• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.879-881
• /
• 2014

A method is proposed to achieve improved number plate detection for mobile devices by applying a two-step convolutional neural network (CNN) approach. Supervised CNN-verified car detection is processed first. In the second step, we apply the detected car regions to the second CNN-verifier for number plate detection. Since mobile devices are limited in computing power, we propose a fast method to detect number plates. We expect to use in the field of intelligent transportation systems (ITS).

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.1
• /
• pp.139-148
• /
• 2015

In this paper, a new algorithm is proposed for detecting the product number of each thick plate and extracting each character of the product number from a image which contains several thick plates. In general, a image of thick plates contains several steal plates. To obtain the product number from the image, we first need to separate each plate. To do so, we use the line edges of thick plates and a clustering algorithm. After separating each plate, background parts are eliminated from the image of each plate. Background parts of an individual thick plate image consist of the dark part of steel and the white part of paint which is used for printing the product number. We propose a two-tiered method where dark background parts are first eliminated and then white parts are eliminated. Finally, each character is extracted from the product number image using the characteristics of product number. The results of the experiments on the various steal plates images emphasize that the proposed algorithm detects each thick plate and extracts the product number from a image effectively.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.40-47
• /
• 2009

This paper proposes a method for vehicle license plate detection using mathematical morphology and symmetry. In general, the shape, color, size, and position of license plate are regulated by authorities for a better recognition by human. Among them, the relatively big intensity difference between the letter and the background region of the license plate and the symmetry about the plate are major discriminating factors for the detection. For the first, the opened image is subtracted from the closed image to intensify the region of plate using the rectangular structuring element which has the width of the distance between two characters. Second the subtraction image is average filtered with the mask size of the plate. Third, the column maximum graph of the average filtered image is acquired and the symmetry of the graph is measured at every position. Fourth, the peaks of the average filtered image are searched. Finally, the plate is assumed to be positioned around the one of local maxima nearest to the point of the highest symmetry. About 1,000 images taken by speed regulation camera are used for the experiment. The experimental result shows that the plate detection rate is about 93%.

• Smart Structures and Systems
• /
• v.22 no.3
• /
• pp.277-290
• /
• 2018

In this paper, wavelet finite element model (WFEM) updating technique is employed to detect sub-element damage in thin plate structures progressively. The procedure of WFEM-based detection method, which can detect sub-element damage gradually, is established. This method involves the optimization of an objective function that combines frequencies and modal assurance criteria (MAC). During the damage detection process, the scales of wavelet elements in the concerned regions are adaptively enhanced or reduced to remain compatible with the gradually identified damage scenarios, while the modal properties from the tests remains the same, i.e., no measurement point replacement or addition are needed. Numerical and experimental examples were conducted to examine the effectiveness of the proposed method. A scanning Doppler laser vibrometer system was employed to measure the plate mode shapes in the experimental study. The results indicate that the proposed method can detect structural damage with satisfactory accuracy by using minimal degrees-of-freedoms (DOFs) in the model and minimal updating parameters in optimization.

• Smart Media Journal
• /
• v.13 no.1
• /
• pp.24-35
• /
• 2024

The combination of Artificial Intelligence and the Internet of Things (AIoT) has gained significant popularity. Deep neural networks (DNNs) have demonstrated remarkable success in various applications. However, deploying complex AI models on embedded boards can pose challenges due to computational limitations and model complexity. This paper presents an AIoT-based system for smart parking lots using edge devices. Our approach involves developing a detection model and a decision tree for occupancy status classification. Specifically, we utilize YOLOv5 for car license plate (LP) detection by verifying the position of the license plate within the parking space.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.15-23
• /
• 2016

This paper proposes an effective algorithm of Korean license plate recognition. By applying Haar-like feature and Canny edge detection on a captured vehicle image, it is possible to find a connected rectangular, which is a strong candidate for license plate. The color information of license plate separates plates into white and green. Then, OTSU binary image processing and foreground neighbor pixel propagation algorithm CLNF will be applied to each license plates to reduce noise except numbers and letters. Finally, through labeling, numbers and letters will be extracted from the license plate. Letter and number regions, separated from the plate, pass through mesh method and thinning process for extracting feature vectors by X-Y projection method. The extracted feature vectors are classified using neural networks trained by backpropagation algorithm to execute final recognition process. The experiment results show that the proposed license plate recognition algorithm works effectively.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.32 no.3
• /
• pp.256-260
• /
• 1999

Minimun-detectable levels to 28 antibacterial agents used for the prevention and the treatment of fish diseases were determined to establish optimal detective method of bioassay in fish by the EEC 4-plate method, the modified method of EEC 4-plate and the standard method of analysis in food safety regulation. The test organisms used in the methods of bioassay were as follows: Bacillus subtilis BGA (B. subtilis) and Micrococcus luteus ATCC 9341 (M. luteus) in the EEC 4-plate method, B. subtilis, M. luteus and Bacillus cereus var. mycoides ATCC 11778 (B. cereus) in the modified of EEC 4-plate, and B. subtilis, M. luteus, B. cereus and Bacillus stearothermophilis var. calidolactis C-953 (B. stearothermophilis) in the standard method. The standard method showed predominant sensitivity in the detection of penicillins (PCs), and was also highly sensitive to aminoglycosides (AGs). The sensitivity of standard method in the detection of tetracyclines (TCs), marrolides (MLs), nitrofuran derivatives(NFs) and quinolones (QNs) was very low, and against sulfonamides (SAs), however, was extremely low. The modified method of EEC 4-plate showed very high sensitivity to TCs. Both the EEC 4-plate and the modified method of EEC 4-plate showed competitively high sensitivity in the detection of PCs, MLs, NFs, QNs and SAs. All the methods studied in the experiment showed very low sensitivity against chloramphenicol (CMs). Consequently, the modified method of EEC 4-Plate was the best bioassay method with a wide range of sensitivity for the optimal detection of the residual antibacterial agents in fish.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.1 s.94
• /
• pp.81-86
• /
• 2005

In this work, we propose a new ultrasonic damage inspection method in plate structures. The proposed method employs an OPMT(orientation-adjustable patch-type magnetostrictive transducer) in order to make the ultrasonic waves directed to a specific target point. For experiments, virtual grid points were set up at every 50 mm in an aluminum plate and two OPMTs were used for inspection. If there exists a crack in a plate, the reflected Lamb wave from the crack is measured in addition to the direct waves from the transmitting transducer to the receiving transducer.

• Korean Journal of Veterinary Service
• /
• v.20 no.3
• /
• pp.313-321
• /
• 1997

The antibiotic residues of the urine, the liver, the lung, the kidney and the spleen in slaughtered pigs at Kyongbuk province were detected by TLC(505 kit) and EEC-4 plate method. 1. The positive rate of residual sulfamethazine which was detected by 505 kit in the urine (n=200) was 0.0%. 2. The positive rate of residual sulfamethazine which was detected by EEC-4 plate in the urine (n=126), the liver(n=98), the kidney(n=72), the spleen (n=68) and the lung(n=48) were 63%, 49%, 36%, 34% and 24%, respectively. 3. By EEC-4 plate method, the positive detection rates of the urine were 53.0% in BS(pH 6.0), 29.0% in BS(pH 7.2), 11.5% in BS(pH 8.0) and 13.0% in ML(pH 8.0) medium, that of the liver 41.5% in BS(pH 6.0), 22.0% in BS(pH 7.2), 6.5% in BS(pH 8.0) and 5.0%, in ML (pH 8.0) medium, that of the lung 21.0% in BS(pH 6.0), 9.5%, in BS(pH 7.2) and 8.5% in BS(pH 8.0) medium, and that of the kidney 31.5% in BS(pH 6.0), 14.5% in BS(pH 7.2), 20.0% in BS(pH 8.0) and 3.0% in ML(pH 8.0) medium. In the spleen, only in BS(pH 6.0) medium the positive rate was detected as 33.5 %. 4. The positive rates of samples which shown TLC-positive detected by EEC-4 plate method were 53.9% in no band, 77.8% in one band, 80.9% in two bands, 66.7% in three bands, respectively. In conclusion, the EEC-4 plate method could be applied for the detection of residual antibiotics in samples which shown as out of standard Rf values by TLC-method (SOS kit).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.10
• /
• pp.909-919
• /
• 2014

License plate (LP) detection is the most imperative part of an automatic LP recognition (LPR) system. Typical LPR contains two steps, namely LP detection (LPD) and character recognition. In this paper, we propose an efficient Vehicle-to-LP detection framework which combines with an adaptive GMM (Gaussian Mixture Model) and a cascade of boosted classifiers to make a faster vehicle LP detector. To develop a background model by using a GMM is possible in the circumstance of a fixed camera and extracts the motions using background subtraction. Firstly, an adaptive GMM is used to find the region of interest (ROI) on which motion detectors are running to detect the vehicle area as blobs ROIs. Secondly, a cascade of boosted classifiers is executed on the blobs ROIs to detect a LP. The experimental results on our test video with the resolution of $720{\times}576$ show that the LPD rate of the proposed system is 99.14% and the average computational time is approximately 42ms.