• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.453-462
• /
• 2021

A lot of license plate data is required for car number recognition. License plate data needs to be balanced from past license plates to the latest license plates. However, it is difficult to obtain data from the actual past license plate to the latest ones. In order to solve this problem, a license plate recognition study through deep learning is being conducted by creating a synthetic license plates. Since the synthetic data have differences from real data, and various data augmentation techniques are used to solve these problems. Existing data augmentation simply used methods such as brightness, rotation, affine transformation, blur, and noise. In this paper, we apply a style transformation method that transforms synthetic data into real-world data styles with data augmentation methods. In addition, real license plate data are noisy when it is captured from a distance and under the dark environment. If we simply recognize characters with input data, chances of misrecognition are high. To improve character recognition, in this paper, we applied the DeblurGANv2 method as a quality improvement method for character recognition, increasing the accuracy of license plate recognition. The method of deep learning for license plate detection and license plate number recognition used YOLO-V5. To determine the performance of the synthetic license plate data, we construct a test set by collecting our own secured license plates. License plate detection without style conversion recorded 0.614 mAP. As a result of applying the style transformation, we confirm that the license plate detection performance was improved by recording 0.679mAP. In addition, the successul detection rate without image enhancement was 0.872, and the detection rate was 0.915 after image enhancement, confirming that the performance improved.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.5
• /
• pp.78-88
• /
• 2012

AVIs on the road are installed for (1) security (2) and for traffic, and they are various managed by (1) police department, (2) local government, (3) national highway management, (4) Korean highway corporation. But although the collected data of the plate number, the travel time, the picture of the car are same, they are used in purposes of its installation because the managements are different and the data are difficult to be connected with each other. For this reason, this study is to appraise the application for creating traffic information by integrating these data, and to suggest the introduction of spatial detection system which integrated security-traffic AVI DB for the purpose of reliability improvement of center's velocity. The estimating sections of link travel information seems to be expanded, and the error rate between the center's velocity and the experimental value will be reduced if integrated DB of traffic and security AVIs is used for creating traffic information. Also, the crime prevention and arrest rate is expected to rise in the future.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 2003.10a
• /
• pp.133.1-133
• /
• 2003

Gummy stem blight, caused by Didymella bryoniae occurs exclusively on cucurbits. This fungus has been known not to produce its pycnidium in vitro unless irradiated. Through this study, we optimized cultural conditions for mass-production of pycnidiospore by Metal Halide Lamp irradiation. In brief, the mycelial was cultured at $26^{\circ}C$ on PDA, for 2 days under the darkness, and then the plate was illuminated with MH lamp continuously for 3-4 days at $26^{\circ}C$, a great number of pycnidia was simultaneously formed. Thus produced pycnidiospores were used as immunogen. From fusions of myeloma cell (v-653) with splenocytes from immunifed mice were car ried out. And, two hybridoma cell lines that recognized the immunogen Didymella bryoniae were obtained. One Monoclonal Antibody, Db1, recognized the supernatant and the other monoclonal antibody, Db15, recognized the spore. Two clones were selected which were used to produce ascite fluid two MAb Db1 and Db15, were immunotyped and identified as IgG1 and IgG2b, respectively. Titer of MAb Db1 and MAb Db15 was measured absorbance exceeded 0.5 even at a $10^{-5}$ dilution. The MAbs reacted positively with Didymella bryoniae but none reacted with other of fungi and CMV, CGMMV Sensitivity of MAb was precise enough to detect spore concentration as low as $10^{3}$ well by indirect ELISA characterization of the MAb Db1, Db15 antigen by heat and protease treatments show that the epitope recognized by the MAb Bb1, Db15 were a glycoprotein.