• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2390-2406
• /
• 2022

Scene text recognition has important application value and attracted the interest of plenty of researchers. At present, many methods have achieved good results, but most of the existing approaches attempt to improve the performance of scene text recognition from the image level. They have a good effect on reading regular scene texts. However, there are still many obstacles to recognizing text on low-quality images such as curved, occlusion, and blur. This exacerbates the difficulty of feature extraction because the image quality is uneven. In addition, the results of model testing are highly dependent on training data, so there is still room for improvement in scene text recognition methods. In this work, we present a natural scene text recognizer to improve the recognition performance from the feature level, which contains feature representation and feature enhancement. In terms of feature representation, we propose an efficient feature extractor combined with Representative Batch Normalization and ResNet. It reduces the dependence of the model on training data and improves the feature representation ability of different instances. In terms of feature enhancement, we use a feature enhancement network to expand the receptive field of feature maps, so that feature maps contain rich feature information. Enhanced feature representation capability helps to improve the recognition performance of the model. We conducted experiments on 7 benchmarks, which shows that this method is highly competitive in recognizing both regular and irregular texts. The method achieved top1 recognition accuracy on four benchmarks of IC03, IC13, IC15, and SVTP.

• The Korea Journal of Herbology
• /
• v.29 no.1
• /
• pp.13-18
• /
• 2014

Objectives : Iridoid glycoside, swertiamarin is a well known bioactive component found in Swertia japonica Makino (SJ). In this study, we tried to optimize a suitable method which would extract swertiamarin effectively. Methods : Extraction of SJ was carried out by various conditions of time (5 - 60 min), temperature ($30-70^{\circ}C$), solvent (from non-polar to polar), and ratio of solvnet / sample (10 : 1 - 40 : 1) using ultrasonic extractor. Swertiamarin in SJ extracts was quantified by high performance liquid chromatography - Phtodiode array detector (HPLC-PDA) using C18 column and the analytical procedure was validated by evaluation of specificity, range, linearity, accuracy (recovery), precision (intra- and inter day variability), limit of detection (LOD), and limit of quantification (LOQ). Results : An efficient extraction condition for swertiamarin in SJ was optimized using sonicator extraction (temperature $40^{\circ}C$, solvent 20% methanol, solvent / sample (20 : 1), and time 10 min. Analytical procedure was optimized by HPLC-PDA using isocratic solvent system of acetonitrile and water (9 : 91), and the method was validated in regard to linearity (correlation coefficient, $R^2$ > 0.9999), range ($50-1000{\mu}g/mL$), intra- and inter-precision (RSD < 5.0 %), and recovery (99 -103 %). LOD and LOQ were 0.051 and $0.155{\mu}g/mL$, respectively. Conclusion : An optimized method of extraction for swertiamarin in SJ was established through conditions of diverse extraction and the validation result indicated that the method is suited for the determination of swertiamarin in SJ.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.483-490
• /
• 2022

Malaria is a disease caused by a parasite and it is prevalent in all over the world. The usual method used to recognize malaria cells is a thick and thin blood smears examination methods, but this method requires a lot of manual calculation, so the efficiency and accuracy are very low as well as the lack of pathologists in impoverished country has led to high malaria mortality rates. In this paper, a malaria cell image recognition model using transfer learning is proposed, which consists in the feature extractor, the residual structure and the fully connected layers. When the pre-training parameters of the VGG-19 model are imported to the proposed model, the parameters of some convolutional layers model are frozen and the fine-tuning method is used to fit the data for the model. Also we implement another malaria cell recognition model without residual structure to compare with the proposed model. The simulation results shows that the model using the residual structure gets better performance than the other model without residual structure and the proposed model has the best accuracy of 97.33% compared to other recent papers.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.4
• /
• pp.283-290
• /
• 2022

This study proposes a voltage control scheme in a synchronous reference frame to improve the dynamic characteristics of double-conversion UPSs. UPSs need to control positive and negative sequence voltage, so that positive and negative sequence extractors are generally used to obtain each sequence of the voltage and current. Voltage and current controllers for each sequence are implemented. However, the extractor causes considerable delay, and the delay restricts the control performance, especially for the current controller. To improve the dynamics of the current controller, the proposed scheme adopts a unified current controller without separating positive and negative sequences. By using discrete-time current controller, the control bandwidth can be extended significantly so that negative sequence current can be controlled. To enhance the performance, an additional feed-forward technique for output voltage regulation is proposed. The validity of the proposed controller is verified by experiments.

• Journal of Software Assessment and Valuation
• /
• v.16 no.1
• /
• pp.81-88
• /
• 2020

Various methods of differentiating and servicing digital content for individual users have been studied. Searching for association rules is a very useful way to discover individual preferences in digital content services. The Apriori algorithm is useful as an association rule extractor using frequent itemsets. However, the Apriori algorithm is not suitable for application to an actual content service because it considers only the reference count of each content. In this paper, we propose a new algorithm based on the Apriori that searches association rules by using purchase history and usage-time for each item. The proposed algorithm utilizes the usage time with the weight value according to purchase items. Thus, it is possible to extract the exact preference of the actual user. We implement the proposed algorithm and verify the performance through the actual data presented in the actual content service system.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.573-587
• /
• 2022

The agricultural sector is completely different from other sectors since it completely relies on various natural and climatic factors. Climate changes have many effects, including lack of annual rainfall and pests, heat waves, changes in sea level, and global ozone/atmospheric CO₂ fluctuation, on land and agriculture in similar ways. Climate change also affects the environment. Based on these factors, farmers chose their crops to increase productivity in their fields. Many existing agricultural ontologies are either domain-specific or have been created with minimal vocabulary and no proper evaluation framework has been implemented. A new agricultural ontology focused on subdomains is designed to assist farmers using Jaccard relative extractor (JRE) and Naïve Bayes algorithm. The JRE is used to find the similarity between two sentences and words in the agricultural documents and the relationship between two terms is identified via the Naïve Bayes algorithm. In the proposed method, the preprocessing of data is carried out through natural language processing techniques and the tags whose dimensions are reduced are subjected to rule-based formal concept analysis and mapping. The subdomain ontologies of weather, pest, and soil are built separately, and the overall agricultural ontology are built around them. The gold standard for the lexical layer is used to evaluate the proposed technique, and its performance is analyzed by comparing it with different state-of-the-art systems. Precision, recall, F-measure, Matthews correlation coefficient, receiver operating characteristic curve area, and precision-recall curve area are the performance metrics used to analyze the performance. The proposed methodology gives a precision score of 94.40% when compared with the decision tree(83.94%) and K-nearest neighbor algorithm(86.89%) for agricultural ontology construction.

• Journal of the Korean GEO-environmental Society
• /
• v.23 no.4
• /
• pp.11-20
• /
• 2022

In order to acquire hydraulic characteristics for unsaturated layers, water retention tests were performed and compared by using the evaporation method, volumetric pressure plate extractor (VPPE) and chilled-mirror dew point method. The evaporation and chilled-mirror method are currently developed experimental technology and measure the water retention curve of unsaturated soils quickly and accurately. In the evaporation and VPPE method, the water retention has been measured and compared until 100kPa matric suction and consequently the result of the evaporation method could be verified. In the chilled-mirror method, the water retention has been measured until high level of matric suction and the overall shape of water retention curves could be obtained. As a result of water retention tests, the representative water retention curves were obtained and the applicability of each test method was discussed. Using both the evaporation and chilled-mirror methods, the soil water retention curve can be acquired reasonably for the whole range of matric suction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1516-1529
• /
• 2023

In this paper, a motor gearbox fault-detection system based on a hierarchical flow-based model is proposed. The proposed system is used for the anomaly detection of a motion sound-based actuator module. The proposed flow-based model, which is a generative model, learns by directly modeling a data distribution function. As the objective function is the maximum likelihood value of the input data, the training is stable and simple to use for anomaly detection. The operation sound of a car's side-view mirror motor is converted into a Mel-spectrogram image, consisting of a folding signal and an unfolding signal, and used as training data in this experiment. The proposed system is composed of an encoder and a decoder. The data extracted from the layer of the pretrained feature extractor are used as the decoder input data in the encoder. This information is used in the decoder by performing an interlayer cross-scale convolution operation. The experimental results indicate that the context information of various dimensions extracted from the interlayer hierarchical data improves the defect detection accuracy. This paper is notable because it uses acoustic data and a normalizing flow model to detect outliers based on the features of experimental data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.942-943
• /
• 2021

The present work proposes a classification system for the HEp-2 cell images using an unsupervised deep feature learning method. Unlike most of the state-of-the-art methods in the literature that utilize deep learning in a strictly supervised way, we propose here the use of the deep convolutional autoencoder (DCAE) as the principal feature extractor for classifying the different types of the HEp-2 cell images. The network takes the original cell images as the inputs and learns to reconstruct them in order to capture the features related to the global shape of the cells. A final feature vector is constructed by using the latent representations extracted from the DCAE, giving a highly discriminative feature representation. The created features will be fed to a nonlinear classifier whose output will represent the final type of the cell image. We have tested the discriminability of the proposed features on one of the most popular HEp-2 cell classification datasets, the SNPHEp-2 dataset and the results show that the proposed features manage to capture the distinctive characteristics of the different cell types while performing at least as well as the actual deep learning based state-of-the-art methods.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.845-850
• /
• 2023

In this paper, we propose a method for diagnosing ball bearing vibration using transfer learning. STFT, which can analyze vibration signals in time-frequency, was used as input to CNN to diagnose failures. In order to rapidly learn CNN-based deep artificial neural networks and improve diagnostic performance, we proposed a transfer learning-based deep learning learning technique. For transfer learning, the feature extractor and classifier were selectively learned using a VGG-based image classification model, the data set for learning was publicly available ball bearing vibration data provided by Case Western Reserve University, and performance was evaluated by comparing the proposed method with the existing CNN model. Experimental results not only prove that transfer learning is useful for condition diagnosis in ball bearing vibration data, but also allow other industries to use transfer learning to improve condition diagnosis.