• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.

• Nuclear Engineering and Technology
• /
• v.56 no.5
• /
• pp.1733-1737
• /
• 2024

In order to specify the location of the scintillation pixel that interacted with gamma rays in the positron emission tomography (PET) detector, conventionally, after acquiring a flood image, the location of interaction between the scintillation pixel and gamma ray could be specified through a pixel-segmentation process. In this study, the experimentally acquired signal was specified as the location of the scintillation pixel directly, without any conversion process, through the simulation data and the deep learning algorithm. To evaluate the accuracy of the specification of the scintillation pixel location through deep learning, a comparative analysis with experimental data through pixel segmentation was performed. In the same way as in the experiment, a detector was configured on the simulation, a model was built using the acquired data through deep learning, and the location was specified by applying the experimental data to the built model. Accuracy was calculated through comparative analysis between the specified location and the location obtained through the segmentation process. As a result, it showed excellent accuracy of about 85 %. When this method is applied to a PET detector, the position of the scintillation pixel of the detector can be specified simply and conveniently, without additional work.

• Journal of Advanced Navigation Technology
• /
• v.24 no.5
• /
• pp.430-437
• /
• 2020

The proposed model implements a model that improves the face prediction rate and recognition rate through learning with an artificial neural network using face detection, landmark and face recognition algorithms. After landmarking in the face images of a specific person, the proposed model use the previously learned Caffe model to extract face detection and embedding vector 128D. The learning is learned by building machine learning algorithms such as support vector machine (SVM) and deep neural network (DNN). Face recognition is tested with a face image different from the learned figure using the learned model. As a result of the experiment, the result of learning with DNN rather than SVM showed better prediction rate and recognition rate. However, when the hidden layer of DNN is increased, the prediction rate increases but the recognition rate decreases. This is judged as overfitting caused by a small number of objects to be recognized. As a result of learning by adding a clear face image to the proposed model, it is confirmed that the result of high prediction rate and recognition rate can be obtained. This research will be able to obtain better recognition and prediction rates through effective deep learning establishment by utilizing more face image data.

• Journal of Internet Computing and Services
• /
• v.20 no.3
• /
• pp.33-41
• /
• 2019

In this paper, we propose a method to learn the redesigned class with background and object for semantic segmentation of indoor scene image. Semantic image segmentation is a technique that divides meaningful parts of an image, such as walls and beds, into pixels. Previous work of semantic image segmentation has proposed methods of learning various object classes of images through neural networks, and it has been pointed out that there is insufficient accuracy compared to long learning time. However, in the problem of separating objects and backgrounds, there is no need to learn various object classes. So we concentrate on separating objects and backgrounds, and propose method to learn after class simplification. The accuracy of the proposed learning method is about 5 ~ 12% higher than the existing methods. In addition, the learning time is reduced by about 14 ~ 60 minutes when the class is configured differently In the same environment, and it shows that it is possible to efficiently learn about the problem of separating the object and the background.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1486-1494
• /
• 2021

Character recognition is a technology required in various platforms, such as smart parking and text to speech, and many studies are being conducted to improve its performance through new attempts. However, with low-quality image used for character recognition, a difference in resolution of the training image and test image for character recognition occurs, resulting in poor accuracy. To solve this problem, this paper designed an end-to-end learning neural network that combines image super-resolution and character recognition so that the character recognition model performance is robust against various quality data, and implemented an alternative whole learning algorithm to learn the whole neural network. An alternative end-to-end learning and recognition performance test was conducted using the license plate image among various text images, and the effectiveness of the proposed algorithm was verified with the performance test.

• Journal of the Korea Furniture Society
• /
• v.24 no.1
• /
• pp.42-50
• /
• 2013

The objective of this study is to explore basic type of character of humans and to suggest a design method of establishing a spatial construction environment for developing effective learning ability based on such type of character. As a range of research, spatial formative language was deduced and space design strategy for the children was suggested through an analysis of spatial requirements by exploring connectivity depending on features of 9 types of character through Enneagram. As a method of research, a process of suggesting a concrete method after defining an element of spatial construction and deducing a formative language for developing and strengthening effective learning ability for each type of character. As a result of research, the methods of children space design strategy for enhancing learning ability for leadership in a future specific fields were suggested through 9 different type of character with image of case study.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.607-614
• /
• 2016

In this paper, we propose an intelligent fire learning and detection system using convolutional neural networks (CNN). Through the convolutional layer of the CNN, various features of flame and smoke images are automatically extracted, and these extracted features are learned to classify them into flame or smoke or no fire. In order to detect fire in the image, candidate fire regions are first extracted from the image and extracted candidate regions are passed through CNN. Experimental results on various image shows that our system has better performances over previous work.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.12
• /
• pp.43-53
• /
• 2019

The construction industry has made great strides in the past decades by utilizing computer programs including CAD. However, compared to other manufacturing sectors, labor productivity is low due to the high proportion of workers' knowledge-based task in addition to simple repetitive task. Therefore, the knowledge-based task efficiency of workers should be improved by recognizing the visual information of computers. A computer needs a lot of training data, such as the ImageNet project, to recognize visual information. This study, aim at proposing building facade datasets that is efficiently constructed by quickly collecting building facade data through portal site road view and automatically labeling using deep learning as part of construction of image dataset for visual recognition construction by the computer. As a method proposed in this study, we constructed a dataset for a part of Dongseong-ro, Daegu Metropolitan City and analyzed the utility and reliability of the dataset. Through this, it was confirmed that the computer could extract the significant facade information of the portal site road view by recognizing the visual information of the building facade image. Additionally, In contribution to verifying the feasibility of building construction image datasets. this study suggests the possibility of securing quantitative and qualitative facade design knowledge by extracting the facade design knowledge from any facade all over the world.

• Journal of Drive and Control
• /
• v.20 no.2
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.