Página 1 dos resultados de 309 itens digitais encontrados em 0.015 segundos

"Hologramas gerados por computador utilizados como sensores ópticos" ; "Computer-generated holograms used as an optical sensor"

Khamis, Eduardo Georges
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 19/01/2005 Português
Relevância na Pesquisa
58.194004%
Dois tipos diferentes de hologramas (Fresnel e Fourier) foram gerados por computador. O holograma de Fresnel foi escolhido para fazer parte de um arranjo experimental que teve como objetivo estimar a rugosidade de amostras metálicas. Para isso, um novo método de aplicação de um correlator óptico foi desenvolvido. Hologramas de Fourier geralmente fazem parte do correlator óptico de VanderLugt, o qual é muito utilizado no reconhecimento de padrões. A reconstrução numérica de hologramas de Fresnel gerados por computador, "distorcidos" por superfícies metálicas (também simuladas), serviram de base para que a reconstrução óptica de um holograma de Fresnel fosse utilizada, de forma inédita, no reconhecimento de padrões para estimar a rugosidade de amostras metálicas. ; Two different types of holograms (Fresnel and Fourier) have been computer-generated. The Fresnel hologram has been chosen as part of an experimental set, which meant to estimate the roughness of the metalic samples. A new method for the aplication of an optical correlator has been developed. Fourier holograms are, generally, part of the VanderLugt optical correlator, that is very used for pattern recognition. The numerical reconstruction of the computer-generated Fresnel holograms...

Um estudo sobre reconhecimento de padrões: um aprendizado supervisionado com classificador bayesiano; A study on pattern recognition: supervised learning with a Bayesian classier

Cerqueira, Pedro Henrique Ramos
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 17/01/2011 Português
Relevância na Pesquisa
67.79614%
A facilidade que temos para reconhecer um rosto, compreender palavras faladas, ler manuscritos, identicar chaves do carro no bolso e decidir se uma maçã está madura pelo seu cheiro, desmentem os processos complexos que estão por trás desses atos de reconhecer estes padrões. Estes reconhecimentos têm sido cruciais para a nossa sobrevivência, e ao longo das últimas dezenas de milhões de anos desenvolvemos sistemas sosticados para a realização dessas tarefas. O reconhecimento de padrões tem por objetivo realizar a classicação de determinado conjunto de dados em determinadas classes ou grupos, considerando os seus padrões e os das classes, permitindo diversas aplicações, como por exemplo: processamento de documentos, leitores de código de barra; identicação de pessoas, leitores óticos ou de impressão digital; automação industrial, processamento de imagens e aplicações agronômicas, análise de marcadores moleculares e classicação de plantas, tornando-se nos últimos anos, uma técnica de grande importância. Para uma melhor classicação é necessário realizar aprendizados, que podem ser elaborados pelo método supervisionado ou não supervisionado, a m de desenvolver os classicadores, tais como o classicador bayesiano e as redes neurais...

9.913-C Pattern Recognition for Machine Vision, Spring 2002; Pattern Recognition for Machine Vision

Poggio, Tomaso; Heisele, Bernd; Ivanov, Yuri A., 1967-
Fonte: MIT - Massachusetts Institute of Technology Publicador: MIT - Massachusetts Institute of Technology
Português
Relevância na Pesquisa
78.03395%
The course is directed towards advanced undergraduate and beginning graduate students. It will focus on applications of pattern recognition techniques to problems of machine vision. The topics covered in the course include: Overview of problems of machine vision and pattern classification Image formation and processing Feature extraction from images Biological object recognition Bayesian Decision Theory Clustering

Reconocimiento de patrones utilizando técnicas estadísticas y conexionistas aplicadas a la clasificación de dígitos manuscritos; Pattern recognition using statistical techniques and neural networks: application to handwritten digit classification

Seijas, Leticia María
Fonte: Facultad de Ciencias Exactas y Naturales. Universidad de Buenos Aires Publicador: Facultad de Ciencias Exactas y Naturales. Universidad de Buenos Aires
Tipo: info:eu-repo/semantics/doctoralThesis; tesis doctoral; info:eu-repo/semantics/publishedVersion Formato: application/pdf
Publicado em //2011 Português
Relevância na Pesquisa
68.157583%
El Reconocimiento de Patrones es el estudio de cómo las máquinas pueden observar el ambiente o entorno, aprender a distinguir patrones de interés a partir de la experiencia, y tomar decisiones razonables con respecto a las categorías a las que pertenecen dichos patrones. El mejor reconocedor de patrones conocido hasta ahora es el ser humano, no sabiéndose a ciencia cierta cuál es el proceso mediante el cual los humanos realizamos esta tarea. El Reconocimiento Optico de Caracteres (OCR) es uno de los tópicos más antiguos dentro del Reconocimiento de Patrones y una de las areas de investigación más importante y activa, que en la actualidad presenta desafío: la precisión en el reconocimiento asociada tanto a caracteres impresos en una imagen degradada o a caracteres manuscritos es aún insuficiente, existiendo errores en el reconocimiento. El Reconocimiento de Dígitos Manuscritos es un tema destacado dentro de OCR, por las aplicaciones relacionadas, como el procesamiento automático de cheques bancarios, la clasificación de correo en base a la lectura de códigos postales, la lectura automática de formularios y documentos con escritura manuscrita, dispositivos de lectura para ciegos, reconocimiento de escritura en computadoras manuales PDA...

Boosting Optical Character Recognition: A Super-Resolution Approach

Dong, Chao; Zhu, Ximei; Deng, Yubin; Loy, Chen Change; Qiao, Yu
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 06/06/2015 Português
Relevância na Pesquisa
67.53673%
Text image super-resolution is a challenging yet open research problem in the computer vision community. In particular, low-resolution images hamper the performance of typical optical character recognition (OCR) systems. In this article, we summarize our entry to the ICDAR2015 Competition on Text Image Super-Resolution. Experiments are based on the provided ICDAR2015 TextSR dataset and the released Tesseract-OCR 3.02 system. We report that our winning entry of text image super-resolution framework has largely improved the OCR performance with low-resolution images used as input, reaching an OCR accuracy score of 77.19%, which is comparable with that of using the original high-resolution images 78.80%.; Comment: 5 pages, 8 figures

Artificial Neural Network Based Optical Character Recognition

Shrivastava, Vivek; Sharma, Navdeep
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 19/11/2012 Português
Relevância na Pesquisa
67.67546%
Optical Character Recognition deals in recognition and classification of characters from an image. For the recognition to be accurate, certain topological and geometrical properties are calculated, based on which a character is classified and recognized. Also, the Human psychology perceives characters by its overall shape and features such as strokes, curves, protrusions, enclosures etc. These properties, also called Features are extracted from the image by means of spatial pixel-based calculation. A collection of such features, called Vectors, help in defining a character uniquely, by means of an Artificial Neural Network that uses these Feature Vectors.; Comment: Signal & Image Processing : An International Journal (SIPIJ) Vol.3, No.5, October 2012

Sequence to Sequence Learning for Optical Character Recognition

Sahu, Devendra Kumar; Sukhwani, Mohak
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 13/11/2015 Português
Relevância na Pesquisa
67.53673%
We propose an end-to-end recurrent encoder-decoder based sequence learning approach for printed text Optical Character Recognition (OCR). In contrast to present day existing state-of-art OCR solution which uses connectionist temporal classification (CTC) output layer, our approach makes minimalistic assumptions on the structure and length of the sequence. We use a two step encoder-decoder approach -- (a) A recurrent encoder reads a variable length printed text word image and encodes it to a fixed dimensional embedding. (b) This fixed dimensional embedding is subsequently comprehended by decoder structure which converts it into a variable length text output. Our architecture gives competitive performance relative to connectionist temporal classification (CTC) output layer while being executed in more natural settings. The learnt deep word image embedding from encoder can be used for printed text based retrieval systems. The expressive fixed dimensional embedding for any variable length input expedites the task of retrieval and makes it more efficient which is not possible with other recurrent neural network architectures. We empirically investigate the expressiveness and the learnability of long short term memory (LSTMs) in the sequence to sequence learning regime by training our network for prediction tasks in segmentation free printed text OCR. The utility of the proposed architecture for printed text is demonstrated by quantitative and qualitative evaluation of two tasks -- word prediction and retrieval.; Comment: 9 pages (including reference)...

A survey of modern optical character recognition techniques

Borovikov, Eugene
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 12/12/2014 Português
Relevância na Pesquisa
67.67546%
This report explores the latest advances in the field of digital document recognition. With the focus on printed document imagery, we discuss the major developments in optical character recognition (OCR) and document image enhancement/restoration in application to Latin and non-Latin scripts. In addition, we review and discuss the available technologies for hand-written document recognition. In this report, we also provide some company-accumulated benchmark results on available OCR engines.; Comment: Technical report surveying OCR/ICR and document understanding methods as of 2004.It contains 38 pages, numerous figures, 93 references, and provides a table of contents

Design of an Optical Character Recognition System for Camera-based Handheld Devices

Mollah, Ayatullah Faruk; Majumder, Nabamita; Basu, Subhadip; Nasipuri, Mita
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 15/09/2011 Português
Relevância na Pesquisa
67.715923%
This paper presents a complete Optical Character Recognition (OCR) system for camera captured image/graphics embedded textual documents for handheld devices. At first, text regions are extracted and skew corrected. Then, these regions are binarized and segmented into lines and characters. Characters are passed into the recognition module. Experimenting with a set of 100 business card images, captured by cell phone camera, we have achieved a maximum recognition accuracy of 92.74%. Compared to Tesseract, an open source desktop-based powerful OCR engine, present recognition accuracy is worth contributing. Moreover, the developed technique is computationally efficient and consumes low memory so as to be applicable on handheld devices.

Optical Character Recognition, Using K-Nearest Neighbors

Wang, Wei
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 05/11/2014 Português
Relevância na Pesquisa
67.53673%
The problem of optical character recognition, OCR, has been widely discussed in the literature. Having a hand-written text, the program aims at recognizing the text. Even though there are several approaches to this issue, it is still an open problem. In this paper we would like to propose an approach that uses K-nearest neighbors algorithm, and has the accuracy of more than 90%. The training and run time is also very short.

Optical pattern recognition based on color vision models

Millán García-Varela, M. Sagrario; Corbalán Fuertes, Montserrat; Romero, J.; Yzuel Giménez, María Josefa
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //1995 Português
Relevância na Pesquisa
67.877393%
A channel transformation based on opponent-color theory of the color vision models is applied to optical pattern recognition so that the conventional red, green, and blue (RGB) channels are transformed into bright–dark, red–green, and yellow–blue (ATD) channels. Matched filtering and correlation are performed over the new components of the target and the scene in the ATD system. The proposed transformation allows us to reduce the number of channels commonly used in color pattern recognition, passing from the three RGB channels to the two red–green and yellow–blue opponent-color channels.

Infrared target simulation environment for pattern recognition applications

Savakis, Andreas; George, Nicholas
Fonte: The International Society for Optical Engineering (SPIE) Publicador: The International Society for Optical Engineering (SPIE)
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
78.155786%
The generation of complete databases of infrared (IR) data is extremely useful for training human observers and testing automatic pattern recognition algorithms. Field data may be used for realism, but require expensive and time-consuming procedures. Infrared scene simulation methods have emerged as a more economical and efficient alternative for the generation of JR databases. A novel approach to IR target simulation is presented in this paper. Model vehicles at 1:24 scale are used for the simulation of real targets. The temperature profile of the model vehicles is controlled using resistive circuits which are embedded inside the models. The infrared target is recorded using an Inframetrics dual channel IR camera system. Using computer processing we place the recorded JR target in a prerecorded background. The advantages of this approach are: (i) the range and 3-D target aspect can be controlled by the relative position between the camera and model vehicle; (ii) the temperature profile can be controlled by adjusting the power delivered to the resistive circuit; (iii) the IR sensor effects are directly incorporated in the recording process, because the real sensor is used; (iv) the recorded target can be embedded in various types of backgrounds recorded under different weather conditions...

Context sensitive optical character recognition using neural networks and hidden Markov models

Elliott, Steven C.
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
67.870146%
This thesis investigates a method for using contextual information in text recognition. This is based on the premise that, while reading, humans recognize words with missing or garbled characters by examining the surrounding characters and then selecting the appropriate character. The correct character is chosen based on an inherent knowledge of the language and spelling techniques. We can then model this statistically. The approach taken by this Thesis is to combine feature extraction techniques, Neural Networks and Hidden Markov Modeling. This method of character recognition involves a three step process: pixel image preprocessing, neural network classification and context interpretation. Pixel image preprocessing applies a feature extraction algorithm to original bit mapped images, which produces a feature vector for the original images which are input into a neural network. The neural network performs the initial classification of the characters by producing ten weights, one for each character. The magnitude of the weight is translated into the confidence the network has in each of the choices. The greater the magnitude and separation, the more confident the neural network is of a given choice. The output of the neural network is the input for a context interpreter. The context interpreter uses Hidden Markov Modeling (HMM) techniques to determine the most probable classification for all characters based on the characters that precede that character and character pair statistics. The HMMs are built using an a priori knowledge of the language: a statistical description of the probabilities of digrams. Experimentation and verification of this method combines the development and use of a preprocessor program...

A Comparison of pattern classification techniques for orienting chest X-rays

Hoffmann, Martin
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
57.71063%
The problem of orienting digital images of chest x-rays, which were captured at some multiple of 90 degrees from the true orientation, is a typical pattern classification problem. In this case, the solution to the problem must assign an instance of a digital image to one of four classes, where each class corresponds to one of the four possible orientations. A large number of techniques are available for developing a pattern classifier. Some of these techniques are characterized by independent variables whose values are difficult to relate back to the problem being solved. If a technique is highly sensitive to the values of these variables, the lack of a rigorous way of defining them can be a significant disadvantage to the inexperienced researcher. This thesis presents experiments by the author to solve the chest x-ray orientation problem using four different pattern classification techniques: genetic programming, an artificial neural network trained with back propagation, a probabilistic neural network, and a simple linear classifier. In addition, the author will demonstrate that an understanding of the design of a feature set may allow a programmer to develop a traditional program which does an adequate job of solving the classification problem. Comparisons of the different techniques will be based not only on their success at solving the problem...

Advanced correlation-based character recognition applied to the Archimedes Palimpsest

Walvoord, Derek J.
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Dissertação
Português
Relevância na Pesquisa
68.159243%
The Archimedes Palimpsest is a manuscript containing the partial text of seven treatises by Archimedes that were copied onto parchment and bound in the tenth-century AD. This work is aimed at providing tools that allow scholars of ancient Greek mathematics to retrieve as much information as possible from images of the remaining degraded text. Acorrelation pattern recognition (CPR) system has been developed to recognize distorted versions of Greek characters in problematic regions of the palimpsest imagery, which have been obscured by damage from mold and fire, overtext, and natural aging. Feature vectors for each class of characters are constructed using a series of spatial correlation algorithms and corresponding performance metrics. Principal components analysis (PCA) is employed prior to classification to remove features corresponding to filtering schemes that performed poorly for the spatial characteristics of the selected region-of-interest. A probability is then assigned to each class, forming a character probability distribution based on relative distances from the class feature vectors to the ROI feature vector in principal component (PC) space. However, the current CPR system does not produce a single classification decision...

A Simulated shape recognition system using feature extraction

Pan, Wendy
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
57.97008%
A simulated shape recognition system using feature extraction was built as an aid for designing robot vision systems. The simulation allows the user to study the effects of image resolution and feature selection on the performance of a vision system that tries to identify unknown 2-D objects. Performance issues that can be studied include identification accuracy and recognition speed as functions of resolution and the size and makeup of the feature set. Two approaches to feature selection were studied as was a nearest neighbor classification algorithm based on Mahalanobis distances. Using a pool of ten objects and twelve features, the system was tested by performing studies of hypothetical visual recognition tasks.

The Application of neural networks to character recognition based on primitive feature detection

Pistacchio, Michael
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
58.05658%
This thesis investigates a character recognition method inspired by the premise that humans recognize shapes using their ability to assimilate a set of primitive features. These features collectively create a higher level shape of a certain category. The primitive features employed in our method include horizontal, vertical, diagonal lines, and corners of various orientations positioned at various places within a character. Combinations of these features form categories of characters to be recognized. The basic approach consists of preprocessing a character bitmap, extracting primitive features to form a feature vector. The feature vector is then input to a classification neural net. Based on weights derived during training, the system selects the character most closely identified by the feature vector. The advantages of this approach are the speed of training and recognition (as opposed to methods which continually iterate to the final solution), and robustness of the "blurring" effect realized by transforming a character bitmap to an array of features, rather than attempting template matching at the bitmap or pixel level. To support this study, a graphics workstation based environment has been developed, equiped with 3000 16X16 pixel characters...

Fuzzy approach for Arabic character recognition

El-Nasan, Adnan
Fonte: Rochester Instituto de Tecnologia Publicador: Rochester Instituto de Tecnologia
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
68.016123%
Pattern recognition/classification is increasingly drawing the attention of scientific research because of its important roll in automation and human-machine communication. Even though many models have been introduced to deal with classification, because of the inherited imprecision and ambiguity, these models did not tackle the problem in an efficient way. Traditional models deal only with statistical uncertainty (randomness) but not with the non-statistical uncertainty (vagueness). Fuzzy set theory allows us to better understand imprecision in both of its categories: vagueness and randomness. The incorporation of fuzzy set theory in existing algorithms helped in many cases to improve the performance and increase the efficiency of those algorithms. This thesis will explore fuzzy logic as it pertains to pattern recognition. In order to demonstrate fuzzy logic, the problem of recognizing the Arabic alphabet is discussed. In this problem moments and central moments were used as discriminating features. A fuzzy classifier was designed in a way that incorporated some statistical knowledge of the problem in hand. Performance of this classifier was compared to a Bayesian classifier and a neural network classifier. Performance, evaluation...

Rotation-invariant synthetic discriminant function filter for pattern recognition

Riasati, Vahid; Banerjee, Partha; Abushagur, Mustafa; Howell, Kenneth
Fonte: SPIE - Optical engineering Publicador: SPIE - Optical engineering
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
87.87739%
The ring synthetic discriminant function (RSDF) filter for rotation-invariant response is discussed for pattern recognition. This method uses one half of a slice of the Fourier transform of the object to generate the transfer function of the filter. This is accomplished by rotating the one half of a slice in the Fourier domain through 2p rad about the zero-frequency point of the Fourier plane. This filter has the advantage of always matching at least one half of a slice of the Fourier transform of any rotation of the image. An analytical discussion of the filter construction and correlation results are presented along with simulated correlation results for a particular target image. These results and established metrics are used for comparison with benchmark algorithms.; Copyright 2000 SPIE. This paper was published by SPIE and is made available as an electronic reprint (preprint) with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. ; RIT community members may access full-text via RIT Libraries licensed databases: http://library.rit.edu/databases/

Rotation-invariant synthetic discriminant function filter for pattern recognition

Riasati, Vahid; Banerjee, Partha; Abushagur, Mustafa; Howell, Kenneth
Fonte: Society of Photo-Optical Instrumentation Engineers (SPIE) - Optical Engineering Publicador: Society of Photo-Optical Instrumentation Engineers (SPIE) - Optical Engineering
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
88.0771%
The ring synthetic discriminant function (RSDF) filter for rotation-invariant response is discussed for pattern recognition. This method uses one half of a slice of the Fourier transform of the object to generate the transfer function of the filter. This is accomplished by rotating the one half of a slice in the Fourier domain through 2p rad about the zero-frequency point of the Fourier plane. This filter has the advantage of always matching at least one half of a slice of the Fourier transform of any rotation of the image. An analytical discussion of the filter construction and correlation results are presented along with simulated correlation results for a particular target image. These results and established metrics are used for comparison with benchmark algorithms.; Copyright 2000 Society of Photo-Optical Instrumentation Engineers. This paper was published by SPIE and is made available as an electronic reprint (preprint) with permission of SPIE. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.; RIT community members may access full-text via RIT Libraries licensed databases: http://library.rit.edu/databases/