• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.691-702
• /
• 2004

In this paper, we propose a sequence of method which extrats ROIs(Region of Interests) rapidly from the parcel image of large size. In the proposed method, original image is spilt into the small masks, and the meaningful masks, the ROIs, are extracted by two criterions sequentially The first criterion is difference of pixel value between Inner points, and the second is deviation of it. After processing, some informational ROIs-the areas of bar code, characters, label and the outline of object-are acquired. Using diagonal axis of each ROI and the feature of various 2D bar code, the area of 2D bar code can be extracted from the ROIs. From an experiment using above methods, various ROIs are extracted less than 200msec from large-size parcel image, and 2D bar code region is selected by the accuracy of 100％.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.50-56
• /
• 2020

With the rapid development of deep neural network theory and application research, the effect of face detection has been improved. However, due to the complexity of deep neural network calculation and the high complexity of the detection environment, how to detect face quickly and accurately becomes the main problem. This paper is based on the relatively simple model of the MTCNN model, using FDDB (Face Detection Dataset and Benchmark Homepage), LFW (Field Label Face) and FaceScrub public datasets as training samples. At the same time of sorting out and introducing MTCNN(Multi-Task Cascaded Convolutional Neural Network) model, it explores how to improve training speed and Increase performance at the same time. In this paper, the dynamic image pyramid technology is used to replace the traditional image pyramid technology to segment samples, and OHEM (the online hard example mine) function in MTCNN model is deleted in training, so as to improve the training speed.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.113-120
• /
• 2022

Mongolian folk songs are inspired by Mongolian labor songs and are classified into long and short songs. Mongolian long songs have ancient origins, are rich in legends, and are a great source of folklore. So it was inscribed by UNESCO in 2008. Mongolian written literature is formed under the direct influence of oral literature. Mongolian long song has 3 classes: ayzam, suman, and besreg by their lyrics and structure. In ayzam long song, the world perfectly embodies the philosophical nature of world phenomena and the nature of human life. Suman long song has a wide range of topics such as the common way of life, respect for ancestors, respect for fathers, respect for mountains and water, livestock and animal husbandry, as well as the history of Mongolia. Besreg long songs are dominated by commanded and trained characters. In this paper, we proposed a method to classify their 3 types of long songs using machine learning, based on their lyrics structures without semantic information. We collected lyrics of over 80 long songs and extracted 11 features from every single song. The features are the name of a song, number of the verse, number of lines, number of words, general value, double value, elapsed time of verse, elapsed time of 5 words, and the longest elapsed time of 1 word, full text, and type label. In experimental results, our proposed features show on average 78% recognition rates in function type machine learning methods, to classify the ayzam, suman, and besreg classes.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.681-684
• /
• 2021

In this paper, we study image clustering without labeling using machine learning techniques. We proposed an unsupervised machine learning technique to design an image clustering model that automatically categorizes images into groups. Our experiment focused on inception convolutional neural networks (inception V3) with k-mean methods to cluster images. For this, we collect the public datasets containing Food-K5, Flowers, Handwritten Digit, Cats-dogs, and our dataset Rice Germination, and the owner dataset Palm print. Our experiment can expand into three-part; First, format all the images to un-label and move to whole datasets. Second, load dataset into the inception V3 extraction image features and transferred to the k-mean cluster group hold on six classes. Lastly, evaluate modeling accuracy using the confusion matrix base on precision, recall, F1 to analyze. In this our methods, we can get the results as 1) Handwritten Digit (precision = 1.000, recall = 1.000, F1 = 1.00), 2) Food-K5 (precision = 0.975, recall = 0.945, F1 = 0.96), 3) Palm print (precision = 1.000, recall = 0.999, F1 = 1.00), 4) Cats-dogs (precision = 0.997, recall = 0.475, F1 = 0.64), 5) Flowers (precision = 0.610, recall = 0.982, F1 = 0.75), and our dataset 6) Rice Germination (precision = 0.997, recall = 0.943, F1 = 0.97). Our experiment showed that modeling could get an accuracy rate of 0.8908; the outcomes state that the proposed model is strongest enough to differentiate the different images and classify them into clusters.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.150-153
• /
• 2022

This paper reports a technique that automatically extracts object shapes through Dense-Net, and subsequently, detects the objects using Mask R-CNN in a manufacturing site, in which workers and objects are mixed. It is based on the customized factory dataset by targeting workers, machines, tools, control boxes, and products as the objects. Mask R-CNN supports multi-object recognition as a well-known object recognition method, while Dense-Net effectively extracts a feature from multiple and overlapping objects. After immediate implementation using the two technologies, the object is naturally extracted from a still image of the manufacturing site to describe image. Afterwards, the result is planned to be used to detect workers' abnormal behavior by adding a label on the objects.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Food Science of Animal Resources
• /
• v.33 no.6
• /
• pp.781-786
• /
• 2013

Nutrients fortified dairy products declare their contents on the label for nutrition claim and marketing. However, there are few monitoring studies about relations between actual quantities of fortified nutrients and the described ones on the label. This study was carried out for comparing actual fortified nutrient contents with labeled ones. Forty calcium fortified dairy products and twenty four fructooligosaccharides (FOS) fortified dairy products were sampled at supermarkets located in Anyang, Korea from March to November in 2010. Calcium contents were analyzed by using inductively coupled plasma optical emission spectrometry followed by microwave sample digestion, and FOS contents were analyzed by HPLC-ELSD followed by solvent extraction. In fresh milk, calcium contents ranged from 1.0 to 2.4 mg/mL, and those values were 87~127% of their labeled contents. In fermented milk products and cheeses, calcium contents ranged from 0.3 to 1.6 mg/g (89~131% of their labeled contents), 4.2 to 23.0 mg/g (83~127% of their labeled contents), respectively. FOS contents ranged from 9.09 to 18.89 mg/g in FOS contents labeled products and showed 83~154% compared to their labeled quantity, and ranged from 1.3~30.8 mg/g in products without quantity labeling. In conclusion, the amounts of calcium and FOS in dairy products were above 80% compared to their labeled ones and conformed to the Korean official livestock products labeling standard.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.33 no.2
• /
• pp.381-385
• /
• 2004

This study was conducted to develop an HPLC method for determining pantothenic acid in fortified foods which has typically been determined by microbiological assay (MBA) according to AOAC and Korean Food Code approved methods. Pantothenic acid was determined by reversed-phase ion-pair HPLC using UV absorption (200 nm) after extraction with 20 mM potassium phosphate solution by sonication. The recovery of spiked samples and detection limit (LOD) by HPLC were 83.5∼109.6% and 0.5 ppm (mg/kg), respectively. The LOD of the microbiological assay (MBA) was much lower than that of HPLC. The concentrations of pantothenic acid analyzed in all tested samples (n=13) confirmed compliance with declared label claims. The range of recovery ratio by the HPLC method when compared to the microbiological assay was 91.9∼117.6%. There was not significant difference (p<0.01) between the HPLC and MBA methods and the equation of the regression curve was y=1.1428x-0.2269 (r=0.9842). This proposed HPLC method for determining pantothenic acid appears to be suitable for determining pantothenic acid concentrations above 0.25 mg/100 g in fortified foods.

• Journal of Periodontal and Implant Science
• /
• v.47 no.5
• /
• pp.312-327
• /
• 2017

Purpose: This study assessed marginal bone remodeling and soft tissue esthetics after the loading of single bone-level implants in the anterior maxilla. Methods: An open, single-arm observational clinical trial with 3 years of follow-up was performed, including 22 implants. The patients presented with a single tooth gap in the anterior maxilla (tooth positions 14-24), with natural or restored adjacent teeth. An implant was placed at least 8 weeks post-extraction and healed submerged for 6 weeks. After the second-stage operation, a fixed provisional prosthesis was provided. The final restoration was placed 6 months after the provisional restoration. The time of the provisional crown connection was considered to be the baseline in this study. Esthetic parameters and the marginal bone level were assessed at 6, 12, 24, and 36 months. Results: All implants were well integrated in the bone. A statistically significant increase was found in the mean implant stability quotient between the time of the provisional prosthesis and the time of the final prosthesis. Most implants (95.5%) revealed marginal bone resorption (<0.5 mm), and just 1 implant (4.5%) showed a change of 2.12 mm from baseline to 36 months (mean $0.07{\pm}0.48mm$), while the crestal bone level decreased significantly, from $2.34{\pm}0.93mm$ at baseline to $1.70{\pm}1.10mm$ at 36 months. The facial gingival margin and papilla were stable and the esthetic scores indicated high patient and dentist satisfaction. Conclusions: Platform-switching bone-level implants placed in maxillary single-tooth gaps resulted in successful osseointegration with minimal marginal bone resorption. The peri-implant soft tissue was also esthetically satisfying and stable.