24,223 Hits in 5.7 sec

Extracting relevant named entities for automated expense reimbursement

Guangyu Zhu, Timothy J. Bethea, Vikas Krishna
2007 Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '07  
We present an approach for extracting relevant named entities from document images by combining rich page layout features in the image space with language content in the OCR text using a discriminative  ...  Extracting relevant named entities robustly from document images with unconstrained layouts and diverse formatting is a fundamental technical challenge to image-based data mining, question answering, and  ...  Two page segmentation strategies can be employed to divide a general document image into homogeneous regions. One is to use a page segmentation algorithm.  ... 
doi:10.1145/1281192.1281300 dblp:conf/kdd/ZhuBK07 fatcat:ptj6bmjwsndz7a7u4kc77r7mn4

Towards Facial Biometrics for ID Document Validation in Mobile Devices

Iurii Medvedev, Farhad Shadmand, Leandro Cruz, Nuno Gonçalves
2021 Applied Sciences  
The original facial biometric template, which is extracted from the trusted frontal face image, is stored on the identification document in a secured personalized machine-readable code.  ...  As an additional contribution, we introduce several print-capture datasets that may be used for training and evaluating similar systems for mobile identification and travel documents validation.  ...  In our work, we adopt a similar approach for protecting ID and travel documents.  ... 
doi:10.3390/app11136134 doaj:c592e4f291df42f4b606796f420b211b fatcat:cbkvgya4hfa5xdh4lxf3lyirp4

Towards Discourse Parsing-inspired Semantic Storytelling [article]

Georg Rehm and Karolina Zaczynska and Julián Moreno-Schneider and Malte Ostendorff and Peter Bourgonje and Maria Berger and Jens Rauenbusch and André Schmidt and Mikka Wild
2020 arXiv   pre-print
, which is based on a semi-automatically collected data set with documents about noteworthy people in one of Berlin's districts.  ...  We envision our approach to be combined with additional features (NER, coreference resolution, knowledge graphs  ...  Step 1: Determine the Relevance of a Segment for a Topic The approach starts with a topic T , instantiated through a text segment such as a complete document, a headline or a named entity.  ... 
arXiv:2004.12190v1 fatcat:xt374rlo7fazfnwqqlkacwpffq

A Detailed Analysis of Optical Character Recognition Technology

Karez Hamad, Mehmet Kaya
2016 International Journal of Applied Mathematics Electronics and Computers  
In many different fields, there is a high demand for storing information to a computer storage disk from the data available in printed or handwritten documents or images to later re-utilize this information  ...  One simple way to store information to a computer system from these printed documents could be first to scan the documents and then store them as image files.  ...  The top-down approach in a document segments large regions into smaller sub regions recursively.  ... 
doi:10.18100/ijamec.270374 fatcat:s2urjyqllfdevnjox6oevlwf24

Recognition of Nastaliq Urdu Text using Multi-SVM

2020 International journal of recent technology and engineering  
In this paper ligature Recognition is performed by using multi-SVM (Sup-port Vector Machine) approach which gives an accuracy of 97% when 903 text images are fed to it.  ...  Due to the peculiarities of Nastaliq Style of writing, we have chosen ligature as a basic unit of recognition in order to reduce the complexity of system.  ...  There are various segmentation approaches for ligatures, which can be classified into top-down, bottom-up and hybrid.  ... 
doi:10.35940/ijrte.e6949.018520 fatcat:vhr5xfnjbrct5mgypcb4exa2cq

Literature survey [chapter]

Cong Lu, Jerry Ying Hsi Fuh, Yoke San Wong
2011 Collaborative Product Assembly Design and Assembly Planning  
Multi-layer perceptron neural network was used for classification. Rhee and Cho [148] used Model guided segmentation approach for segment to segment comparison to obtain consistent segmentation.  ...  For example [110] , among the biometrics of face, finger, hand, voice, eye, DNA and signature, the face biometric ranks first in the compatibility evaluation of a machine readable travel document (MRTD  ... 
doi:10.1533/9780857093882.9 fatcat:xw6alngzynh3tdy6axlo2i2pva

Cost-Effectiveness of Seven Approaches to Map Vegetation Communities — A Case Study from Northern Australia's Tropical Savannas

Donna Lewis, Stuart Phinn, Lara Arroyo
2013 Remote Sensing  
Other semi-automated methods include pixel-and object-based image analysis. While these methods have been used for decades, there is a lack of comparative research.  ...  We evaluated the cost-effectiveness of seven approaches to map vegetation communities in a northern Australia's tropical savanna environment.  ...  Acknowledgments This study is a component of a PhD undertaken through the University of Queensland.  ... 
doi:10.3390/rs5010377 fatcat:plxismz3ifadxccbjcf5uf3nyq

Topic model allocation of conversational dialogue records by Latent Dirichlet Allocation

Jui-Feng Yeh, Chen-Hsien Lee, Yi-Shiuan Tan, Liang-Chih Yu
2014 Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific  
According to the experimental results, we can find the proposed method outperforms the approach based on support vector machine in topic detection and tracking in spoken dialogue.  ...  For evaluating the proposed method, support vector machine is developed for comparison.  ...  Document classification is a search in data mining, the purpose is, how to classify and analyse the huge and complicated document data, such news document class, science paper class, image analysis.  ... 
doi:10.1109/apsipa.2014.7041546 dblp:conf/apsipa/YehLTY14 fatcat:4xwmvymqbrc5fa6ii4iavhupw4

An Insight of Script Text Extraction Performance using Machine Learning Techniques

Firstly, the study presents a survey for various kinds of techniques adopted by the users for extraction of text from image.  ...  With the evolution of huge amount of ancient and modern text available in digital format, it is ascertain to mine for researchers, government, tourist and travelers visiting all over the world.  ...  Image Printed Oriya script Classified News Scene text recognition Reduced label error unsupervised approach group unlabeled text document extraction.  ... 
doi:10.35940/ijitee.a5224.119119 fatcat:rasvnqr5nvevbgjituxs3butsu

Study Of Deep Learning Techniques For Differently Abled Applications And Detection Techniques

Anandh N, Et. al.
2021 Turkish Journal of Computer and Mathematics Education  
Due to the increase development of machine learning and deep learning algorithms, the digital image recognition and object recognition are become more efficient.  ...  The objective of this paper is to provide the detailed survey about the existing object recognition, face recognition and text to voice recognition methods proposed to assist VIP.  ...  This proposed approach obtains high detection rate of 15 frames per second than other algorithms. Zhang et al., [34] proposed a multi-task cascaded CNN for face detection and alignment.  ... 
doi:10.17762/turcomat.v12i10.5396 fatcat:zw45ghte4vaavpjgdxa4emjlb4

Automated border control e-gates and facial recognition systems

Jose Sanchez del Rio, Daniela Moctezuma, Cristina Conde, Isaac Martin de Diego, Enrique Cabello
2016 Computers & security  
Face recognition systems, installed in small kiosks inside the e-gates, require high quality facial images to allow high performance and efficiency.  ...  Accurate face recognition algorithms, which should be invariant to non-idealities, such as changes in pose and expression, occlusions, and changes in lighting, are also required for these systems.  ...  Acknowledgments This project ABC4EU (Automated Border Control Gates for Europe) received funding from the EU's Seventh Framework Programme for research, technological development, and demonstration under  ... 
doi:10.1016/j.cose.2016.07.001 fatcat:66gvociowffihdov4ivzihokmm

Card3DFace—An Application to Enhance 3D Visual Validation in ID Cards and Travel Documents

Leandro Dihl, Leandro Cruz, Nuno Gonçalves
2021 Applied Sciences  
The identification of a person is a natural way to gain access to information or places. A face image is an essential element of visual validation.  ...  In this paper, we present the Card3DFace application, which captures a single-shot image of a person's face.  ...  This application is aimed to be an easy and rapid way to provide a solution for the use of 3D face images in ID cards and travel documents for authentication.  ... 
doi:10.3390/app11198821 fatcat:koivo4ebjjcwvi3baa5vepcdkq

In-air gestures around unmodified mobile devices

Jie Song, Gábor Sörös, Fabrizio Pece, Sean Ryan Fanello, Shahram Izadi, Cem Keskin, Otmar Hilliges
2014 Proceedings of the 27th annual ACM symposium on User interface software and technology - UIST '14  
We propose a machine learning based algorithm for gesture recognition expanding the interaction space around the mobile device (B), adding in-air gestures and hand-part tracking (D) to commodity off-the-shelf  ...  We demonstrate a number of compelling interactive scenarios including bi-manual input to mapping and gaming applications (C+D).  ...  Furthermore, we thank Emily Whiting and Alec Jacobson for providing the voice-over for the video. Finally, we thank the study participants for their valuable time and feedback.  ... 
doi:10.1145/2642918.2647373 dblp:conf/uist/SongSPFIKH14 fatcat:wxf2zgom5nhhhkgseyjmzlov44

Automated Fare Calculation in Delhi Metro Using Face Recognition

Shrutika Shukla, Anuj Bhargava
2015 International Journal of Signal Processing, Image Processing and Pattern Recognition  
Face detection technology is developed for detecting facial features and ignores background images or cluttered images.  ...  Human face is the most dominant characteristic which is used to verify/authenticate a person amongst group of people.  ...  Face recognition technology in general sense can be classified on the basis of holistic approach or the global appearance of the face perceived by human eye and processed by the brain whereas feature-based  ... 
doi:10.14257/ijsip.2015.8.9.18 fatcat:dmiavv3phvhqdndooe6flzilwu

Audio Denoising, Recognition and Retrieval by Using Feature Vectors

Shruti Vaidya, Dr. Kamal Shah
2014 IOSR Journal of Computer Engineering  
A block thresholding estimation procedure is introduced, which relates the parameters adaptively to signal property.  ...  Content Based Audio Retrieval system is very useful to identify the unknown audio signals. Audio signals are classified into music, speech and background sounds.  ...  Vector quantization (VQ) is one of the lossy data compression techniques and has been used in number of applications, like pattern recognition, speech recognition and face detection, image segmentation  ... 
doi:10.9790/0661-1622107112 fatcat:cuw2xh6xdzbi5axsxap5xuplh4
« Previous Showing results 1 — 15 out of 24,223 results