Avaliação de Técnicas de Interpolação de Imagens Digitais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Desenvolvimento de metodologia para a obtenção da cubicagem de madeira em toras empilhadas através de imagens digitais

Obtaining accurate estimates of the volume of stacked wood is important in view of the increasing value of wood as raw material. Therefore, the forest companies have become increasingly concerned about the methods currently used to convert cubic meters for stereo. In this context, emerged the need of optimizing the measurement process and accuracy of the volume of stacked wood. For this, companies have been testing methods with greater efficiency, speed and low operating cost. Existing methods made through approximate equations, and also by determining the conversion factor, called the stacking factor (Fe), are questioned, due to errors and inaccuracies. The use of digital photographs is an alternative method that would minimize operator intervention, allowing greater control and speed the process, thus eliminating part of the imprecision of the traditional method. The use of the method is viable, due to present an error of about 10% while traditional methods showed an error of 17%

Inserção e extração de marca d'água em imagens digitais usando a transformada wavelet

Pós-graduação em Engenharia Elétrica - FEIS

Detecção e restauração de áreas sombreadas em imagens digitais de alta resolução espacial

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Análise de formas planas em imagens digitais

Given the widespread use of computers, the visual pattern recognition task has been automated in order to address the huge amount of available digital images. Many applications use image processing techniques as well as feature extraction and visual pattern recognition algorithms in order to identify people, to make the disease diagnosis process easier, to classify objects, etc. based on digital images. Among the features that can be extracted and analyzed from images is the shape of objects or regions. In some cases, shape is the unique feature that can be extracted with a relatively high accuracy from the image. In this work we present some of most important shape analysis methods and compare their performance when applied on three well-known shape image databases. Finally, we propose the development of a new shape descriptor based on the Hough Transform.

Estimativa do número de frutos verdes em laranjeiras com o uso de imagens digitais

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Imagens digitais na análise do uso da terra de uma microbacia como subsídio ao desenvolvimento sustentável

The present work sought to discriminate, to map and to quantify the areas of soil use of the Stream Monte Belo watershed - Botucatu (SP), obtained by digitale images. The cartographic bases were the shart planialtimetric, edited by IBGE (1969) and the satellite images LANDSAT - 7, passages of 21/01/1999, 08/01/2003 and 23/10/2006. The Software Idrisi Andes 15.0 were used for conversion of the analogical information for digital and for determination of the vegetable coverings areas. The results allowed to verify that the SIG - IDRISI Andes 15.0 were efficient in the quantification of the areas with soil use and that the analysis of the data showed a cash progress of the areas of reforestations to the detriment of the areas of pastures, especially from 1999, 2003 to 2006, when the field areas were substituted by the forestry in his totality. In spite of that progress, the forest areas that you correspond to the Permanent Preservation Areas, They are considerably preserved. That result comes to the encounter of the tendency of expansion of the forestry, especially after the installation of cellulose industries in the area, what worsened the environmental problems originating from of the practice of the monoculture.

Imagens digitais aplicadas no estudo da análise multitemporal do uso e ocupação do solo numa microbacia

The knowledge of the soil occupation as for his nature, location, occurrence form, changes happened in certain periods, they are valuable for the programming of activities that you seek to the development agricultural, economical and social of the area. This work aimed at to identify and to quantify the soil occupation of Stream Petiço Watershed - Botucatu (SP), through the Geographical Information System IDRISI and data of sensor Landsat 5 TM of 09/06/97 and 23/08/2013. For the analysis of the results it was verified that the eucalyptus culture, due to existence of great reforestation companies in the watershed, together with the native forests they are predominant in the study area, the remaining of the area is occupied by pastures and soil prepared for the planting of agricultural cultures.

Calibração e validação de um método de medida da radiação solar global por meio de actinógrafos baseada em técnicas de processamento de imagens digitais

O objetivo do trabalho é desenvolver um sistema informático de digitalização e processamento de actinogramas baseado em técnicas de Processamento de Imagens Digitais e comparar com o sistema tradicional de medidas. Os actinogramas foram fornecidos pela Estação Meteorológica de Botucatu (FCA/UNESP). As análises preliminares indicam um desempenho satisfatório do software proposto, gerando medidas na mesma ordem de grandeza do método de referência para partição diária. O software proposto pertence a um projeto que se encontra ainda em andamento, onde rotinas de técnicas diversas continuam sendo implementadas no reconhecimento da curva de interesse para melhorar a qualidade do processamento das informações gráficas dos actinogramas. Os actinogramas estão em fase de digitalização para que o software possa ser testado com uma base de dados mais consistente, onde poderão ser identificados tendências temporais dos dados resultantes da aplicação das técnicas de Processamento de Imagens Digitais no monitoramento da radiação solar por actinógrafos.

Análise do descritor de padrões mapeados localmente em multiescala para classificação de textura em imagens digitais

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Segmentação de texturas em imagens digitais utilizando wavelets redundantes

Pós-graduação em Matematica Aplicada e Computacional - FCT

Sistema inteligente para o processamento de imagens digitais intrabucais oclusais

Several are the areas in which digital images are used in solving day-to-day problems. In medicine the use of computer systems have improved the diagnosis and medical interpretations. In dentistry it’s not different, increasingly procedures assisted by computers have support dentists in their tasks. Set in this context, an area of dentistry known as public oral health is responsible for diagnosis and oral health treatment of a population. To this end, oral visual inspections are held in order to obtain oral health status information of a given population. From this collection of information, also known as epidemiological survey, the dentist can plan and evaluate taken actions for the different problems identified. This procedure has limiting factors, such as a limited number of qualified professionals to perform these tasks, different diagnoses interpretations among other factors. Given this context came the ideia of using intelligent systems techniques in supporting carrying out these tasks. Thus, it was proposed in this paper the development of an intelligent system able to segment, count and classify teeth from occlusal intraoral digital photographic images. The proposed system makes combined use of machine learning techniques and digital image processing. We first carried out a color-based segmentation on regions of interest, teeth and non teeth, in the images through the use of Support Vector Machine. After identifying these regions were used techniques based on morphological operators such as erosion and transformed watershed for counting and detecting the boundaries of the teeth, respectively. With the border detection of teeth was possible to calculate the Fourier descriptors for their shape and the position descriptors. Then the teeth were classified according to their types through the use of the SVM from the method one-against-all used in multiclass problem. The multiclass classification problem has been approached in two different ways. In the first approach we have considered three class types: molar, premolar and non teeth, while the second approach were considered five class types: molar, premolar, canine, incisor and non teeth. The system presented a satisfactory performance in the segmenting, counting and classification of teeth present in the images.

Sistema inteligente para o processamento de imagens digitais intrabucais oclusais

Several are the areas in which digital images are used in solving day-to-day problems. In medicine the use of computer systems have improved the diagnosis and medical interpretations. In dentistry it’s not different, increasingly procedures assisted by computers have support dentists in their tasks. Set in this context, an area of dentistry known as public oral health is responsible for diagnosis and oral health treatment of a population. To this end, oral visual inspections are held in order to obtain oral health status information of a given population. From this collection of information, also known as epidemiological survey, the dentist can plan and evaluate taken actions for the different problems identified. This procedure has limiting factors, such as a limited number of qualified professionals to perform these tasks, different diagnoses interpretations among other factors. Given this context came the ideia of using intelligent systems techniques in supporting carrying out these tasks. Thus, it was proposed in this paper the development of an intelligent system able to segment, count and classify teeth from occlusal intraoral digital photographic images. The proposed system makes combined use of machine learning techniques and digital image processing. We first carried out a color-based segmentation on regions of interest, teeth and non teeth, in the images through the use of Support Vector Machine. After identifying these regions were used techniques based on morphological operators such as erosion and transformed watershed for counting and detecting the boundaries of the teeth, respectively. With the border detection of teeth was possible to calculate the Fourier descriptors for their shape and the position descriptors. Then the teeth were classified according to their types through the use of the SVM from the method one-against-all used in multiclass problem. The multiclass classification problem has been approached in two different ways. In the first approach we have considered three class types: molar, premolar and non teeth, while the second approach were considered five class types: molar, premolar, canine, incisor and non teeth. The system presented a satisfactory performance in the segmenting, counting and classification of teeth present in the images.