• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.799-802
• /
• 2000

There are many methods that extract the depth information based on the blurring ratio for object point in DFD(Depth from Defocus). However, it is often difficult to measure the depth of the object in two-dimensional images that was affected by various elements such as edges, textures, and etc. To solve the problem, new DFD method employing the texture classification with a neural network is proposed. This method extracts the feature of texture from an evaluation window in an image and classifies the texture class. Finally, It allocates the correspondent value for the blurring ratio. The experimental result shows that the method gives more accurate than the previous methods.

• The KIPS Transactions:PartD
• /
• v.11D no.7 s.96
• /
• pp.1443-1450
• /
• 2004

The clustering characteristics for a number of classes, and defining the inheritance relations between the classes is a difficult and complex problem in an early stage of object oriented software development. We discuss a traditional iterative approach for the reuse of the existing classes in a library and an integrated approach to creating a number of new classes presented in this study. This paper formulates a character-istic clustering problem for zero-one integer programming and presents a network solution method with illustrative examples and the basic rules to define the inheritance relations between the classes. The network solution method for a characteristic clustering problem is based on a distance parameter between every pair of objects with characteristics. We apply the approach to a real problem taken from industry.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.710-715
• /
• 2004

The design problem of manufacturing system is addressed, adopting the closed queueing network model with multiple loops and re-entrant flows. The entire design problem is divided into two hierarchical sub-problems of (1) determining the station configuration and (2) optimizing the lot constitution; then they are tackled by neighbor search algorithm (NSA) and greedy mean value analysis (GMVA), respectively. Unlike the conventional MVA concerning multi-class closed queueing networks, the GMVA doesn't stick to a fixed lot proportion; rather it tries to find the optimal balance. The NSA, on the other hand, improves the object function value by altering the station configuration successively with its superior neighbor. The moderate time complexity, presented in big-${o}$ notation, enables us to apply the method even to the large-size practical cases, and the CPU time of an enlarged problem can be approximated by the same equation. The validity of our analytic approach is backed up by simulation studies with a widespread simulation package.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1919-1925
• /
• 2022

In this paper, we propose an image-to-image translation approach based on the conditional generative adversarial network for semantic segmentation. Semantic segmentation is the task of clustering parts of an image together which belong to the same object class. Unlike the traditional pixel-wise classification approach, the proposed method parses an input RGB image to its corresponding semantic segmentation mask using a pixel regression approach. The proposed method is based on the Pix2Pix image synthesis method. We employ residual connections-based convolutional neural network architectures for both the generator and discriminator architectures, as the residual connections speed up the training process and generate more accurate results. The proposed method has been trained and tested on the NYU-depthV2 dataset and could achieve a good mIOU value (49.5%). We also compare the proposed approach to the current methods in semantic segmentation showing that the proposed method outperforms most of those methods.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.12
• /
• pp.1-7
• /
• 2021

The deep learning image processing technique was used to prevent accidents in lathe work caused by worker negligence. During lathe operation, when the chuck is rotated, it is very dangerous if the operator's hand is near the chuck. However, if the chuck is stopped during operation, it is not dangerous for the operator's hand to be in close proximity to the chuck for workpiece measurement, chip removal or tool change. We used YOLO (You Only Look Once), a deep learning image processing program for object detection and classification. Lathe work images such as hand, chuck rotation and chuck stop are used for learning, object detection and classification. As a result of the experiment, object detection and class classification were performed with a success probability of over 80% at a confidence score 0.5. Thus, we conclude that the artificial intelligence deep learning image processing technique can be effective in preventing incidents resulting from worker negligence in future manufacturing systems.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2002.05a
• /
• pp.273-277
• /
• 2002

This paper describes an optimal synthesis method of binary neural network(BNN) for an approximation problem of a circular region and synthetic image having four class using a newly proposed learning algorithm. Our object is to minimize the number of connections and neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm(NETLA) based on the multilayer BNN. The synthesis method in the NETLA is based on the extension principle of Expanded and Truncated Learning (ETL) learning algorithm using the multilayer perceptron and is based on Expanded Sum of Product (ESP) as one of the boolean expression techniques. The number of the required neurons in hidden layer can be reduced and fasted for learning pattern recognition.. The superiority of this NETLA to other algorithms was proved by simulation.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.11
• /
• pp.2671-2678
• /
• 1997

The MHEG-5 standard defines representation of multimedia and hypermedia information. The MHEG-5 can make it possible to interchange and present information between heterogeneous networked environment. Also, it can provide real-time user interaction. MHEG-5 object generating is the essential requirements for the MHEG-5 applications, In this paper, we designed encoding/decoding class library for the MHEG-5 objects. We can use it for the interchange on the network. The designed class library can provide base technology for the MHEG-5 based distributed multimedia and hypermedia services on the networked environment.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.31-40
• /
• 2019

To understand how a Convolutional Neural Network (CNN) model captures the features of a pattern to determine which class it belongs to, in this paper, we use Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize and analyze how well a CNN model behave on the CNU weeds dataset. We apply this technique to Resnet model and figure out which features this model captures to determine a specific class, what makes the model get a correct/wrong classification, and how those wrong label images can cause a negative effect to a CNN model during the training process. In the experiment, Grad-CAM highlights the important regions of weeds, depending on the patterns learned by Resnet, such as the lobe and limb on 미국가막사리, or the entire leaf surface on 단풍잎돼지풀. Besides, Grad-CAM points out a CNN model can localize the object even though it is trained only for the classification problem.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.329-332
• /
• 2023

3D Object Detection using deep neural network has been developed a lot for obstacle detection in autonomous vehicles because it can recognize not only the class of target object but also the distance from the object. But in the case of 3D Object Detection models, the detection performance for distant objects is lower than that for nearby objects, which is a critical issue for autonomous vehicles. In this paper, we introduce a technique that increases the performance of 3D object detection models, particularly in recognizing distant objects, by generating virtual 3D vehicle data and adding it to the dataset used for model training. We used a spherical point tracing method that leverages the characteristics of 3D LiDAR sensor data to create virtual vehicles that closely resemble real ones, and we demonstrated the validity of the virtual data by using it to improve recognition performance for objects at all distances in model training.