• Current Optics and Photonics
• /
• v.2 no.6
• /
• pp.554-562
• /
• 2018

This study presents a color 3D scanner based on the laser structured-light imaging method that can simultaneously acquire 3D shape data and color of a target object using a single camera. The 3D data acquisition of the scanner is based on the structured-light imaging method, and the color data is obtained from a natural color image. Because both the laser image and the color image are acquired by the same camera, it is efficient to obtain the 3D data and the color data of a pixel by avoiding the complicated correspondence algorithm. In addition to the 3D data, the color data is helpful for enhancing the realism of an object model. The proposed scanner consists of two line lasers, a color camera, and a rotation table. The line lasers are deployed at either side of the camera to eliminate shadow areas of a target object. This study addresses the calibration methods for the parameters of the camera, the plane equations covered by the line lasers, and the center of the rotation table. Experimental results demonstrate the performance in terms of accurate color and 3D data acquisition in this study.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2098-2114
• /
• 2021

Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a Nonnegative Matrix Factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle; Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature; At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.6
• /
• pp.4108-4114
• /
• 2015

An image acquisition by using an optical mirror is called as a catadioptric method. The catadioptric imaging method is generally used for acquisition of 360-degree all directional visual information in an image. An exemplar omnidirectional optical mirror is the bowl-shaped hyperbolic mirror. In this paper, a single camera omnidirectional stereo imaging method is studied with an additional concave lens. It is possible to obtain 3 dimensional coordinates of environmental objects from the omnidirectional stereo image by matching the stereo image having different view points. The omnidirectional stereo imaging system in this paper is cost-effective and relatively easy for correspondence matching because of consistent camera intrinsic parameters in the stereo image. The parameters of the imaging system are extracted through 3-step calibration and the performance for 3-dimensional coordinates reconstruction is verified through experiments in this paper. Measurable range of the proposed imaging system is also presented by depth-resolution analysis.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.6
• /
• pp.691-697
• /
• 1999

This paper describes the implementation of a high speed image processing board. This image processing board is consist of a image acquisition part and a image processing part. The image acquistion part is digitizing the image input data from CIS and save it to the dual port RAM. By putting on the dual port memory between two parts, during acquistion of image, the image processing part can be effectively processing of large-volume image data. Most of all image preprocessing part are integrated in a large-scaled FPGA. We arwe using ADSP-2181 of the Analog Device Inc., LTD. for a image processing part, and using the available all memory of DSP for the large-volume image data. Especially, using of IDMA exchanges the data with the external microprocessor or the external PC, and can watch the result of image processing and acquired image. Finally, we show that an implemented image processing board used for the simulation of image retreval by the one of the typical application.

• Journal of information and communication convergence engineering
• /
• v.9 no.3
• /
• pp.336-340
• /
• 2011

Many approaches to image restoration are aimed at removing either gauss or impulse noise. This is because both types of degradation processes are distinct in nature, and hence they are easier to manage when considered separately. Nevertheless, it is possible to find them operating on the same image, which produces a hard damage. This happens when an image, already contaminated by Gaussian noise in the image acquisition procedure, undergoes impulsive corruption during its digital transmission. Here we proposed an algorithm first judge the type of the noise according to the difference values of pixel's neighborhood region and impulse noise's characteristic. Then removes the gauss noise by modified weighted mean filter and removes the impulse noise by modified nonlinear filter. The result of computer simulation on test images indicates that the proposed method is superior to traditional filtering algorithms. The proposed method can not only remove mixed noise effectively, but also preserve image details.

• Journal of Biosystems Engineering
• /
• v.26 no.3
• /
• pp.279-286
• /
• 2001

The purpose of this study were to organize a sorting system, to develop an algorithm of image processing for the shape sorting, and to finally develop a scientific and objective shape sorting system of Korean Red-Ginseng for mechanization of the shape sorting. The results of this study are followed. 1. The shape sorting system of Korean Red-Ginseng consists of a control computer, a color CCD camera(WV-CP4110) for image processing, an image processing board(DT3153), and an image acquisition unit. 2. Many image processing skill, such as sliding, stretching, threshold, binary and D$\sub$t/ were used to analyze the shape sorting factors of Korean Red-ginseng. 3. The sorting accuracy of the shape sorting system for the Korean Red-Ginseng was 74.7%. It is 21.1% lower than that of human inspector. Although the system has low accuracy, using more cameras may improve its sorting accuracy.

• Journal of information and communication convergence engineering
• /
• v.9 no.5
• /
• pp.591-596
• /
• 2011

Image denoising is a key issue in all image processing researches. Generally, the quality of an image could be corrupted by a lot of noise due to the undesired conditions of image acquisition phase or during the transmission. Many approaches to image restoration are aimed at removing either Gaussian or impulse noise. Nevertheless, it is possible to find them operating on the same image, which is called mixed noise and it produces a hard damage. In this paper, we proposed noise type classification method and a mixed nonlinear filter for mixed noise suppression. The proposed filtering scheme applies a modified adaptive switching median filter to impulse noise suppression and an efficient nonlinear filer was carried out to remove Gaussian noise. The simulation results based on Matlab show that the proposed method can remove mixed Gaussian and impulse noise efficiently and it can preserve the integrity of edge and keep the detailed information.

• Journal of Biosystems Engineering
• /
• v.28 no.5
• /
• pp.439-448
• /
• 2003

An image processing algorithm was developed for a robot system which was used in gene study. The robot system achieved a job of colony picking. The colony included DNA of an organism. The robot picked up the colony in petri-dish, which included the cultivated colony in medium, by a picking pin, and moved the colony to wellplates. The vision system consisted of an image acquisition system which acquired the image information of colony, an illumination device which irradiated the object once when it got the image of it, a computer and so on. The image processing algorithm distinguished the colony and detected colony positions. Performance test of the developed algorithm showed that the distinguishing success rate of colony and detecting success rate of colony positions were over 96%.

• The Magazine of the IEIE
• /
• v.23 no.3
• /
• pp.83-93
• /
• 1996

Picture archiving and communications systems(PACS) for digital image distribution, archiving and transmission, represent the modern hospital. PACS is the medical image management system within a hospital, whereas teleradiology system is the medical image communication system between remote sites. PACS and teleradiology systems usually consists of mainly four parts such as image acquisition part, image storage and database part, Image communication network part, and image display workstation part. Among these components comprised In the PACS, workstations are the point of contact between a PACS and the radiologist or referring physician. Therefore, the acceptance of PACS is highly dependent on workstation functionality, performance and easy of use compared with the conventional film-based radiology. This paper describes overall configurations and some requirements of PACS and teleradiology.