• Journal of the Korea Computer Graphics Society
• /
• v.8 no.1
• /
• pp.1-11
• /
• 2002

In order to widely use volume rendering technology in practical fields, a user should be able to control the classification parameter interactively and extract a meaningful information easily from the 3D data as fast as it can be. Previous work on an accelerating volume rendering reconstructs an isotropic volume from an anisotropic one and classifies in pre-processing time and then renders the classified volume rapidly in run time. But, this traditional step may result in long pre-processing time and no real-time feedback. In this paper, we present an efficient classification and rendering method that allows a user to set the opacity transfer function interactively at rendering time on a personal computer without special-purpose hardware.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.11
• /
• pp.124-130
• /
• 2009

In the multi-stage shape drawing process, the most important aspect for the economy is the correct design of the various drawing stage. For most of the products commonly available round or square materials can be used as initial material. However, special products should be pre-rolled. This study proposes a process design method of multi-stage shape drawing process for producing cross roller guide. Firstly, a standard classification of shape drawing process is suggested based on the requirement of pre-rolling process. And a design method is proposed to design the intermediate die shape. The process design method is applied to design the multi-stage shape drawing process for producing cross roller guide. Finally, the effectiveness of the proposed design method is verified by FE-analysis and shape drawing experiment.

• Journal of Multimedia Information System
• /
• v.6 no.2
• /
• pp.49-60
• /
• 2019

Plants are very crucial for life on Earth. There is a wide variety of plant species available, and the number is increasing every year. Species knowledge is a necessity of various groups of society like foresters, farmers, environmentalists, educators for different work areas. This makes species identification an interdisciplinary interest. This, however, requires expert knowledge and becomes a tedious and challenging task for the non-experts who have very little or no knowledge of the typical botanical terms. However, the advancements in the fields of machine learning and computer vision can help make this task comparatively easier. There is still not a system so developed that can identify all the plant species, but some efforts have been made. In this study, we also have made such an attempt. Plant identification usually involves four steps, i.e. image acquisition, pre-processing, feature extraction, and classification. In this study, images from Swedish leaf dataset have been used, which contains 1,125 images of 15 different species. This is followed by pre-processing using Gaussian filtering mechanism and then texture and color features have been extracted. Finally, classification has been done using Multiclass-support vector machine, which achieved accuracy of nearly 93.26%, which we aim to enhance further.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1818-1832
• /
• 2022

Violence in the Internet era poses a new challenge to the current counter-riot work, and according to research and analysis, most of the violent incidents occurring are related to the dissemination of violence images. The use of the popular deep learning neural network to automatically analyze the massive amount of images on the Internet has become one of the important tools in the current counter-violence work. This paper focuses on the use of transfer learning techniques and the introduction of an attention mechanism to the residual network (ResNet) model for the classification and identification of violence images. Firstly, the feature elements of the violence images are identified and a targeted dataset is constructed; secondly, due to the small number of positive samples of violence images, pre-training and attention mechanisms are introduced to suggest improvements to the traditional residual network; finally, the improved model is trained and tested on the constructed dedicated dataset. The research results show that the improved network model can quickly and accurately identify violence images with an average accuracy rate of 92.20%, thus effectively reducing the cost of manual identification and providing decision support for combating rebel organization activities.

• Journal of Korean Society for Geospatial Information Science
• /
• v.4 no.2 s.8
• /
• pp.181-193
• /
• 1996

A new technique for land cover classification which applies digital image pre-classified by unsupervised classification technique, clustering, to Canonical Correlation Analysis(CCA) was proposed in this paper. Compared with maximum likelihood classification, the proposed technique had a good flexibility in selecting training areas. This implies that any selected position of training areas has few effects on classification results. Land cover of each cluster designated by CCA after clustering is able to be used as prior information for maximum likelihood classification. In case that the same training areas are used, accuracy of classification using Canonical Correlation Analysis after cluster analysis is better than that of maximum likelihood classification. Therefore, a new technique proposed in this study will be able to be put to practical use. Moreover this will play an important role in the construction of GIS database

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.7
• /
• pp.1202-1208
• /
• 2020

Objective: The aim of this study was to identify a distribution pattern of meat quality grade (MQG) as a function of carcass yield index (CYI) and the gender of Hanwoo (bull, cow, and steer) to determine the optimum point between both yield and quality. We also attempted to identify how pre- and post-deboning variables affect the gender-specific beef quality of Hanwoo. Methods: A total of 31 deboning variables, consisting of 7 pre-deboning and 24 post-deboning variables from bulls (n = 139), cows (n = 69), and steers (n = 153), were obtained from the National Institute of Animal Science (NIAS) in South Korea. The database was reconstructed to be suitable for a statistical significance test between the CYI and the MQG as well as classification of meat quality. Discriminant function analysis was used for classifying MQG using the deboning parameters of Hanwoo by gender. Results: The means of CYI according to 1+, 1, 2, and 3 of MQG were 68.64±2.02, 68.85±1.94, 68.62±5.88, and 70.99±3.32, respectively. High carcass yield correlated with low-quality grade, while high-quality meat most frequently was obtained from steers. The classification ability of pre-deboning parameters was higher than that of post-deboning parameters. Moisture and the shear force were the common significant parameters in all discriminant functions having a classification accuracy of 80.6%, 71%, and 56.9% for the bull, cow, and steer, respectively. Conclusion: This study provides basic information for predicting the meat quality by gender using pre-deboning variables consistent with the actual grading index.

• Journal of Animal Reproduction and Biotechnology
• /
• v.36 no.2
• /
• pp.99-105
• /
• 2021

In horse management, the alarm system with sensors in the foaling period enables the breeder can appropriately prepare the time of the parturition. It is important to prevent losses by unpredictable parturition because there are several high risks such as dystocia and the death of foals and mares during foaling. However, unlike analysis in the alarm system that detects specific motions has been widely performed, analysis of classification following specific behavior patterns or number needs to be more organized. Thus, the objective of this study is to classify signs of the specific behaviors of the mares for the prediction of pre-foaling behaviors. Five Thoroughbred mares (9-20 yrs) were randomly selected for observation of the pre-foaling behaviors. The behaviors were monitored for 90 min that was divided into three different periods as 1) from -90 to -60 min, 2) from -60 to -30 min, 3) from -30 min to the time for the discharge of the amniotic fluid, respectively. The behaviors were divided into two different categories as state and frequent behaviors and each specific behavioral pattern for classification was individually described. In the state behaviors, the number of mares in the standing of the foaling group (3.17 ± 0.18^b) at period 3 was significantly higher than the control group (1.67 ± 0.46^a). In contrast, the number of the mares in the eating of the foaling group (1.17 ± 0.34^b) at period 3 was significantly lower than the control group (3.33 ± 0.46^a). In the frequent behaviors, the weaving of the foaling group was significantly higher than the control group, and looking at the belly of the foaling group was significantly lower than the control group. In period 2, defecation, weaving, and lowering the head of the foaling group were significantly higher than the control group, respectively. In period 3, sitting down and standing up, pawing, weaving, and lowering the head in the foaling group were also significantly higher than the control group. In conclusion, the behavior is significantly different in foaling periods, and the prediction of foaling may be feasible by the detection of the pre-foaling behaviors in the mares.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.39-47
• /
• 2021

The construction of high-quality input features through effective segmentation is essential for increasing the sentence comprehension of a language model. Improving the quality of them directly affects the performance of the downstream task. This paper comparatively studies the segmentation that effectively reflects the linguistic characteristics of Korean regarding word and sentence classification. The segmentation types are defined in four categories: eojeol, morpheme, syllable and subchar, and pre-training is carried out using the RoBERTa model structure. By dividing tasks into a sentence group and a word group, we analyze the tendency within a group and the difference between the groups. By the model with subchar-level segmentation showing higher performance than other strategies by maximal NSMC: +0.62%, KorNLI: +2.38%, KorSTS: +2.41% in sentence classification, and the model with syllable-level showing higher performance at maximum NER: +0.7%, SRL: +0.61% in word classification, the experimental results confirm the effectiveness of those schemes.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.133-145
• /
• 2022

Compared to the continuously increasing dog population and industry size in Korea, systematic analysis of related data and research on breed classification methods are very insufficient. In this paper, an automatic breed classification method is proposed using deep learning technology for 14 major dog breeds domestically raised. To do this, dog images are collected for deep learning training and a dataset is built, and a breed classification algorithm is created by performing transfer learning based on VGG-16 and Resnet-34 as backbone networks. In order to check the transfer learning effect of the two models on dog images, we compared the use of pre-trained weights and the experiment of updating the weights. When fine tuning was performed based on VGG-16 backbone network, in the final model, the accuracy of Top 1 was about 89% and that of Top 3 was about 94%, respectively. The domestic dog breed classification method and data construction proposed in this paper have the potential to be used for various application purposes, such as classification of abandoned and lost dog breeds in animal protection centers or utilization in pet-feed industry.

• The KIPS Transactions:PartD
• /
• v.12D no.6 s.102
• /
• pp.829-836
• /
• 2005

The way to assign a splitting criterion for correct object classification is the main issue in all decisions trees. This paper describes new splitting rules for classification in order to find an optimal split point. Unlike the current splitting rules that are provided by searching all threshold values, this paper proposes the splitting rules that we based on the probabilities of pre assigned intervals. Our methodology provides that user can control the accuracy of tree by adjusting the number of intervals. In addition, we applied the proposed splitting rules to a set of image data that was retrieved by parameterized feature extraction to recognize image objects.