ONNIS-GI: uma rede neural oscilatória para segmentação de imagens implementada em arquitetura maciçamente paralela

نویسنده

  • Dênis Fernandes
چکیده

The present thesis aims at proposing a new oscillatory neural network and at implementating using a massively parallel architecture, which is suitable to the implementation of digital vision chips for image segmentation. The final version of the proposed network called ONNIS-GI (Oscillatory Neural Network for Image Segmentation with Global Inhibition) was inspired on a network called LEGION (Locally Excitatory Globally Inhibitory Oscillator Network), also of recent conception. Primarily, an introduction to the procedures of image segmentation is presented with the objective to situate and emphasize the importance of the subject in the general context of artificial vision. The thesis also covers the utilization of artificial neural networks in image segmentation, with emphasis on the oscillatory neural networks, which have presented encouraging results in this area. The implementation of vision chips, integrating image sensors and massively parallel processor networks, is also mentioned emphasizing the practical application of the new network proposed. In the study of the LEGION network, results of original applications in image segmentation are presented, in which its segment temporal separation property is verified. The continuous version of this network, a two-dimensional array of neurons based on differential equations, presents both high computational complexity to implementation using digital hardware and many parameters with little practical setting procedures. On the other hand, its massively parallel topology is particularly adequate to the implementation of analog vision chips suitable to segment images. Based on the good results obtained with the developed applications, a new oscillatory neural network is proposed in two versions, called ONNIS and ONNIS-GI, supplanting the LEGION network in several aspects related to practical implementation. The structure of the processing elements of the two versions of the proposed network, its implementation in massively parallel architecture and results concerning simulations and FPGA implementation are presented, demonstrating the viability of the proposal. As a final result, it is concluded that the ONNIS-GI network is more attractive for practical applications, being an innovative approach, efficient in solving image segmentation problems, and possessing the ability to separate the image segments in time for easier identification. Under a practical point of view, the new network can be used for the implementation of vision chips with massively parallel architecture using digital technology, exploring the speed of such implementations and also presenting flexibility to implement more sophisticated segmentation procedures.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

XIRU: Interface de Rede Extensível para Integração de Núcleos a uma Rede-em-Chip

For the integration of the cores of a SoC (System-on-Chip) to a NoC (Network-on-Chip), it is necessary the using of communication interfaces that perform the adaptation of the core protocol to the network protocol and provide the necessary communication services to the cores. This paper presents a research done in order to provide an extensible network interface for the integration of cores to ...

متن کامل

Técnicas em Processamento e Análise de Documentos Manuscritos

This work aims to present the main modules of a typical Handwriting Document Processing and Analysis System (HDPAS): data acquisition, preprocessing, segmentation, feature extraction and recognition. First, the relevant aspects of each HDPAS process are given, different types of documents, filtering and segmentation techniques applied to extract the interested data. Then, the main Hidden Markov...

متن کامل

Um Sistema de Apoio à Decisão Baseado em Agentes para Tratamento de Ocorrências no Setor Elétrico

Ronneesley M. Teles, Marcos Ivamoto, Leonardo H. S. Mello, Valdemar V. Graciano Neto, Cedric Luiz de Carvalho 1 Resumo: Empresas fornecedoras de energia elétrica e mantenedoras das redes de distribuição lidam diariamente com a reparação de falhas na rede elétrica e alocação de veículos especializados para atendimento de ocorrências. Em geral, tais empresas dispõem de recursos humanos limitados ...

متن کامل

OntoSAIA: Um Ambiente Baseado em Ontologias para Recuperação e Anotação Semi-Automática de Imagens

This article proposes the use of image content, keywords and ontologies to improve the image annotation and retrieval processes through the enhancement of the user’s knowledge of an image database. It proposes an architecture of a flexible system capable of dealing with multiple ontologies and multiple image content descriptors to help these tasks. The validation of the idea is being done throu...

متن کامل

Evaluation of Classifiers for Image Segmentation: Applications for Eucalypt Forest Inventory

The task of counting eucalyptus trees from aerial images collected by unmanned aerial vehicles (UAVs) has been frequently explored by techniques of estimation of the basal area, i.e, by determining the expected number of trees based on sampling techniques. An alternative is the use of machine learning to identify patterns that represent a tree unit, and then search for the occurrence of these p...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004