• International Journal of Computer Science & Network Security
• /
• 제22권7호
• /
• pp.220-228
• /
• 2022

Image always carry useful information, detecting a text from scene images is imperative. The proposed work's purpose is to recognize scene text image, example boarding image kept on highways. Scene text detection on highways boarding's plays a vital role in road safety measures. At initial stage applying preprocessing techniques to the image is to sharpen and improve the features exist in the image. Likely, morphological operator were applied on images to remove the close gaps exists between objects. Here we proposed a two phase algorithm for extracting and recognizing text from scene images. In phase I text from scenery image is extracted by applying various image preprocessing techniques like blurring, erosion, tophat followed by applying thresholding, morphological gradient and by fixing kernel sizes, then canny edge detector is applied to detect the text contained in the scene images. In phase II text from scenery image recognized using MSER (Maximally Stable Extremal Region) and OCR; Proposed work aimed to detect the text contained in the scenery images from popular dataset repositories SVT, ICDAR 2003, MSRA-TD 500; these images were captured at various illumination and angles. Proposed algorithm produces higher accuracy in minimal execution time compared with state-of-the-art methodologies.

• Journal of Plant Biotechnology
• /
• 제47권4호
• /
• pp.273-282
• /
• 2020

In Vietnam, Celastrus hindsii Benth, a medicinal plant rich in secondary metabolites, has been used to alleviate distress caused by ulcers, tumors, and inflammation for generations. The occurrence of two phenotypes, Broad Leaf (BL) and Narrow Leaf (NL), has raised questions about the selection of appropriate varieties for conservation and crop improvement to enhance medicinal properties. This study examined molecular differences in C. hindsii by comparing protein profiles between the NL and BL types using 2D-PAGE and MS. Peptide sequences and proteins were identified by matching MS data against the MSPnr100 databases and verified using the MultiIdent tool on ExPASy and the Blast2GO software. Our results revealed notable variations in protein abundance between the NL and BL proteomes. Selected proteins were confidently identified from 12 protein spots, thereby highlighting the molecular variation between NL and BL proteomes. Upregulated proteins in BL were found to be associated with flavonoid and amino acid biosynthesis as well as nuclease metabolism, which probably attributed to the intraspecific variations. Several bioactive proteins identified in this study can have applications in cancer therapeutics. Therefore, the BL phenotype characterized by healthier external morphological features has higher levels of bioactive compounds and could be better suited for medicinal use.

• Mycobiology
• /
• 제50권1호
• /
• pp.12-19
• /
• 2022

Paramyrothecium eichhorniae sp. nov. was observed and collected from Chiang Mai and Phetchaburi Provinces, Thailand. This new species is introduced based on morphological and molecular evidence. This fungus is characterized by its production of sporodochium conidiomata with a white setose fringe surrounding an olivaceous green to dark green slimy mass of conidia, penicillately branched conidiophores, and aseptate and cylindrical to ellipsoid conidia. Phylogenetic analyses of combined LSU rDNA, ITS rDNA, tef1, rpb2, tub2 and cmdA sequence data using maximum parsimony, maximum likelihood and Bayesian approaches placed the fungus in a strongly supported clade with other Paramyrothecium species in Stachybotryaceae (Hypocreales, Sordariomycetes). The descriptions of the species are accompanied by illustrations of morphological features, and a discussion of the related taxa is presented.

• 한국해양바이오학회지
• /
• 제14권1호
• /
• pp.51-60
• /
• 2022

A green alga specimen was collected from the eastern coast of Korea. This species shared the typical features of genus Ulva and was characterized by irregularly shaped thalli, relatively small and thick thallus, entire undulate margins without serrations, and one or two pyrenoids per cell. In a phylogenetic tree, based on sequences of the nuclear-encoded internal transcribed spacer region, it nests as a sister clade to a few species including Ulva ohnoi, which has a relatively large thallus. This Korean algal specimen differs from the species forming the same subclades, including U. ohnoi, Ulva fasciata, Ulva reticulata, and Ulva gigantean, and has a relatively small (3-8 cm) and thick (60-100 ㎛) thallus. Of these species, U. ohnoi, originally described from Japan, is similar to the Korean alga as it had a thick thallus of 30-90 ㎛, but it has microscopic serrations on the thallus margin, unlike the Korean alga. The genetic distance between the Korean alga species and the aforementioned species was determined to be 1.8%-4.8%, indicating an inter-specific divergence level at the genus Ulva. Herein, Ulva grossa sp. nov. (Ulvales, Chlorophyta) from Korea is described based on the morphological and molecular analyses.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.120-128
• /
• 2023

In this work, we have presented ATSA, a hierarchical attention deep learning model for Arabic sentiment analysis. ATSA was proposed by addressing several challenges and limitations that arise when applying the classical models to perform opinion mining in Arabic. Arabic-specific challenges including the morphological complexity and language sparsity were addressed by modeling semantic composition at the Arabic morphological analysis after performing tokenization. ATSA proposed to perform phrase-chunks sentiment embedding to provide a broader set of features that cover syntactic, semantic, and sentiment information. We used phrase structure parser to generate syntactic parse trees that are used as a reference for ATSA. This allowed modeling semantic and sentiment composition following the natural order in which words and phrase-chunks are combined in a sentence. The proposed model was evaluated on three Arabic corpora that correspond to different genres (newswire, online comments, and tweets) and different writing styles (MSA and dialectal Arabic). Experiments showed that each of the proposed contributions in ATSA was able to achieve significant improvement. The combination of all contributions, which makes up for the complete ATSA model, was able to improve the classification accuracy by 3% and 2% on Tweets and Hotel reviews datasets, respectively, compared to the existing models.

• ALGAE
• /
• 제37권4호
• /
• pp.281-291
• /
• 2022

Quantifying the abundance of Chattonella species is necessary to effectively manage the threats from ichthyotoxic raphidophytes, which can cause large-scale mortality of aquacultured fish in temperate waters. The identification and cell counting of Chattonella species have been conducted primarily on living cells without fixation by light microscopy because routine fixatives do not retain their morphological features. Species belonging to the Chattonella marina complex, including C. marina and C. marina var. ovata, had high genetic similarities and the lack of clear morphological delimitations between the species. To estimate the abundance of C. marina complex in marine plankton samples, we developed a protocol based on the droplet digital polymerase chain reaction (ddPCR) assay, with C. marina complex-specific primers targeting the internal transcribed spacer (ITS) region of the rDNA. Cell abundance of the C. marina complex can be determined using the ITS copy number per cell, ranging from 25 ± 1 for C. marina to 112 ± 7 for C. marina var. ovata. There were no significant differences in ITS copies estimated by the ddPCR assay between environmental DNA samples from various localities spiked with the same number of cells of culture strains. This approach can be employed to improve the monitoring efficiency of various marine protists and to support the implementation of management for harmful algal blooms, which are difficult to analyze using microscopy alone.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제61차 동계학술대회논문집 28권1호
• /
• pp.11-14
• /
• 2020

The importance of data in the development of deep learning is very high. Data with high morphological features are usually utilized in the domains where careful lens calibrations are needed by a human to capture those data. Synthesis of high morphological data for that domain can be a great asset to improve the classification accuracy of systems in the field. Unsupervised learning can be employed for this task. Generating photo-realistic objects of interest has been massively studied after Generative Adversarial Network (GAN) was introduced. In this paper, we propose Morpho-GAN, a method that unifies several GAN techniques to generate quality data of high morphology. Our method introduces a new suitable training objective in the discriminator of GAN to synthesize images that follow the distribution of the original dataset. The results demonstrate that the proposed method can generate plausible data as good as other modern baseline models while taking a less complex during training.

• 한국동물생명공학회지
• /
• 제38권2호
• /
• pp.54-61
• /
• 2023

Background: Germ cells undergo towards male or female pathways to produce spermatozoa or oocyte respectively which is essential for sexual reproduction. Mesenchymal stem cells (MSCs) have the potential of trans-differentiation to the multiple cell lineages. Methods: Herein, rat MSCs were isolated from bone marrow and characterized by their morphological features, expression of MSC surface markers, and in vitro differentiation capability. Results: Thereafter, we induced these cells only by retinoic acid supplementation in MSC medium and, could able to show that bone marrow derived MSCs are capable to trans-differentiate into male germ cell-like cells in vitro. We characterized these cells by morphological changes, the expressions of germ cell specific markers by immunophenotyping and molecular biology tools. Further, we quantified these differentiated cells. Conclusions: This study suggests that only Retinoic acid in culture medium could induce bone marrow MSCs to differentiate germ cell-like cells in vitro. This basic method of germ cell generation might be helpful in the prospective applications of this technology.

• 환경생물
• /
• 제30권1호
• /
• pp.54-63
• /
• 2012

This study characterizes three $Anabaena$ strains and 5 $Trichormus$ strains isolated from Korean waters and 3 $Anabaena$ $flos-aquae$ strains procured from the UTEX based on morphological features and molecular analyses. The $Anabaena$ and $Trichormus$ isolates were morphologically assigned to $A.$ $variabilis$ K$\ddot{u}$tzing and $T.$ $variabilis$(K$\ddot{u}$tzing ex Bornet et Flahault) Kom$\acute{a}$rek et Anagnostidis, respectively. The $Anabaena$ and $Trichormus$ strains differed significantly in the mean length of their vegetative cells. The 16S rRNA genes from the $Anabaena$ strains showed a 100% identity to that from $A.$ $variabilis$ ATCC 29413, while the 16S rRNA genes from the $Trichormus$ strains showed a 99.9% identity to that from $T.$ $variabilis$ GREIFSWALD. The overall topology was in agreement for the 16S rRNA gene and $cpcBA$-IGS trees in the both tree-constructing methods. In a neighbor-joining tree based on the 16S rRNA gene, the 3 $Anabaena$ strains were asso-ciated with $A.$ $variabilis$, the 5 $Trichormus$ strains with $T.$ $variabilis$, and the 3 $Anabaena$ (UTEX) strains were with $Nostoc$. To date, this is the first report on $A.$ $variabilis$ and $T.$ $variabilis$ strains originating from Korea.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권12호
• /
• pp.946-950
• /
• 2010

기계 학습 기반의 많은 감정 분류 시스템들은 문장으로부터 언어적 자질을 추출하기 위하여 형태소 분석기를 사용한다. 그러나 온라인 상품평에는 많은 띄어쓰기 오류 및 철자 오류가 포함되어 있어서 일반적으로 형태소 분석기가 좋은 성능을 내기 어려우며, 기반 시스템의 낮은 성능은 감정 분류 시스템의 성능하락을 초래한다. 이러한 문제를 해결하기 위하여 본 논문에서는 어절 패턴과 음운 패턴의 최장 일치 매칭(matching)에 기반한 자질 추출 방법을 제안한다. 두 종류의 패턴은 대용량의 품사 부착 말뭉치로부터 자동으로 구축된다. 어절 패턴은 영사, 동사와 같은 내용어를 포함하는 어절들로 구성되며, 음운 패턴은 동사나 형용사와 같은 용언의 초성과 중성의 쌍으로 구성된다. 음운 패턴에 초성과 중성만을 사용한 이유는 철자 오류에 영향을 덜 받기 때문이다. 제안 방법을 평가하기 위하여 SVM(Support Vector Machine)을 기계 학습기로 사용하는 감정 분류 시스템을 구현하였다. 한국어 상품평에 대한 실험에서 제안 방법을 자질 추출 모듈로 사용하는 감정 분류 시스템이 형태소 분석기를 사용하는 것보다 우수한 성능을 보였다.