• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.522-524
• /
• 2019

In spite of a rapid development in the quality of built-in mobile cameras, their some physical restrictions hinder them to achieve the satisfactory results of digital single lens reflex (DSLR) cameras. In this work we propose an end-to-end deep learning method to translate ordinary images by mobile cameras into DSLR-quality photos. The method is based on the framework of generative adversarial networks (GANs) with several improvements. First, we combined the U-Net with DenseNet and connected dense block (DB) in terms of U-Net. The Dense U-Net acts as the generator in our GAN model. Then, we improved the perceptual loss by using the VGG features and pixel-wise content, which could provide stronger supervision for contrast enhancement and texture recovery.

• Animal Systematics, Evolution and Diversity
• /
• v.34 no.4
• /
• pp.215-219
• /
• 2018

Protochitonidae Ashby, 1925 is a family of small to medium sized chitons that includes a single fossil genus and two extant genera. Of the two extant genera, Deshayesiella Carpenter in Dall, 1879 contains 5 described species. Although most Deshayesiella species are known to be found in deep sea habitats(over 100 m), D. curvata (Carpenter in Pilsbry, 1892) is found from shallow waters(1-20 m). In this study, we provide details of microstructure of shell and radula characters using scanning electron microscopy and morphological features of D. curvata, and its partial sequence of mitochondrial DNA cox1 gene as DNA barcode sequence. In addition, we compare morphological differences of D. curvata from other congeneric species.

• CELLMED
• /
• v.9 no.4
• /
• pp.7.1-7.4
• /
• 2019

A cuttlefish bone is not a bone, but the internal shell of the Cuttlefish/ sepia officinalis, a small, squid-like cephalopod of phylum molusca, an animals of the order Sepiida. Cuttlefish bone comprises up to 90 percent of its content of calcium carbonate with the abundance of different bioinorganic elements such as magnesium, strontium, iron, even trace amounts of copper, zinc, aragonite and ${\beta}$-chitin which makes it extremely valuable and worthwhile to be used for biomedical research. Unani system of medicine has been using cuttlefish bone under the name of 'kafe dariya' for the treatment various disorders and ailments since centuries. Unani scholars were well aware of the valuable medical and cosmetologically aspect of cuttlefish bone. However, the drug has been forgotten for its beneficial effect and went deep away from the scientific researches. The purpose of the present review is to highlight and revive the data on cuttlefish and cuttlefish bone for its morphology, composition, types, pharmacological actions, temperament, therapeutic dosage, contraindications, correctives, alternatives and therapeutic uses with special reference of Unani medicine to attain its the beneficial features in biomedical sciences.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1582-1590
• /
• 2022

Due to the situation of the widespread of the coronavirus, which causes the problem of lack of face image data occluded by masks at recent time, in order to solve the related problems, this paper proposes a method to generate face images with masks using a combination of generative adversarial networks and spatial transformation networks based on CNN model. The system we proposed in this paper is based on the GAN, combined with multi-scale convolution kernels to extract features at different details of the human face images, and used Wasserstein divergence as the measure of the distance between real samples and synthetic samples in order to optimize Generator performance. Experiments show that the proposed method can effectively put masks on face images with high efficiency and fast reaction time and the synthesized human face images are pretty natural and real.

• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.148-154
• /
• 2021

With the advent of context-aware computing, many attempts were made to understand emotions. Among these various attempts, Speech Emotion Recognition (SER) is a method of recognizing the speaker's emotions through speech information. The SER is successful in selecting distinctive 'features' and 'classifying' them in an appropriate way. In this paper, the performances of SER using neural network models (e.g., fully connected network (FCN), convolutional neural network (CNN)) with Mel-Frequency Cepstral Coefficients (MFCC) are examined in terms of the accuracy and distribution of emotion recognition. For Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset, by tuning model parameters, a two-dimensional Convolutional Neural Network (2D-CNN) model with MFCC showed the best performance with an average accuracy of 88.54% for 5 emotions, anger, happiness, calm, fear, and sadness, of men and women. In addition, by examining the distribution of emotion recognition accuracies for neural network models, the 2D-CNN with MFCC can expect an overall accuracy of 75% or more.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.12
• /
• pp.1665-1670
• /
• 2018

A convolutional neural network (CNN), which is one of the deep learning models, has been very successful in a variety of computer vision tasks. Filters of a CNN are automatically generated, however, they can be further optimized since there exist the possibility of existing redundant and less important features. Therefore, the aim of this paper is a filter reduction to accelerate and compress CNN models. Evolutionary algorithms is adopted to remove the unnecessary filters in order to minimize the parameters of CNN networks while maintaining a good performance of classification. We demonstrate the proposed filter reduction methods performing experiments on CIFAR10 data based on the classification performance. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1171-1178
• /
• 2019

This study proposes a deep neural network model based on an encoder-decoder structure for visual dialogs. Ongoing linguistic understanding of the dialog history and context is important to generate correct answers to questions in visual dialogs followed by questions and answers regarding images. Nevertheless, in many cases, a visual understanding that can identify scenes or object attributes contained in images is beneficial. Hence, in the proposed model, by employing a separate person detector and an attribute recognizer in addition to visual features extracted from the entire input image at the encoding stage using a convolutional neural network, we emphasize attributes, such as gender, age, and dress concept of the people in the corresponding image and use them to generate answers. The results of the experiments conducted using VisDial v0.9, a large benchmark dataset, confirmed that the proposed model performed well.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.717-723
• /
• 2019

Smart systems and services aim to facilitate growing urban populations and their prospects of virtual-real social behaviors, gig economies, factory automation, knowledge-based workforce, integrated societies, modern living, among many more. To satisfy these objectives, smart systems and services must comprises of a complex set of features such as security, ease of use and user friendliness, manageability, scalability, adaptivity, intelligent behavior, and personalization. Recently, artificial intelligence (AI) is realized as a data-driven technology to provide an efficient knowledge representation, semantic modeling, and can support a cognitive behavior aspect of the system. In this paper, an integration of AI with the smart systems and services is presented to mitigate the existing challenges. Several novel researches work in terms of frameworks, architectures, paradigms, and algorithms are discussed to provide possible solutions against the existing challenges in the AI-based smart systems and services. Such novel research works involve efficient shape image retrieval, speech signal processing, dynamic thermal rating, advanced persistent threat tactics, user authentication, and so on.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.67.4-67.4
• /
• 2019

We present preliminary results of our long-term (2009-2017) observing campaign using the NASA IRTF at Mauna Kea, to obtain $2-5{\mu}m$ spectroscopy of ~200 red point sources in the line of sight to the Galactic center. Point sources in our sample were selected from the mid-infrared images of the Spitzer Space telescope, and include candidate massive young stellar objects, which have previously been identified from our Spitzer/IRS spectroscopy. We show high foreground extinction of these sources from deep $3.1{\mu}m$ H2O ice and aliphatic hydrocarbon absorption features, suggesting that they are likely located in the central 300 pc region of the Galactic center. While many sources reveal photospheric $2.3{\mu}m$ gas CO absorption, few of them clearly indicate $3.54{\mu}m$ CH3OH ice absorption, possibly indicating a large dust column density intrinsic to a massive young stellar object.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.