• Title/Summary/Keyword: text extraction

Search Result 459, Processing Time 0.026 seconds

Applying Natural Language Processing Techniques to Bioinformatics

  • Park, Hyun-Seok
    • Proceedings of the Korean Society for Bioinformatics Conference
    • /
    • 2000.11a
    • /
    • pp.71-73
    • /
    • 2000
  • Considering that there is the lack of standards for storing genome-related on-line documents, the techniques in Natural Language Processing (NLP) is likely to become more and more important. It is necessary to extract useful information from the raw text and to store it in a computer-readable database format. Recent advances in NLP technologies raise new challenges and opportunities for tackling genome-related on-line text for information extraction task, For example, we can obtain many useful information related to genetic network or metabolic pathways simply by analyzing verbs such as 'activate'or 'inhibit'in Medline abstracts in a fully automatic way, Thus, combining NLP techniques with genome informatics extends beyond the traditional realms of either technology to a variety of emerging applications.

  • PDF

A Text Extraction in Complex Images using Texture Clustering Method (텍스쳐 클러스터링 기법을 이용한 복잡한 영상에서의 문자영역 추출)

  • Koo, Kyung-Mo;Lee, Sang-Lyn;Park, Hyun-Jun;Cha, Eui-Young
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2007.10a
    • /
    • pp.431-433
    • /
    • 2007
  • In This paper, we present a texture clustering method to extract Container ISO code in complex images. First, we make texture informations using top-hat morphology from realtime images, and we cluster those informations using horizontal and vertical clustering method to extract text area. After extensive experiment, our method demonstrated superior performance against well-known techniques as texture and histogram method.

  • PDF

Mining Parallel Text from the Web based on Sentence Alignment

  • Li, Bo;Liu, Juan;Zhu, Huili
    • Proceedings of the Korean Society for Language and Information Conference
    • /
    • 2007.11a
    • /
    • pp.285-292
    • /
    • 2007
  • The parallel corpus is an important resource in the research field of data-driven natural language processing, but there are only a few parallel corpora publicly available nowadays, mostly due to the high labor force needed to construct this kind of resource. A novel strategy is brought out to automatically fetch parallel text from the web in this paper, which may help to solve the problem of the lack of parallel corpora with high quality. The system we develop first downloads the web pages from certain hosts. Then candidate parallel page pairs are prepared from the page set based on the outer features of the web pages. The candidate page pairs are evaluated in the last step in which the sentences in the candidate web page pairs are extracted and aligned first, and then the similarity of the two web pages is evaluate based on the similarities of the aligned sentences. The experiments towards a multilingual web site show the satisfactory performance of the system.

  • PDF

Dysarthric speaker identification with different degrees of dysarthria severity using deep belief networks

  • Farhadipour, Aref;Veisi, Hadi;Asgari, Mohammad;Keyvanrad, Mohammad Ali
    • ETRI Journal
    • /
    • v.40 no.5
    • /
    • pp.643-652
    • /
    • 2018
  • Dysarthria is a degenerative disorder of the central nervous system that affects the control of articulation and pitch; therefore, it affects the uniqueness of sound produced by the speaker. Hence, dysarthric speaker recognition is a challenging task. In this paper, a feature-extraction method based on deep belief networks is presented for the task of identifying a speaker suffering from dysarthria. The effectiveness of the proposed method is demonstrated and compared with well-known Mel-frequency cepstral coefficient features. For classification purposes, the use of a multi-layer perceptron neural network is proposed with two structures. Our evaluations using the universal access speech database produced promising results and outperformed other baseline methods. In addition, speaker identification under both text-dependent and text-independent conditions are explored. The highest accuracy achieved using the proposed system is 97.3%.

A text region extraction algorithm based on Android for real-time text recognition (실시간 글자 인식을 위한 안드로이드 기반의 글자 영역 추출 기술)

  • Lee, Gyu-Cheol;Lee, Sangyong;Yoo, Jisang
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2016.11a
    • /
    • pp.194-196
    • /
    • 2016
  • 본 논문에서는 안드로이드 환경에서 글자 인식을 위한 전처리 과정으로 입력 영상에서 글자 영역만을 추출하는 기법을 제안한다. 대부분의 글자 인식 어플리케이션에서 글자를 인식하는 방법은 RoI(Region of Interest)에 인식하려는 글자를 위치시켜 놓고 사용자가 촬영함으로써 진행된다. 하지만 촬영된 영상 그대로를 인식에 사용하기 때문에 잡음 및 글자가 아닌 영역들을 글자로 인식하는 문제 등으로 인하여 인식률이 현저히 떨어진다. 제안하는 기법에서는 MSER(Maximally Stable Extremal Regions) 기법을 통해 각각의 글자를 추출한 후, 글자의 특성을 이용하여 글자 영역만을 추출한다. 기법의 성능 평가는 무료 OCR(Optical Character Recognition) 엔진인 Tesseract-OCR을 통해 글자 인식률을 비교하였으며, 제안하는 기법을 적용한 글자 인식 시스템이 적용하지 않은 시스템보다 글자의 인식률이 향상되는 것을 확인하였다.

  • PDF

Improving Transformer with Dynamic Convolution and Shortcut for Video-Text Retrieval

  • Liu, Zhi;Cai, Jincen;Zhang, Mengmeng
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.16 no.7
    • /
    • pp.2407-2424
    • /
    • 2022
  • Recently, Transformer has made great progress in video retrieval tasks due to its high representation capability. For the structure of a Transformer, the cascaded self-attention modules are capable of capturing long-distance feature dependencies. However, the local feature details are likely to have deteriorated. In addition, increasing the depth of the structure is likely to produce learning bias in the learned features. In this paper, an improved Transformer structure named TransDCS (Transformer with Dynamic Convolution and Shortcut) is proposed. A Multi-head Conv-Self-Attention module is introduced to model the local dependencies and improve the efficiency of local features extraction. Meanwhile, the augmented shortcuts module based on a dual identity matrix is applied to enhance the conduction of input features, and mitigate the learning bias. The proposed model is tested on MSRVTT, LSMDC and Activity-Net benchmarks, and it surpasses all previous solutions for the video-text retrieval task. For example, on the LSMDC benchmark, a gain of about 2.3% MdR and 6.1% MnR is obtained over recently proposed multimodal-based methods.

An Ensemble Classifier Based Method to Select Optimal Image Features for License Plate Recognition (차량 번호판 인식을 위한 앙상블 학습기 기반의 최적 특징 선택 방법)

  • Jo, Jae-Ho;Kang, Dong-Joong
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.65 no.1
    • /
    • pp.142-149
    • /
    • 2016
  • This paper proposes a method to detect LP(License Plate) of vehicles in indoor and outdoor parking lots. In restricted environment, there are many conventional methods for detecting LP. But, it is difficult to detect LP in natural and complex scenes with background clutters because several patterns similar with text or LP always exist in complicated backgrounds. To verify the performance of LP text detection in natural images, we apply MB-LGP feature by combining with ensemble machine learning algorithm in purpose of selecting optimal features of small number in huge pool. The feature selection is performed by adaptive boosting algorithm that shows great performance in minimum false positive detection ratio and in computing time when combined with cascade approach. MSER is used to provide initial text regions of vehicle LP. Throughout the experiment using real images, the proposed method functions robustly extracting LP in natural scene as well as the controlled environment.

A Method of Predicting Service Time Based on Voice of Customer Data (고객의 소리(VOC) 데이터를 활용한 서비스 처리 시간 예측방법)

  • Kim, Jeonghun;Kwon, Ohbyung
    • Journal of Information Technology Services
    • /
    • v.15 no.1
    • /
    • pp.197-210
    • /
    • 2016
  • With the advent of text analytics, VOC (Voice of Customer) data become an important resource which provides the managers and marketing practitioners with consumer's veiled opinion and requirements. In other words, making relevant use of VOC data potentially improves the customer responsiveness and satisfaction, each of which eventually improves business performance. However, unstructured data set such as customers' complaints in VOC data have seldom used in marketing practices such as predicting service time as an index of service quality. Because the VOC data which contains unstructured data is too complicated form. Also that needs convert unstructured data from structure data which difficult process. Hence, this study aims to propose a prediction model to improve the estimation accuracy of the level of customer satisfaction by combining unstructured from textmining with structured data features in VOC. Also the relationship between the unstructured, structured data and service processing time through the regression analysis. Text mining techniques, sentiment analysis, keyword extraction, classification algorithms, decision tree and multiple regression are considered and compared. For the experiment, we used actual VOC data in a company.

Improving methods for normalizing biomedical text entities with concepts from an ontology with (almost) no training data at BLAH5 the CONTES

  • Ferre, Arnaud;Ba, Mouhamadou;Bossy, Robert
    • Genomics & Informatics
    • /
    • v.17 no.2
    • /
    • pp.20.1-20.5
    • /
    • 2019
  • Entity normalization, or entity linking in the general domain, is an information extraction task that aims to annotate/bind multiple words/expressions in raw text with semantic references, such as concepts of an ontology. An ontology consists minimally of a formally organized vocabulary or hierarchy of terms, which captures knowledge of a domain. Presently, machine-learning methods, often coupled with distributional representations, achieve good performance. However, these require large training datasets, which are not always available, especially for tasks in specialized domains. CONTES (CONcept-TErm System) is a supervised method that addresses entity normalization with ontology concepts using small training datasets. CONTES has some limitations, such as it does not scale well with very large ontologies, it tends to overgeneralize predictions, and it lacks valid representations for the out-of-vocabulary words. Here, we propose to assess different methods to reduce the dimensionality in the representation of the ontology. We also propose to calibrate parameters in order to make the predictions more accurate, and to address the problem of out-of-vocabulary words, with a specific method.

Estimating Media Environments of Fashion Contents through Semantic Network Analysis from Social Network Service of Global SPA Brands (패션콘텐츠 미디어 환경 예측을 위한 해외 SPA 브랜드의 SNS 언어 네트워크 분석)

  • Jun, Yuhsun
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.43 no.3
    • /
    • pp.427-439
    • /
    • 2019
  • This study investigated the semantic network based on the focus of the fashion image and SNS text utilized by global SPA brands on the last seven years in terms of the quantity and quality of data generated by the fast-changing fashion trends and fashion content-based media environment. The research method relocated frequency, density and repetitive key words as well as visualized algorithms using the UCINET 6.347 program and the overall classification of the text related to fashion images on social networks used by global SPA brands. The conclusions of the study are as follows. A common aspect of global SPA brands is that by looking at the basis of text extraction on SNS, exposure through image of products is considered important for sales. The following is a discriminatory aspect of global SPA brands. First, ZARA consistently exposes marketing using a variety of professions and nationalities to SNS. Second, UNIQLO's correlation exposes its collaboration promotion to SNS while steadily exposing basic items. Third, in the case of H&M, some discriminatory results were found with other brands in connectivity with each cluster category that showed remarkably independent results.