• 한국정보디스플레이학회:학술대회논문집
• /
• 2002.08a
• /
• pp.887-890
• /
• 2002

In this paper, a new 3D robot vision system using the hierarchical opto-digital algorithm is proposed and implemented. From some experimental results with the 20 frames of the stereo input image pairs, the proposed system is found to be able to effectively extract the area where the target object is located from the stereo input image regardless of the background noises.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.746-750
• /
• 2005

This paper describes image processing techniques that can detect, segment, and analyze the mango's physical properties such as size, shape, surface area, and color from images. First, images of mangoes taken by a digital camera are analyzed and segmented. The segmentation is done based on constructed hue model of the sample mangoes. Some morphological and filtering techniques are then applied to clean noises before fitting spline curve on the mango boundary. From the clean segmented image, the mango projected area can be computed. The shape of the mango is then analyzed using some structuring models. Color is also spatially analyzed and indexed in the database for future classification. To obtain the surface area, the mango is peeled. The scanned image of its peels is then segmented and filtered using similar approach. With calibration parameters, the surface area could then be computed. We employed the system to evaluate physical properties of a mango cultivar called "Nam Dokmai". There were sixty mango samples in three various sizes graded by an experienced farmer's eyes and hands. The results show the techniques could be a good alternative and more feasible method for grading mango comparing to human's manual grading.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.834-841
• /
• 1996

Egg production in Korea is becoming automated with a large scale farm. Although many operations in egg production have been and cracks are regraded as a critical problem. A computer vision system was built to generate images of a single , stationary egg. This system includes a CCD camera, a frame grabber board, a personal computer (IBM PC AT 486) and an incandescent back lighting system. Image processing algorithms were developed to inspect egg shell and to sort eggs. Those values of both gray level and area of dark spots in the egg image were used as criteria to detect holes in egg and those values of both area and roundness of dark spots in the egg and those values of both area and roundness of dark spots in the egg image were used to detect cracks in egg. Fro a sample of 300 eggs. this system was able to correctly analyze an egg for the presence of a defect 97.5% of the time. The weights of eggs were found to be linear to both the projected area and the perimeter of eggs v ewed from above. Those two values were used as criteria to sort eggs. Accuracy in grading was found to be 96.7% as compared with results from weight by electronic scale.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• v.11 no.2
• /
• pp.447-453
• /
• 2006

This paper presents an area-based stereo algorithm suitable to real time applications. The core of the algorithm depends on the uniqueness constraint and on a matching process that allows for rejecting previous matches. The proposed approach is compared with the left right consistency constraint, being the latter the basic method for detecting unreliable matches in many area-based stereo algorithms. We used the watermelon and tomatoes for experiments.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.32 no.3
• /
• pp.274-279
• /
• 2008

Roll to roll (R2R) manufacturing process, also known as 'web processing', has been tried for producing electronic devices on a flexible plastic or metal foil. To increase the performance and productivity the R2R process, effective control and on-line supervision for web quality becomes very important. Wrinkle is one of the defects, which is incurred due to compressive stresses. A system for on-line measurement of wrinkle is developed using area scan camera and machine vision laser. The 2D image, obtained by area scan camera, is produced by Gaussian regression method to characterize the wrinkle on a transparent web. The experiment proves that 0.3mm wrinkle height can be measured successfully with 74fps.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.953-958
• /
• 2007

Passenger safety is a primary concern of railway system but, it has been urgent issue that dozens of people are killed every year when they are fallen from train platforms. In this paper, we propose a vision based monitoring system for railway station platform. The system immediately perceives dangerous factors of passengers on the platform by using image processing technology. To monitor almost entire length of the track line in the platform, we use several video cameras. Each camera conducts surveillance its own preset monitoring area whether human or dangerous object was fallen in the area. Moreover, to deal with the accident immediately, the system provides local station, central control room employees and train driver with the video information about the accident situation including alarm message. This paper introduces the system overview and detection process with experimental results. According to the results, we expect the proposed system will play a key role for establishing highly intelligent monitoring system in railway.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.72-81
• /
• 2022

Visual Object Tracking is known as the most fundamental problem in the field of computer vision. Object tracking localize the region of target object with bounding box in the video. In this paper, a custom CNN is created to extract object feature that has strong and various information. This network was constructed as a Siamese network for use as a feature extractor. The input images are passed convolution block composed of a bottleneck layers, and features are emphasized. The feature map of the target object and the search area, extracted from the Siamese network, was input as a local proposal network. Estimate the object area using the feature map. The performance of the tracking algorithm was evaluated using the OTB2013 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.611 in Success Plot and 0.831 in Precision Plot were achieved.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.3
• /
• pp.102-109
• /
• 1996

In this paper, we present a new approach for the automation of deburring process. An algorithm for teaching skills of a human expert to a robot manipulator is developed. This approach makes use of TSK fuzzy mode that can wxpress a highly nonlinear functional relation with small number of rules. Burr features such as height, width, area, grinding area are extracted from image processing by use of the vision system. Grinding depth, repetitive number and normal grinding force are chosen as control signals representing actions of the human expert. It is verified that our proposed fuzzy model can accurately express the skills of human experts for the deburring process.

• Korean Journal of Materials Research
• /
• v.34 no.7
• /
• pp.315-320
• /
• 2024

In order to maximize the function and increase the compatibility of silicone hydrogel lens, this study compared and analyzed the properties of Amino modified silicone oil using mini and microemulsion technique, respectively. Optical and physical properties were evaluated by spectral transmittance, refractive index, water content, oxygen transmittance and contact angle measurements to evaluate the performance of the manufactured hydrogel lens. The spectral transmittance results revealed the copolymerization method lens showed 31 % of the visible light area, which did not satisfy the basic optical properties. However, the lens using the mini and microemulsion materials showed more than 90 % of the visible light area, satisfying the optical characteristics. In addition, all physical properties were superior to a basic hydrogel lens. The mini and microemulsion techniques effectively improved the stability and function of the ophthalmic hydrogel lens and are considered a promising ways of manufacturing an ophthalmic hydrogel contact lens with increased compatibility and stability.