• Title/Summary/Keyword: 이미지 처리기법

Search Result 806, Processing Time 0.025 seconds

Facial Detection using Haar-like Feature and Bezier Curve (Haar-like와 베지어 곡선을 이용한 얼굴 성분 검출)

  • An, Kyeoung-Jun;Lee, Sang-Yong
    • Journal of Digital Convergence
    • /
    • v.11 no.9
    • /
    • pp.311-318
    • /
    • 2013
  • For face detection techniques, the correctness of detection decreases with different lightings and backgrounds so such requires new methods and techniques. This study has aimed to obtain data for reasoning human emotional information by analyzing the components of the eyes and mouth that are critical in expressing emotions. To do this, existing problems in detecting face are addressed and a detection method that has a high detection rate and fast processing speed good at detecting environmental elements is proposed. This method must detect a specific part (eyes and a mouth) by using Haar-like Feature technique with the application of an integral image. After which, binaries detect elements based on color information, dividing the face zone and skin zone. To generate correct shape, the shape of detected elements is generated by using a bezier curve-a curve generation algorithm. To evaluate the performance of the proposed method, an experiment was conducted by using data in the Face Recognition Homepage. The result showed that Haar-like technique and bezier curve method were able to detect face elements more elaborately.

A Study on Lightweight Transformer Based Super Resolution Model Using Knowledge Distillation (지식 증류 기법을 사용한 트랜스포머 기반 초해상화 모델 경량화 연구)

  • Dong-hyun Kim;Dong-hun Lee;Aro Kim;Vani Priyanka Galia;Sang-hyo Park
    • Journal of Broadcast Engineering
    • /
    • v.28 no.3
    • /
    • pp.333-336
    • /
    • 2023
  • Recently, the transformer model used in natural language processing is also applied to the image super resolution field, showing good performance. However, these transformer based models have a disadvantage that they are difficult to use in small mobile devices because they are complex and have many learning parameters and require high hardware resources. Therefore, in this paper, we propose a knowledge distillation technique that can effectively reduce the size of a transformer based super resolution model. As a result of the experiment, it was confirmed that by applying the proposed technique to the student model with reduced number of transformer blocks, performance similar to or higher than that of the teacher model could be obtained.

Analysis of the Effect of Corner Points and Image Resolution in a Mechanical Test Combining Digital Image Processing and Mesh-free Method (디지털 이미지 처리와 강형식 기반의 무요소법을 융합한 시험법의 모서리 점과 이미지 해상도의 영향 분석)

  • Junwon Park;Yeon-Suk Jeong;Young-Cheol Yoon
    • Journal of the Computational Structural Engineering Institute of Korea
    • /
    • v.37 no.1
    • /
    • pp.67-76
    • /
    • 2024
  • In this paper, we present a DIP-MLS testing method that combines digital image processing with a rigid body-based MLS differencing approach to measure mechanical variables and analyze the impact of target location and image resolution. This method assesses the displacement of the target attached to the sample through digital image processing and allocates this displacement to the node displacement of the MLS differencing method, which solely employs nodes to calculate mechanical variables such as stress and strain of the studied object. We propose an effective method to measure the displacement of the target's center of gravity using digital image processing. The calculation of mechanical variables through the MLS differencing method, incorporating image-based target displacement, facilitates easy computation of mechanical variables at arbitrary positions without constraints from meshes or grids. This is achieved by acquiring the accurate displacement history of the test specimen and utilizing the displacement of tracking points with low rigidity. The developed testing method was validated by comparing the measurement results of the sensor with those of the DIP-MLS testing method in a three-point bending test of a rubber beam. Additionally, numerical analysis results simulated only by the MLS differencing method were compared, confirming that the developed method accurately reproduces the actual test and shows good agreement with numerical analysis results before significant deformation. Furthermore, we analyzed the effects of boundary points by applying 46 tracking points, including corner points, to the DIP-MLS testing method. This was compared with using only the internal points of the target, determining the optimal image resolution for this testing method. Through this, we demonstrated that the developed method efficiently addresses the limitations of direct experiments or existing mesh-based simulations. It also suggests that digitalization of the experimental-simulation process is achievable to a considerable extent.

A method for concrete crack detection using U-Net based image inpainting technique

  • Kim, Su-Min;Sohn, Jung-Mo;Kim, Do-Soo
    • Journal of the Korea Society of Computer and Information
    • /
    • v.25 no.10
    • /
    • pp.35-42
    • /
    • 2020
  • In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).

The Lens Aberration Correction Method for Laser Precision Machining in Machine Vision System (머신비전 시스템에서 레이저 정밀 가공을 위한 렌즈 수차 보정 방법)

  • Park, Yang-Jae
    • Journal of Digital Convergence
    • /
    • v.10 no.10
    • /
    • pp.301-306
    • /
    • 2012
  • We propose a method for accurate image acquisition in a machine vision system in the present study. The most important feature is required by the various lenses to implement real and of the same high quality image-forming optical role. The input of the machine vision system, however, is generated due to the aberration of the lens distortion. Transformation defines the relationship between the real-world coordinate system and the image coordinate system to solve these problems, a mapping function that matrix operations by calculating the distance between two coordinates to specify the exact location. Tolerance Focus Lens caused by the lens aberration correction processing to Galvanometer laser precision machining operations can be improved. Aberration of the aspheric lens has a two-dimensional shape of the curve, but the existing lens correction to linear time-consuming calibration methods by examining a large number of points the problem. How to apply the Bilinear interpolation is proposed in order to reduce the machining error that occurs due to the aberration of the lens processing equipment.

An Integrated Face Detection and Recognition System (통합된 시스템에서의 얼굴검출과 인식기법)

  • 박동희;이규봉;이유홍;나상동;배철수
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2003.05a
    • /
    • pp.165-170
    • /
    • 2003
  • This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

  • PDF

Recent Progress in Computational Imaging Through Turbid Media (불규칙 매체를 통한 컴퓨테이셔널 이미징의 최근 연구 동향)

  • Jang, Hwanchol;Yoon, Changhyeong;Chung, Euiheon;Choi, Wonshik;Lee, Heung-No
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.39A no.12
    • /
    • pp.764-770
    • /
    • 2014
  • It is expected that the techniques of optical imaging through turbid media enables non-invasive imaging through human skin and biological tissues. In recent years, many researches have shown that imaging through turbid media can be made possible by measuring the transmission matrix (TM) of the turbid medium and utilizing it for image recovery. However, this TM based image recovery requires a huge amount of data acquisition and post signal processing of them. Very recently, there were new results that this problem of huge data acquisition and processing can be resolved by using the compressed sensing (CS) framework. CS is a relatively new signal acquisition and reconstruction framework which makes possible to recover the signal of interest correctly with significantly smaller number of signal measurements. In this paper, the TM-based image recovery in imaging through turbid media is reviewed and the recent progress made by using CS is introduced.

Comparison between GOx/Kerosene and GN2O/Ethanol Reactive Spray in a Subscale Liquid Rocket Engine (축소형 액체로켓엔진에서 기체산소/케로신 및 기체아산화질소/에탄올 연소 분무의 비교)

  • Choi, Songyi;Shin, Bongchul;Lee, Keonwoong;Kim, Dohun;Koo, Jaye;Park, Dong-Kun
    • Journal of the Korean Society of Propulsion Engineers
    • /
    • v.19 no.4
    • /
    • pp.61-68
    • /
    • 2015
  • Reactive sprays of two propellant combinations(GOx/kerosene and $GN_2O$/ethanol) were observed and compared with each other as a basic research of visualizing supercritical combustion. A shadowgraph imaging method was used to visualize the reactive sprays, and shadowgraph images were converted to density gradient magnitude images to analyse the structure of reactive sprays. The gas-liquid interface of GOx/kerosene spray showed rougher boundary and steeper density gradient near the injector face than the $N_2O$/ethanol at similar combustion chamber pressure. Spray core length was calculated from averaged density gradient magnitude images and it was revealed that spray core length of GOx/kerosene was shorter than that of $GN_2O$/ethanol, although momentum flux ratio of GOx/kerosene propellant combination was lower.

An Integrated Face Detection and Recognition System (통합된 시스템에서의 얼굴검출과 인식기법)

  • 박동희;배철수
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.7 no.6
    • /
    • pp.1312-1317
    • /
    • 2003
  • This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

A Driver's Condition Warning System using Eye Aspect Ratio (눈 영상비를 이용한 운전자 상태 경고 시스템)

  • Shin, Moon-Chang;Lee, Won-Young
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.15 no.2
    • /
    • pp.349-356
    • /
    • 2020
  • This paper introduces the implementation of a driver's condition warning system using eye aspect ratio to prevent a car accident. The proposed driver's condition warning system using eye aspect ratio consists of a camera, that is required to detect eyes, the Raspberrypie that processes information on eyes from the camera, buzzer and vibrator, that are required to warn the driver. In order to detect and recognize driver's eyes, the histogram of oriented gradients and face landmark estimation based on deep-learning are used. Initially the system calculates the eye aspect ratio of the driver from 6 coordinates around the eye and then gets each eye aspect ratio values when the eyes are opened and closed. These two different eye aspect ratio values are used to calculate the threshold value that is necessary to determine the eye state. Because the threshold value is adaptively determined according to the driver's eye aspect ratio, the system can use the optimal threshold value to determine the driver's condition. In addition, the system synthesizes an input image from the gray-scaled and LAB model images to operate in low lighting conditions.