• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.345-359
• /
• 2017

Optical Character Recognition (OCR) that has been a main research topic of computer vision and artificial intelligence now extend its applications to detection of text area from video or image contents taken by camera devices and retrieval of text information from the area. This paper aims to implement a binarization algorithm that removes user intervention and provides robust performance to outdoor lights by using TopHat algorithm and channel transformation technique. In this study, we particularly concentrate on text information of outdoor signboards and validate our proposed technique using those data.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.60-67
• /
• 2020

Recently, artificial intelligence related technologies including machine learning are being applied to various fields, and the demand is also increasing. In particular, with the development of AR, VR, and MR technologies related to image processing, the utilization of computer vision based on deep learning has increased. The algorithms for object recognition and detection based on deep learning required for image processing are diversified and advanced. Accordingly, problems that were difficult to solve with the existing methodology were solved more simply and easily by using deep learning. This paper introduces various deep learning-based object recognition and extraction algorithms used to detect and recognize various objects in an image and analyzes the technologies that attract attention.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4763-4775
• /
• 2020

This research aims to develop a deep learning-based method that automatically detects and segments the defects on railroad surfaces to reduce the cost of visual inspection of the railroad. We developed our segmentation model by modifying a fully convolutional network model [1], a well-known segmentation model used for machine learning, to detect and segment railroad surface defects. The data used in this research are images of the railroad surface with one or more defect regions. Railroad images were cropped to a suitable size, considering the long height and relatively narrow width of the images. They were also normalized based on the variance and mean of the data images. Using these images, the suggested model was trained to segment the defect regions. The proposed method showed promising results in the segmentation of defects. We consider that the proposed method can facilitate decision-making about railroad maintenance, and potentially be applied for other analyses.

• International Journal of Advanced Culture Technology
• /
• 제10권1호
• /
• pp.302-309
• /
• 2022

Occupational safety accidents are caused by various factors, and it is difficult to predict when and why they occur, and it is directly related to the lives of workers, so the interest in safety accidents is increasing every year. Therefore, in order to reduce safety accidents at industrial fields, workers are required to wear personal protective equipment. In this paper, we proposes a method to automatically check whether workers are wearing safety helmets among the protective equipment in the industrial field. It detects whether or not the helmet is worn using YOLOv5, a computer vision-based deep learning object detection algorithm. We transfer learning the s model among Yolov5 models with different learning rates and epochs, evaluate the performance, and select the optimal model. The selected model showed a performance of 0.959 mAP.

• ETRI Journal
• /
• 제44권2호
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• Journal of information and communication convergence engineering
• /
• 제20권3호
• /
• pp.153-159
• /
• 2022

Plain radiographic analysis is the initial imaging modality for suspected small bowel obstruction. Among the many features that affect the diagnosis of small bowel obstruction (SBO), the presence of gas-filled or fluid-filled small bowel loops is the most salient feature that can be automatized by computer vision algorithms. In this study, we compare three frequently applied pixel-clustering algorithms for extracting gas-filled areas without human intervention. In a comparison involving 40 suspected SBO cases, the Possibilistic C-Means and Fuzzy C-Means algorithms exhibited initialization-sensitivity problems and difficulties coping with low intensity contrast, achieving low 72.5% and 85% success rates in extraction. The Adaptive Resonance Theory 2 algorithm is the most suitable algorithm for gas-filled region detection, achieving a 100% success rate on 40 tested images, largely owing to its dynamic control of the number of clusters.

• Journal of information and communication convergence engineering
• /
• 제20권3호
• /
• pp.226-233
• /
• 2022

Video surveillance is widely used in security surveillance, military navigation, intelligent transportation, etc. Its main research fields are pattern recognition, computer vision and artificial intelligence. This article uses OpenCV to detect and track vehicles, and monitors by establishing an adaptive model on a stationary background. Compared with traditional vehicle detection, it not only has the advantages of low price, convenient installation and maintenance, and wide monitoring range, but also can be used on the road. The intelligent analysis and processing of the scene image using CAMSHIFT tracking algorithm can collect all kinds of traffic flow parameters (including the number of vehicles in a period of time) and the specific position of vehicles at the same time, so as to solve the vehicle offset. It is reliable in operation and has high practical value.

• Journal of Information Processing Systems
• /
• 제19권1호
• /
• pp.33-45
• /
• 2023

This paper proposes an algorithm that automatically converts images into Pipo, painting images using OpenCV-based image processing technology. The existing "purity," "palm," "puzzling," and "painting," or Pipo, painting image production method relies on manual work, so customized production has the disadvantage of coming with a high price and a long production period. To resolve this problem, using the OpenCV library, we developed a technique that automatically converts an image into a Pipo painting image by designing a module that changes an image, like a picture; draws a line based on a sector boundary; and writes sector numbers inside the line. Through this, it is expected that the production cost of customized Pipo painting images will be lowered and that the production period will be shortened.

• 전자통신동향분석
• /
• 제38권5호
• /
• pp.12-22
• /
• 2023

The development of neural networks is evolving towards the adoption of transformer structures with attention modules. Hence, active research focused on extending the concept of lightweight neural network algorithms and hardware acceleration is being conducted for the transition from conventional convolutional neural networks to transformer-based networks. We present a survey of state-of-the-art research on lightweight neural network algorithms and hardware architectures to reduce memory usage and accelerate both inference and training. To describe the corresponding trends, we review recent studies on token pruning, quantization, and architecture tuning for the vision transformer. In addition, we present a hardware architecture that incorporates lightweight algorithms into artificial intelligence processors to accelerate processing.

• International Journal of Advanced Culture Technology
• /
• 제11권3호
• /
• pp.253-259
• /
• 2023

The increasing incorporation of AI in video storyboard creation has been observed recently. Traditionally, the production of storyboards requires significant time, cost, and specialized expertise. However, the integration of AI can amplify the efficiency of storyboard creation and enhance storytelling. In Korea, AiSAC stands at the forefront of AI-driven storyboard platforms, boasting the capability to generate realistic images built on open datasets foundations. Yet, a notable limitation is the difficulty in intricately conveying a director's vision within the storyboard. To address this challenge, we proposed the application of image generation features from ChatGPT and Midjourney to AiSAC. Through this research, we aimed to enhance the efficiency of storyboard production and refined the intricacy of expression, thereby facilitating advancements in the video production process.