In this study, we have proposed an algorithm that solves the problems which occur during the recognition of a vehicle license plate through closed-circuit television (CCTV) by using a deep learning model trained with a general database. The deep learning model which is commonly used suffers with a disadvantage of low recognition rate in the tilted and low-resolution images, as it is trained with images acquired from the front of the license plate. Furthermore, the vehicle images acquired by using CCTV have issues such as limitation of resolution and perspective distortion. Such factors make it difficult to apply the commonly used deep learning model. To improve the recognition rate, an algorithm which is a combination of the super-resolution generative adversarial network (SRGAN) model, and the perspective distortion correction algorithm is proposed in this paper. The accuracy of the proposed algorithm was verified with a character recognition algorithm YOLO v2, and the recognition rate of the vehicle license plate image was improved 8.8% from the original images.

An algorithm for measurement of the cutting blade of the ultrasonic vibration cutting machine used in an automation machine is proposed in this paper. The proposed algorithm, which is based upon a multi-step detection method, is developed for the accurate measurement of the cutting blade by exactly determining its rotation angle, length, and thickness. Instead of the commonly used Otsu method, we propose a new curvature-based adaptive binarization method, which provides more accurate details about the dimensions of the cutting blade. A region of interest containing the cutting blade from the acquired image is first extracted in the multi-step detection method, which is further processed to remove the noise, which increases the measurement reliability. An important feature of the proposed process is the restoration of the cutting blade’s tip data, which used to be lost during the fine noise-filtering process. The rotation angle and length are measured using the minimum rotated rectangle while the line fitting based upon the least square method is applied to increase the reliability of the thickness measurement. Experimental results validate the superiority of the proposed method over the conventional Otsu method.

This research investigates the degrees of slipperiness felt by the participants who walk on contaminants applied to a floor surface to decide degrees of slipperiness for various contaminants. For the experiment, 30 participants walked on a floor to which six contaminants were applied. All participants took the analytic hierarchy process (AHP)-based slipperiness questionnaire survey for the six kinds of contaminants, and the results were compared with the coefficient of friction. The results of slip risk from the AHP indicate that grease is the most slippery of the six contaminants, followed by diesel engine oil, hydraulic oil, cooking oil, water-soluble cutting oil, and water in a decreasing order of slipperiness. When the results of slip risk from the AHP are compared with the static coefficient of friction for each contaminant, the order of slip risk follows the same trend. Although the results of slip risk from the AHP coincide with the static coefficient of friction, further study would be needed to investigate this relationship. This study will contribute as reference material for future research on preventing industrial accidents that result in falls from high places due to slipping.

Korea’s agriculture is facing a manpower shortage due to a decrease in the population and an aging workforce. Involving disabled people in agriculture as a solution to the problem of manpower shortage can help both agricultural workers and people with disabilities, and for this purpose, it is necessary to develop agricultural tools that disabled people can use in agricultural tasks. This study was intended to create a representative human body model used in the anthropometric design of agricultural tools for people with spinal cord disabilities. This study used the existing anthropometric data for the spinal cord disabled and created a representative human body model using the method of boundary for the accommodation range of the body size distribution. As a result of factor analysis, 26 body dimensions were reduced to 4 factors, and the representative group had 16 body models to have an accommodation rate of 90% of the distribution. As a result of the evaluation of the accommodation rate of the representative human model group, only 42% of cases satisfied all the ranges of 26 body dimensions for the representative group, but 88% of cases satisfied all the ranges of 23 body dimensions, which is close to the target rate. The representative human model group for spinal cord disabilities was visualized using the Tecnomatix human model module. This can be utilized in identification of problems with existing agricultural tools and anthropometric design for the disabled.