Spelling suggestions: "subject:"arecognition off patterns"" "subject:"arecognition oof patterns""
1 |
The role of symmetry features in connectionist pattern recognitionHolland, Sam January 2012 (has links)
An investigation has been made into symmetry features of patterns as a means by which the patterns are described, or with which they are transformed prior to classification in order to assist a pattern recognition system. There are two main points of departure from existing symmetry use in the pattern recognition domain. The first is the adoption of the theory that patterns can be categorised solely using a map of the symmetry features that exist within the static pattern. The second is the application of symmetry transforms to aid non-trivial recognition in patterns which are not intended to be perfectly symmetrical. An experiment is conducted to classify the reflectional symmetry features of digits, using the Generalised Symmetry Transform to produce the features and Probabilistic Neural Networks to perform the classification. Symmetry feature information is also used to define parameters of affine transformations to achieve improved performance in tolerance to variances in position and orientation. The results lead to an investigation of the role of asymmetry. The Generalised Symmetry Transform is modified to produce two related transforms: the Generalised Asymmetry Transform and the Generalised Asymmetry and Symmetry Transform. Finally, a new symmetry transform is proposed which separates the factors affecting the degree of symmetry in an image into three non-linear functions of corresponding pairs of pixels. These factors are: the colour intensity values; the pixel orientations; and the respective distance between the point and potential reflection plane. The strictness of symmetry, or tolerance to non-symmetrical artifacts, is defined in variable parameters which are set to suit the desired application. This new transform is called the Reflectional Symmetry Transform. The structure of its input and output match those of the Generalised Symmetry Transform, which it is intended to replace.
|
2 |
Reconhecimento e classificação de fáceis geológicas através da análise de componentes independentes / Recognition and classification of geological facies based on independent component analysisSanchetta, Alexandre Cruz, 1986- 12 February 2010 (has links)
Orientador: Rodrigo de Souza Portugal / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecânica e Instituto de Geociências / Made available in DSpace on 2018-08-17T11:39:01Z (GMT). No. of bitstreams: 1
Sanchetta_AlexandreCruz_M.pdf: 1944469 bytes, checksum: 4ef771f7cb51787e86e285c870e84c53 (MD5)
Previous issue date: 2010 / Resumo: O uso método de análise multivariada ICA (Análise de Componentes Independentes), mais o método K-NN (K-vizinhos mais Próximos) aplicados em dados de poços e em dados sísmicos buscando classificar fácies geológicas e suas características. Esses dois métodos foram aplicados em dados retirados do Campo de Namorado, na Bacia de Campos, Brasil. A ICA encontra as componentes independentes dos dados, que quando treinadas pelo método K-NN para reconhecer padrões nos dados, predizem fácies geológicas e outras informações sobre as rochas, como as características de reservatório. Essas componentes independentes configuram uma nova opção de interpretação das informações disponíveis, pois nessas novas variáveis, o espaço de análise não apresenta dimensões dependentes e exclui informações repetidas ou dúbias da interpretação dos resultados. Além disso, a maior parte da informação é resumida em poucas dimensões, resultando em uma possível redução de variáveis referentes ao problema. Um abundante número de testes foi feito procurando a taxa de sucesso desse método. Como taxa de sucesso, é compreendida a divisão do número de predições corretas dividido pelo número total de tentativas. O que se observa é uma taxa de sucesso alta, em torno de 85% de acerto em algumas situações, ressaltando-se que as componentes têm distribuição gaussiana, sendo que o método funciona melhor em encontrar componentes não-gaussianas. Mesmo nessa situação adversa o método se mostrou robusto. A solidez do método mostra-se uma alternativa para novas formas de interpretação geológicas e petrofísicas. Um dos trunfos desse método é que a base da sua aplicação pode ser estendida para outros tipos de dados, inclusive de naturezas físicas diferentes / Abstract: The use of multivariate analysis method ICA (Independent Component Analysis), plus the K-NN method (K-nearest Neighbor) applied on well log data and seismic data to predict the classification of geological facies and their characteristics. These two methods were applied to data from the Campo de Namorado, in the Campos Basin, Brasil. The ICA finds the independent components of the data that can be trained by K-NN method to recognize patterns in the data and predict the geological facies or other information about the rocks, as the characteristics of the reservoir. These independent components make up a new option for interpretation of available information, because with these new variables, the space has no dependent dimensions and the duplicate information or dubious interpretation of results are excluded. Moreover, most of the information is summarized in a few dimensions, resulting in a possible reduction of variables related to the problem. An abundant number of tests were done looking for the success rate of this method. As success rate, it is understood by the division of the number of correct predictions divided by total attempts. What is observed is a high success rate, around 85% accuracy in some situations, pointing out that the components have a Gaussian distribution and the method works best in finding non-Gaussian components. Even in this adverse situation the method was robust. The robustness of the method proves that ICA can be an alternative to new forms of geological and petrophysical interpretation. One of the advantages of this method is that the basis of their application can be extended to other types of data, including datas with different physical natures / Mestrado / Reservatórios e Gestão / Mestre em Ciências e Engenharia de Petróleo
|
3 |
Desenvolvimento de tecnologia baseada em redes neurais artificiais para reconhecimento de gestos da língua de sinais / Development of technology based on artificial neural network for sign language gesture recognitionSilva, Brunna Carolinne Rocha 06 April 2018 (has links)
Submitted by Liliane Ferreira (ljuvencia30@gmail.com) on 2018-07-19T10:58:33Z
No. of bitstreams: 2
Dissertação - Brunna Carolinne Rocha Silva - 2018.pdf: 18872874 bytes, checksum: 227a38d63020f0863a2632461b79e19c (MD5)
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2018-07-19T11:21:27Z (GMT) No. of bitstreams: 2
Dissertação - Brunna Carolinne Rocha Silva - 2018.pdf: 18872874 bytes, checksum: 227a38d63020f0863a2632461b79e19c (MD5)
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2018-07-19T11:21:27Z (GMT). No. of bitstreams: 2
Dissertação - Brunna Carolinne Rocha Silva - 2018.pdf: 18872874 bytes, checksum: 227a38d63020f0863a2632461b79e19c (MD5)
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)
Previous issue date: 2018-04-06 / The purpose of this paper is to design, develop and evaluate four devices capable of identifying configuration, orientation and movement of the hands, verifying which one has better performance recognition of sign language gestures. The methodology starts from the definition of the layout and the components of data acquisition and processing, the construction of the database treated for each gesture to be recognized and validation of the proposed devices. Signs of flex sensors, accelerometers and gyroscopes are collected, positioned differently on each device. The recognition of the patterns of each gesture is performed using artificial neural networks. After being trained, validated and tested, the neural network interconnected to the devices obtain a hit rate of up to 96.8%. The validated device offers efficacy and efficiency to identify sign language gestures and demonstrates that the use of the sensory approach is promising. / O intuito deste trabalho é projetar, desenvolver e avaliar quatro dispositivos capazes de identificar configuração, orientação e movimento das mãos, verificando qual possui melhor desempenho para reconhecimento de gestos da língua de sinais. A metodologia parte da definição do leiaute e dos componentes de aquisição e processamento de dados, da construção da base de dados tratados para cada gesto a ser reconhecido e da validação dos dispositivos propostos. São coletados sinais de sensores de flexão, acelerômetros e giroscópios, posicionados diferentemente em cada dispositivo. O reconhecimento dos padrões de cada gesto é realizado utilizando redes neurais artificiais. Após treinada, validada e testada, a rede neural interligada aos dispositivos obtêm média de acerto de até 96,8%. O dispositivo validado oferece eficácia e eficiência para identificar gestos da língua de sinais e demonstra que o uso da abordagem sensorial é promissora.
|
Page generated in 0.0926 seconds