• Journal of the Semiconductor & Display Technology
• /
• v.18 no.2
• /
• pp.73-77
• /
• 2019

Data mining techniques can also be used to increase the efficiency of production in the tax sector, which requires professional skills. As tax-related computerization was carried out, large amounts of data were accumulated, creating a good environment for data mining. In this paper, we have developed a system that can help tax accountant who have existing professional abilities by using data mining techniques on accumulated tax related data. The data mining technique used is random forest and improved by using f1-score. Using the implemented system, data accumulated over two years was learned, showing high accuracy at prediction.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.1
• /
• pp.79-86
• /
• 2019

In the recent industry, unmanned systems are expected to continue to spread throughout the economy. Especially in case of cosmetics, Users do not buy it right away. They look around, test it thoroughly, check the reviews, and decide on the purchase. Therefore, unmanned system using kiosk is more popular than face - to - face service of clerks. In this study, the persona analysis was completed based on the results obtained from the questionnaires and in - depth interviews. After sorting out the needs of the users, we applied them to the kiosk UI design of "Lalavela". The purpose of this study is to propose a kiosk UI design that helps many users who want to know information about the product though they are reluctant to ask directly to the clerk.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.1
• /
• pp.97-101
• /
• 2019

Understanding and classification of the human's emotion play an important tasks in interacting with human and machine communication systems. This paper proposes a novel emotion recognition method by extracting facial keypoints, which is able to understand and classify the human emotion, using active Appearance Model and the proposed classification model of the facial features. The existing appearance model scheme takes an expression of variations, which is calculated by the proposed classification model according to the change of human facial expression. The proposed method classifies four basic emotions (normal, happy, sad and angry). To evaluate the performance of the proposed method, we assess the ratio of success with common datasets, and we achieve the best 93% accuracy, average 82.2% in facial emotion recognition. The results show that the proposed method effectively performed well over the emotion recognition, compared to the existing schemes.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.117-119
• /
• 2021

With the development of the industry, the use of drones in specific mission flight is being actively studied. These drones fly a specified path and perform repetitive tasks. if the drone system will detect objects in real time, the performance of these mission flight will increase. In this paper, we implement object detection system and mount GPU acceleration to maximize the efficiency of limited device resources with drone video using Tensorflow Lite which enables in-device inference from a mobile device and Mobile SDK of DJI, a drone manufacture. For performance comparison, the average processing time per frame was measured when object detection was performed using only the CPU and when object detection was performed using the CPU and GPU at the same time.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.2
• /
• pp.137-140
• /
• 2021

High dynamic range (HDR) technology has been drawing attention in the field of imaging and consumer entertainment. As tools for capturing and creating HDR contents, encoding, and transmission evolve to support HDR formats, various display capabilities are being developed and increased. Hence, there is need for remapping native HDR imagery for display on lower quality legacy standard dynamic range (SDR) displays. This operation is referred to as tone mapping. In this paper, we present a sectional tone mapping method by Lenzen, and expand upon a tone mapping approach to improve temporal stability while maintaining picture quality. Compared to the existing block-based sectional tone mapping, our method uses the edge awareness-based tone mapping. We estimate the performance of the objective metric on temporal flickering. The experimental result shows that the algorithm maintains a smoother relationship between the output luminance values, and this reveals success in reducing halos and improving temporal stability with adopted edge aware filtering.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.77-80
• /
• 2022

Automatic Vision Inspection (AVI) systems automatically detect defect features and measure their sizes via camera vision. It has been populated because of the accuracy and consistency in terms of QC (Quality Control) of inspection processes. Also, it is important to predict the performance of an AVI to meet customer's specification in advance. AVI are usually suffered from false negative and positives. It can be overcome by providing extra information such as 3D depth information. Stereo vision processing has been popular for depth extraction of the 3D images from 2D images. However, stereo vision methods usually take long time to process. In this paper, retro optical system using reflectors is proposed and experimented to overcome the problem. The optical system extracts the depth without special SW processes. The vision sensor and optical components such as illumination and depth detecting module are integrated as a unit. The depth information can be extracted on real-time basis and utilized and can improve the performance of an AVI system.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.7-11
• /
• 2022

Object detection technology is one of the main research topics in the field of computer vision and has established itself as an essential base technology for implementing various vision systems. Recent DNN (Deep Neural Networks)-based algorithms achieve much higher recognition accuracy than traditional algorithms. However, it is well-known that the DNN model inference operation requires a relatively high computational power. In this paper, we analyze the inference time complexity of the state-of-the-art object detection architecture Yolov7 in various environments. Specifically, we compare and analyze the time complexity of four types of the Yolov7 model, YOLOv7-tiny, YOLOv7, YOLOv7-X, and YOLOv7-E6 when performing inference operations using CPU and GPU. Furthermore, we analyze the time complexity variation when inferring the same models using the Pytorch framework and the Onnxruntime engine.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.87-91
• /
• 2022

Bokeh effect is a stylistic technique that can produce blurring the background of photos. This paper implements to produce a bokeh effect with a single image by post processing. Generating depth map is a key process of bokeh effect, and depth map is an image that contains information relating to the distance of the surfaces of scene objects from a viewpoint. First, this work presents algorithms to determine the depth map from a single input image. Then, we obtain a sparse defocus map with gradient ratio from input image and blurred image. Defocus map is obtained by propagating threshold values from edges using matting Laplacian. Finally, we obtain the blurred image on foreground and background segmentation with bokeh effect achieved. With the experimental results, an efficient image processing method with bokeh effect applied using a single image is presented.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.4
• /
• pp.55-61
• /
• 2021

In this paper, we proposed and implemented defect detection methods of polarized film with half-wave phase retardation plates. We investigated the principles of phase retardation compensation and optical principle of half-wave phase retardation plates. We analyzed of samples of polarized film with half-wave phase retardation plates. The optical defect detection methods are proposed and the performance is validated with experiments.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.75-78
• /
• 2022

Deep Neural Networks (DNN) has become an essential data processing architecture for the implementation of multiple computer vision tasks. Recently, DNN-based algorithms achieve much higher recognition accuracy than traditional algorithms based on shallow learning. However, training and inference DNNs require huge computational capabilities than daily usage purposes of computers. Moreover, with increased size and depth of DNNs, CPUs may be unsatisfactory since they use serial processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. In this paper, we analyze the inference time complexity of DNNs using well-known computer vision library, OpenCV. We measure and analyze inference time complexity for three cases, CPU, GPU-Float32, and GPU-Float16.