• Journal of Internet Computing and Services
• /
• v.8 no.6
• /
• pp.155-167
• /
• 2007

There are four types of human beings according to the Sasang Typology, Oriental medical doctors frequently prescribe healthcare information and treatment depending on one's type, The feature ratios (Table 1) on the human face are the most important criterions to decide which type a patient is. In this paper, we proposed a system to extract these feature ratios from the people's side face, There are two challenges in acquiring the feature ratio: one that selecting representative features; the other, that detecting region of interest from human profile facial image effectively and calculating the feature ratio accurately. In our system, an adaptive color model is used to separate human side face from background, and the method based on geometrical model is designed for region of interest detection. Then we present the error analysis caused by image variation in terms of image size and head pose, To verify the efficiency of the system proposed in this paper, several experiments are conducted using about 173 korean's left side facial photographs. Experiment results shows that the accuracy of our system is increased 17,99% after we combine the front face features with the side face features, instead of using the front face features only.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.85-92
• /
• 2023

Deep learning applications are increasingly being leveraged for disease detection tasks in medical imaging modalities such as X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). Most data-centric deep learning challenges necessitate the use of supervised learning methodologies to attain high accuracy and to facilitate performance evaluation through comparison with the ground truth. Supervised learning mandates a substantial amount of image and label sets, however, procuring an adequate volume of medical imaging data for training is a formidable task. Various data augmentation strategies can mitigate the underfitting issue inherent in supervised learning-based models that are trained on limited medical image and label sets. This research investigates the enhancement of a deep learning-based rib fracture segmentation model and the efficacy of data augmentation techniques such as left-right flipping, rotation, and scaling. Augmented dataset with L/R flipping and rotations(30°, 60°) increased model performance, however, dataset with rotation(90°) and ⨯0.5 rescaling decreased model performance. This indicates the usage of appropriate data augmentation methods depending on datasets and tasks.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.17-23
• /
• 2020

Biometric information indicating measurement items related to human characteristics has attracted great attention as security technology with high reliability since there is no fear of theft or loss. Among these biometric information, fingerprints are mainly used in fields such as identity verification and identification. If there is a problem such as a wound, wrinkle, or moisture that is difficult to authenticate to the fingerprint image when identifying the identity, the fingerprint expert can identify the problem with the fingerprint directly through the preprocessing step, and apply the image processing algorithm appropriate to the problem. Solve the problem. In this case, by implementing artificial intelligence software that distinguishes fingerprint images with cuts and wrinkles on the fingerprint, it is easy to check whether there are cuts or wrinkles, and by selecting an appropriate algorithm, the fingerprint image can be easily improved. In this study, we developed a total of 17,080 fingerprint databases by acquiring all finger prints of 1,010 students from the Royal University of Cambodia, 600 Sokoto open data sets, and 98 Korean students. In order to determine if there are any injuries or wrinkles in the built database, criteria were established, and the data were validated by experts. The training and test datasets consisted of Cambodian data and Sokoto data, and the ratio was set to 8: 2. The data of 98 Korean students were set up as a validation data set. Using the constructed data set, five CNN-based architectures such as Classic CNN, AlexNet, VGG-16, Resnet50, and Yolo v3 were implemented. A study was conducted to find the model that performed best on the readings. Among the five architectures, ResNet50 showed the best performance with 81.51%.

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.2
• /
• pp.16-22
• /
• 2001

In this paper we mose a new scheme for recognition of deformed letters by extracting feature vectors based on Gibbs distributions which are well suited for representing the spatial continuity. The extracted feature vectors are comprised of 2-D conditional moments which are invariant under translation, rotation, and scale of an image. The Algorithm for pattern recognition of deformed letters contains two parts: the extraction of feature vector and the recognition process. (i) We extract feature vector which consists of an improved 2-D conditional moments on the basis of estimated conditional Gibbs distribution for an image. (ii) In the recognition phase, the minimization of the discrimination cost function for a deformed letters determines the corresponding template pattern. In order to evaluate the performance of the proposed scheme, recognition experiments with a generated document was conducted. on Workstation. Experiment results reveal that the proposed scheme has high recognition rate over 96%.

• KIISE Transactions on Computing Practices
• /
• v.21 no.10
• /
• pp.658-669
• /
• 2015

The paradigm of game development changes with technological trends. If the system can analyze and determine undefined inputs, users' input choices are not restricted. Therefore, game scenarios can have multifarious flows depending upon the user's input data. In this paper, we propose a method of including an output plan in the game system that is based on the user's input but is not restricted to predefined choices. We have implemented an experimental game on the Android platform by combining network communication and APIs. The game interface works as follows: first, the user's input data is transmitted to the server using HTTP protocol; then, the server carries out an analysis on the input data; and finally, the server returns the decision result to the game device. The game can provide users a scenario that corresponds to the decision results. In this paper, we used an image file for the user's input data format. The server calculates similarities between the user's image file and reference images obtained from the Naver Image Search API and then returns determination results. We have confirmed the value of integrating the game development framework with other computing technologies demonstrating the potential of the proposed methods for application to various future game interfaces.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.270-278
• /
• 2022

This study was conducted using deep learning technology to classify for 'Mihwang' peach maturity with RGB images and fruit quality attributes during fruit development and maturation periods. The 730 images of peach were used in the training data set and validation data set at a ratio of 8:2. The remains of 170 images were used to test the deep learning models. In this study, among the fruit quality attributes, firmness, Hue value, and a^* value were adapted to the index with maturity classification, such as immature, mature, and over mature fruit. This study used the CNN (Convolutional Neural Networks) models for image classification; VGG16 and InceptionV3 of GoogLeNet. The performance results show 87.1% and 83.6% with Hue left value in VGG16 and InceptionV3, respectively. In contrast, the performance results show 72.2% and 76.9% with firmness in VGG16 and InceptionV3, respectively. The loss rate shows 54.3% and 62.1% with firmness in VGG16 and InceptionV3, respectively. It considers increasing for adapting a field utilization with firmness index in peach.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.297-302
• /
• 2012

In this paper, we present a object detection and tracking method based on image context analysis. It is robust from the image variations such as complicated background, dynamic movement of the object. Image context analysis is carried out using the hybrid network of k-means and RBF. The proposed object detection employs context-driven adaptive Bayesian framework to relive the effect due to uneven object images. The proposed method used feature vector generator using 2D Haar wavelet transform and the Bayesian discriminant method in order to enhance the speed of learning. The system took less time to learn, and learning in a wide variety of data showed consistent results. After we developed the proposed method was applied to real-world environment. As a result, in the case of the object to detect pass outside expected area or other changes in the uncertain reaction showed that stable. The experimental results show that the proposed approach can achieve superior performance using various data sets to previously methods.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1643-1656
• /
• 2010

It is necessary to develop a system to judge inferiority of goods to minimize the loss at small factories in which produces various kinds of goods with small amounts. That system can be developed based on HTM theory. HTM is a model to apply the operation principles of the neocortex in human brain to the machine learning. We have to build the trained HTM network to use the HTM-based machine learning system. It requires the knowledge for the HTM theory. This paper presents the design and implementation of the training system to support the development of HTM networks which recognize the molding parts to judge its badness. This training system allows field technicians to train the HTM network with high accuracy without the knowledge of the HTM theory. It also can be applied to any kind of the HTM-based judging systems for molding parts.

• Journal of Advanced Navigation Technology
• /
• v.16 no.2
• /
• pp.386-393
• /
• 2012

In this paper, we propose an efficient multi-object recognition and tracking scheme based on interest points of objects and their feature descriptors. To do that, we first define a set of object types of interest and collect their sample images. For sample images, we detect interest points and construct their feature descriptors using SURF. Next, we perform a statistical analysis of the local features to select representative points among them. Intuitively, the representative points of an object are the interest points that best characterize the object. in addition, we make the movement vectors of the interest points based on matching between their SURF descriptors and track the object using these vectors. Since our scheme treats all the objects independently, it can recognize and track multiple objects simultaneously. Through the experiments, we show that our proposed scheme can achieve reasonable performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.3
• /
• pp.262-268
• /
• 2010

In this paper, this study restores the distorted image to its original image by compensating for the distortion of image from a fixed-focus camera lens. The various developments and applications of the imaging devices and the image sensors used in a wide range of industries and expanded use, but due to the needs of the small size and light weight of the camera, the distortion from acquiring images of the distorted curvature of the lens tends to affect many. In particular, the three-dimensional imaging camera, each different distortion of left and right lens cause the degradation of three-dimensional sensitivity and left-right image distortion ratio. we approached the way of generalizing the approximate equations to restore each part of left-right camera images to the coordinators of the original images. The adaptive Neuro-Fuzzy Inference System is configured for it. This system is divided from each membership function and is inferred by 1st order Sugeno Fuzzy model. The result is that the compensated images close to the left, right original images. Using low-cost and compact imaging lens by which also determine the exact three-dimensional image-sensing capabilities and will be able to expect from this study.