• The Journal of Korean Institute of Information Technology
• /
• v.17 no.8
• /
• pp.11-19
• /
• 2019

Against advanced image-related crimes, a high level of digital forensic methods is required. However, feature-based methods are difficult to respond to new device features by utilizing human-designed features, and deep learning-based methods should improve accuracy. This paper proposes a deep learning model to identify camera models based on DenseNet, the recent technology in the deep learning model field. To extract camera sensor features, a HPF feature extraction filter was applied. For camera model identification, we modified the number of hierarchical iterations and eliminated the Bottleneck layer and compression processing used to reduce computation. The proposed model was analyzed using the Dresden database and achieved an accuracy of 99.65% for 14 camera models. We achieved higher accuracy than previous studies and overcome their disadvantages with low accuracy for the same manufacturer.

• Applied Microscopy
• /
• v.11 no.1
• /
• pp.39-50
• /
• 1981

An electron microscopical observation was carried out to compare the general shape of the mast cells and structures of granules inside the cells in the stomach of 5 species in 3 orders of Mammals. In convenience, the granules in the cytoplasm were abbreviated as follows: 1) Homogeneous granule, GR1 2) Particulate granule, GR2 a. Dark dense particulate granule, GR2-1 b. Less dense particulate granule, GR2-2 3) Reticular granule, GR5 a. Dark dense reticular granule, GR5-1 b. Light dense reticular granule, GR5-2 In Mammalia including goat, dog, cat, and hamster, most of cytoplasmic organelle were Golgi apparatus and mitochondria, and most of the cytoplasmic granules were highly densed GR1and GR2. However GR5-1 and GR5-2 appeared in guinea pig while one side sunken or crescent-like types occured in both dog and guinea pig. All mast cells were oval or spindle with cytoplasmic processes around the cell. There was also found vacuoles and vesicles in these cells. These results demonstrated that there was a morphological difference between species of vertebrate in the mast cells and their cytoplasmic granules. It was also suggested that a variety of structures of granules were closely related with the composition (histamine, heparin, serotonin, hyaluronic acid etc.) and mature of the granules.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

• Communications of the Korean Mathematical Society
• /
• v.11 no.4
• /
• pp.1061-1066
• /
• 1996

We will give an example which is a normal Hausdorff countable dense homogeneous space but not a densely homogeneous space. Next, we will give a proof for the fact that every nondegenerate component of densely homogenous spaces is open and densely homogeneous.

• Bulletin of the Korean Mathematical Society
• /
• v.51 no.2
• /
• pp.539-545
• /
• 2014

We show that roots of log-concave Alexander knot polynomials are dense in C. This in particular implies that the log-concavity and Hoste's conjecture on the Alexander polynomial of alternating knots are (essentially) independent.

• Proceedings of the Korean Ceranic Society Conference
• /
• 2003.04a
• /
• pp.209.2-209
• /
• 2003

• The Pure and Applied Mathematics
• /
• v.6 no.1
• /
• pp.13-16
• /
• 1999

We introduce the notion of the $\omega$-derived set and $\omega$-dense, and investigate some of their properties.

• Applied Microscopy
• /
• v.25 no.2
• /
• pp.39-52
• /
• 1995

Pinealocytes in the lower vertebrate are known to have photoreceptive function. These photoreceptor cells have been characterized morphologically in various species of lower vertebrates. No such ultrastructural studies, however, were reported in fresh water turtle. The purpose of this study is to characterize the pinealocytes and the phylogenetic evoluton of these cells is discussed in terms of functional analogy. I. Light microscopy: The pineal body was divided into incomplete lobules by connective tissue septa containing blood vessels, and parenchymal cells were arranged as irregular cords or follicular pattern. In the lobules, glandular lumina were present and contained often densely stained materials. II. Electron microscopy: The pineal parenchyma had three categories of cells: photoreceptor cells, supportive cells and nerve cells. The photoreceptor cells had darker cytoplasm compared to the supportive cells, and the enlarged apical cytoplasm(inner segment) containing abundant mitochondria and dense cored vescles protruded into the glandular lumen in which lamellar membrane stacks(outer segment), dense membranous materials, and cilia were present. Some of these lamellated membrane stacks appeared to be dege-nerating while others were apparently newly formed. Constricted neck portion of the photoreceptor cells contained longitudinally arranged abundant microtubules. centrioles and cross-striated rootlets. Cell body had well developed Golgi apparatus, abundant mitochondria, dense granules($0.5{\sim}1{\mu}m$), dense cored vesicles($70{\sim}100nm$), and rough endoplasmic reticulum occasionally with dense material within its cisterna. Basal portion of the photoreceptor cells had basal processes often with synaptic ribbons, which terminate in the complicated zone of cellular and neuronal processes. Synatpic ribbons often made contact with the nerve processes and the cell processes of neighboring cells. In some instances, these ribbons were noted free within the basal process and were also present at the basal cell mem-brane facing the basal lamina. Obvious nerve endings with clear and dense cored vesicles were observed among the parenchymal cells. Photoreceptor cells of the snapping turtle pineal body were generally similar in fine structure to those of other lower verterbrates reported previously, and suggested to have both photoreceptive and secretory functions which were modulated by pinealofugal and pinealopedal nerves. The supportive cells were characterized by having large dense granules($0.3{\sim}1{\mu}m$), abundant ribosomes, well developed Golgi apparatus and rough endoplasmic reticulum. These cells were furnished with microvilli on the luminal cell surfaces, and often had centrioles, striated rootlets, abundant filaments especially around the nucleus, and scattered microtubules. Some supportive cells had cell body close to the lumen and extended a long process reaching to basal lamina, which appeared to be a glial cell. Nerve cells within the parenchyma were difficult to identify, but some large cells located basally were suspected to be nerve cells, since they had synaptic ribbon contact with photoreceptor cells.

• Applied Microscopy
• /
• v.30 no.3
• /
• pp.265-272
• /
• 2000

In this study, the brachial ganglion of Octopus minor was investigated with light microscope and electron microscope,andthefollowingresultswereobtained. The brachial ganglions of the octopus, round in shapes , are located under each of suckers. Their sizes are proportional to those of the suckers. A brachial ganglion of round shape consists of cortex and medulla. In cortex, nerve cells exist collectively while neuropiles in medulla. Three kinds of nerve cells (large, middle, and small neurons) are found in the cluster of nerve cells. The small one is a round cell of about $0.9{\mu}m$ in diameter while the middle and large ones are an elliptical cell of $1.6\times1.3{\mu}m$ and an ovoid cell of $2.8{\mu}m$ in diameter, respectively. All of those cells look light due to their low electron densities , in which cell organelle are not well developed. It was also observed that the middle neurons are surrounded by median electron-dense neuroglial cells of pyramidal shapes and about $0.6\times0.4{\mu}m$ in sizes. In the neuropiles of medulla, dendrites and axons of various sizes make a complex net. They contain four kinds of chemical synaptic vesicles-electron-dense synaptic vesicle of 100 nm in diameter, median electron-dense synaptic vesicle of 90 nm in diameter, electron-dense cored synaptic vesicle of 90 nm in diameter, and electron-lucent synaptic vesicle of 50 nm in diameter.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_1
• /
• pp.823-833
• /
• 2020

In order to stably produce crops, there is an increasing demand for effective crop monitoring techniques in domestic agricultural areas. In this manuscript, a cultivation area extraction method by using deep learning model is developed, and then, applied to satellite imagery. Training dataset for crop cultivation areas were generated using RapidEye satellite images that include blue, green, red, red-edge, and NIR bands useful for vegetation and environmental analysis, and using this, we tried to estimate the crop cultivation area of onion and garlic by deep learning model. In order to training the model, atmospheric-corrected RapidEye satellite images were used, and then, a deep learning model using FC-DenseNet, which is one of the representative deep learning models for semantic segmentation, was created. The final crop cultivation area was determined as object-based data through combination with cadastral maps. As a result of the experiment, it was confirmed that the FC-DenseNet model learned using atmospheric-corrected training data can effectively detect crop cultivation areas.