• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.273-282
• /
• 2022

MPEG-VCM(Video Coding for Machine) aims to standardize video codec for machines. VCM provides data sets and anchors, which provide reference data for comparison, for several machine vision tasks including object detection, object segmentation, and object tracking. The evaluation template can be used to compare compression and machine vision task performance between anchor data and various proposed video codecs. However, performance comparison is carried out separately for each machine vision task, and information related to performance evaluation of multiple machine vision tasks on a single bitstream is not provided currently. In this paper, we propose a performance evaluation method of a video codec for AI-based multi-tasks. Based on bits per pixel (BPP), which is the measure of a single bitstream size, and mean average precision(mAP), which is the accuracy measure of each task, we define three criteria for multi-task performance evaluation such as arithmetic average, weighted average, and harmonic average, and to calculate the multi-tasks performance results based on the mAP values. In addition, as the dynamic range of mAP may very different from task to task, performance results for multi-tasks are calculated and evaluated based on the normalized mAP in order to prevent a problem that would be happened because of the dynamic range.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.6 no.3
• /
• pp.24-30
• /
• 2007

The FPCs(Flexible Printed Circuit) are currently used in several electronic products like digital cameras, cellular phones because of flexible material characteristics. Because the FPC is usually small size and flexible, only one FPC should not enter chip mounting process, instead, several FPCs are placed on the large rigid pallette and enter into the chip mounting process. Currently the job of mounting FPC on the pallette is carried by totally manual way. Thus, the goals of the research is develop the automatic machine of FPC mounting on pallette using vision alignment. Instead of using two cameras or using moving one camera, the proposed vision system with only one fixed camera is adopted. Moreover, the two picker heads which can handle two FPCs simultaneously are used to make process time shortened. The procedure of operation is firstly to measure alignment error of FPC, correct alignment errors, and finally mount well-aligned FPC on the pallette. The vision technology is used to measure alignment error accurately, and precision motion control is used in correcting errors and mounting FPC.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.11-13
• /
• 2007

The appearance inspection of various electronic products and parts has been executed by the eyesight of human. But inspection by eyesight can't bring about uniform inspection result. Because the appearance inspection result by eyesight of human is changed by condition of physical and spirit of the checker. So machine vision inspection system is currently used to many appearance inspection fields instead of the checker. However the inspection result of machine vision is changed by the illumination of workplace. Therefore we have used a power-law transformation in this paper. for improvement of vision inspection accuracy and could increase inspection accuracy of vision system. Also this system has been developed only using PC, CCD Camera and Visual C++ for universal workplace.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.12
• /
• pp.105-114
• /
• 2003

In this study, a dicing machine with vision system was built and an algorithm for automatic alignment was developed for dual camera system. The system had a macro and a micro inspection tool. The algorithm was formulated from geometric relations. When a wafer was put on the cutting stage within certain range, it was inspected by vision system and compared with a standard pattern. The difference between the patterns was analyzed and evaluated. Then, the stage was moved by x, y, $\theta$ axes to compensate these differences. The amount of compensation was calculated from the result of the vision inspection through the automatic alignment algorithm. The stage was moved to the compensated position and was inspected by vision for checking its result again. Accuracy and validity of the algorithm was discussed from these data.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.1
• /
• pp.29-33
• /
• 2017

This paper presents a development of vision aligner with three channels for the wafer and plate bonding machine in manufacturing of LED. The developed vision aligner consists of three cameras and performs wafer alignment of rotation and translation, flipped wafer detection, and UV Tape detection on the target wafer and plate. Normally the process step of wafer bonding is not defined by standards in semiconductor's manufacturing which steps are used depends on the wafer types so, a lot of processing steps has many unexpected problems by the workers and environment of manufacturing such as the above mentioned. For the mass production, the machine operation related to production time and worker's safety so the operation process should be operated at one time with considering of unexpected problem. The developed system solved the 4 kinds of unexpected problems and it will apply on the massproduction environment.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.6
• /
• pp.867-875
• /
• 2004

In order to inspect burr geometry and hole quality in micro-drilling processes, a cost-effective method using an image processing and shape from focus (SFF) methods on the machine tool is proposed. A CCD camera with a zoom lens and a novel illumination unit is used in this paper. Since the on-machine vision unit is incorporated with the CNC function of the machine tool, direct measurement and condition monitoring of micro-drilling processes are conducted between drilling processes on the machine tool. Stainless steel and hardened tool steel are used as specimens, as well as twist drills made of carbide are used in experiments. Validity of the developed system is confirmed through experiments.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.3
• /
• pp.49-56
• /
• 2014

Generally, the tool presetter is utilized to align and measure some specific dimensions of a machine tool. It is classified into two types(contact and contactless) according to the measurement method, and the optical sensor based contactless scheme has the advantages of measurement flexibility and convenience. This paper describes the design and realization of an industrial tool presetter using machine vision and linear scaler. Before measurement, the objective tool is attached to the mechanical mount and is aligned with the optical apparatus. After capturing tool images, the suggested image processing algorithm calculates its dimesions accurately, combining the traversing distance from the linear scaler. Experimental results conforms that the present tool presetter system has the precision within ${\pm}20um$ error.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.155-170
• /
• 2020

Passive ranging is a critical part of machine vision measurement. Most of passive ranging methods based on machine vision use binocular technology which need strict hardware conditions and lack of universality. To measure the distance of an object placed on horizontal plane, we present a passive ranging method based on monocular vision system by smartphone. Experimental results show that given the same abscissas, the ordinatesis of the image points linearly related to their actual imaging angles. According to this principle, we first establish a depth extraction model by assuming a linear function and substituting the actual imaging angles and ordinates of the special conjugate points into the linear function. The vertical distance of the target object to the optical axis is then calculated according to imaging principle of camera, and the passive ranging can be derived by depth and vertical distance to the optical axis of target object. Experimental results show that ranging by this method has a higher accuracy compare with others based on binocular vision system. The mean relative error of the depth measurement is 0.937% when the distance is within 3 m. When it is 3-10 m, the mean relative error is 1.71%. Compared with other methods based on monocular vision system, the method does not need to calibrate before ranging and avoids the error caused by data fitting.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.951-954
• /
• 1998

This paper describes the implementation of the machine vision system and the method of classifying the objects. Its system described in this paper is consisted of robot, conveyer system, warehouse, and machine vision. This system first recognizes the object on conveyer, and then robot moves it to the warehouse. The position of the object on conveyer is always not constant, because it is not easy to extract the feature of its object and classify it into one of several categories. In this paper, to classify or inspect the pattern of the object, we propose the method of template matching using feature vector such as position invariant moment and mophological operation such as opening and closing. And we indentified an unregistered object using unsuperviser learning method and assigned it to the new pattern. We implemented its system and obtained satisfied results.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.13 no.3
• /
• pp.84-90
• /
• 2004

Today, automobile world market is highly competitive. In order to strengthen the competitiveness, quality of automobile is recognized as important and efforts are being made to improve the quality of manufactured components. The directional ability of automobile has influence on driver directly and hence it must be solved on the preferential basis. In the present research, an automated vision system has been developed to inspect the front chassis module. To interpret the inspection data obtained for front chassis module, new interpreting algorithm have been developed. Previously the control of tolerance of front chassis module was done manually. With the help of the new algorithm developed, the dimension is calculated automatically to check whether the front chassis module is within the tolerance limit or not.