algorithm implemented in software performs segmentation, normalization, feature encoding, data storage, and matching. By using the Haar and Biorthogonal wavelet families at various levels feature encoding is performed by decomposing the normalized iris image. The vertical coefficient is encoded into the iris template and is stored in the database. The performance of the system is evaluated by using the number of degrees of freedom, False Reject Rate (FRR), False Accept Rate (FAR), and Equal Error Rate (EER) and the metrics show that the proposed algorithm can be employed for an iris recognition system.

• 한국컴퓨터정보학회논문지
• /
• 제26권2호
• /
• pp.19-25
• /
• 2021

본 논문에서는 비전 기술과 딥러닝 기반의 얼굴인식을 통해 실종자를 식별하는 방법을 제안하였다. 모바일 디바이스에서 전송된 원본 이미지에 대해 얼굴인식에 적합하도록 이미지를 전처리한 후, 얼굴인식의 정확도 향상을 위한 이미지 데이터 증식과 CNN 기반 얼굴학습 및 검증을 통해 실종자를 인식하였다. 본 논문의 구현 결과를 이용하여 가상의 실종자 이미지를 식별한 결과, 원본 데이터와 블러 처리한 데이터를 함께 학습한 모델의 성능이 가장 우수하게 나왔다. 또한 사전학습된 가중치를 사용한 학습 모델은 사용하지 않은 모델보다 높은 성능을 보였지만, 편향과 분산이 높게 나오는 한계를 확인할 수 있었다.

• 한국정보전자통신기술학회논문지
• /
• 제9권6호
• /
• pp.546-552
• /
• 2016

We present a quantitative evaluation of an algorithm for model-based face recognition. The algorithm actively learns how individual faces vary through video sequences, providing on-line suppression of confounding factors such as expression, lighting and pose. By actively decoupling sources of image variation, the algorithm provides a framework in which identity evidence can be integrated over a sequence. We demonstrate that face recognition can be considerably improved by the analysis of video sequences. The method presented is widely applicable in many multi-class interpretation problems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3534-3549
• /
• 2020

The traditional method of smoke image recognition has low accuracy. For this reason, we proposed an algorithm based on the good group of IMFOA which is GMFOA to optimize the parameters of SVM. Firstly, we divide the motion region by combining the three-frame difference algorithm and the ViBe algorithm. Then, we divide it into several parts and extract the histogram of oriented gradient and volume local binary patterns of each part. Finally, we use the GMFOA to optimize the parameters of SVM and multiple kernel learning algorithms to Classify smoke images. The experimental results show that the classification ability of our method is better than other methods, and it can better adapt to the complex environmental conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3488-3500
• /
• 2020

At the present time, the economy continues to flourish, and private cars have become the means of choice for most people. Therefore, the license plate recognition technology has become an indispensable part of intelligent transportation, with research and application value. In recent years, the convolution neural network for image classification is an application of deep learning on image processing. This paper proposes a strategy to improve the YOLO model by studying the deep learning convolutional neural network (CNN) and related target detection methods, and combines the OpenCV and TensorFlow frameworks to achieve efficient recognition of license plate characters. The experimental results show that target detection method based on YOLO is beneficial to shorten the training process and achieve a good level of accuracy.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.60-67
• /
• 2020

Recently, artificial intelligence related technologies including machine learning are being applied to various fields, and the demand is also increasing. In particular, with the development of AR, VR, and MR technologies related to image processing, the utilization of computer vision based on deep learning has increased. The algorithms for object recognition and detection based on deep learning required for image processing are diversified and advanced. Accordingly, problems that were difficult to solve with the existing methodology were solved more simply and easily by using deep learning. This paper introduces various deep learning-based object recognition and extraction algorithms used to detect and recognize various objects in an image and analyzes the technologies that attract attention.

• Journal of Biosystems Engineering
• /
• 제19권2호
• /
• pp.124-137
• /
• 1994

Visual features of a mushroom(Lentinus Edodes, L.) are critical in grading and sorting as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. To realize the automatic handling and grading of mushrooms in real time, the computer vision system should be utilized and the efficient and robust processing of the camera captured visual information be provided. Since visual features of a mushroom are distributed over the front and back sides, recognizing sides and states of the stalk including the stalk orientation from the captured image is a prime process in the automatic task processing. In this paper, the efficient and robust recognition process identifying the front and back side and the state of the stalk was developed and its performance was compared with other recognition trials. First, recognition was tried based on the rule set up with some experimental heuristics using the quantitative features such as geometry and texture extracted from the segmented mushroom image. And the neural net based learning recognition was done without extracting quantitative features. For network inputs the segmented binary image obtained from the combined type automatic thresholding was tested first. And then the gray valued raw camera image was directly utilized. The state of the stalk seriously affects the measured size of the mushroom cap. When its effect is serious, the stalk should be excluded in mushroom cap sizing. In this paper, the stalk removal process followed by the boundary regeneration of the cap image was also presented. The neural net based gray valued raw image processing showed the successful results for our recognition task. The developed technology through this research may open the new way of the quality inspection and sorting especially for the agricultural products whose visual features are fuzzy and not uniquely defined.