No projeto Habitar a Paisagem, propuz uma prática investigativa envolvendo a imagem impressa e diversos meios de reprodução de imagens, incluindo linguagens como o vídeo e a fotografia, considerando suas singularidades e aproximações. As imagens tratam poeticamente de questões relativas à paisagem e a relação do homem com os espaços que habita. Os principais conceitos que permeiam e constituem o eixo deste grupo de trabalhos são: serialidade, transitoriedade, materialidade, singularidade e repetição. / In the project Inhabiting the Landscape, I proposed an investigative practice involving the printed image and various means of reproduction of images, including languages such as video and photography, considering its uniqueness and approximations. The images poetically deal with issues of landscape and man\'s relation to the space it inhabits. The main concepts that permeate and constitute the axis of this group of works are: seriality, transience, materiality, uniqueness and repetition.

No projeto Habitar a Paisagem, propuz uma prática investigativa envolvendo a imagem impressa e diversos meios de reprodução de imagens, incluindo linguagens como o vídeo e a fotografia, considerando suas singularidades e aproximações. As imagens tratam poeticamente de questões relativas à paisagem e a relação do homem com os espaços que habita. Os principais conceitos que permeiam e constituem o eixo deste grupo de trabalhos são: serialidade, transitoriedade, materialidade, singularidade e repetição. / In the project Inhabiting the Landscape, I proposed an investigative practice involving the printed image and various means of reproduction of images, including languages such as video and photography, considering its uniqueness and approximations. The images poetically deal with issues of landscape and man\'s relation to the space it inhabits. The main concepts that permeate and constitute the axis of this group of works are: seriality, transience, materiality, uniqueness and repetition.

This research focuses on developing algorithms to automatically classify, detect, simulate and improve the quality of defective printed images since the human visual system is unreliable. With the development of deep learning algorithms, state-of-the-art accuracy could be achieved for many computer vision tasks. This research applies the deep learning method to printed image quality assessment. Because most deep learning approaches require a large amount of data even after data augmentation, we propose to use Generative Adversarial Networks for simulation images generation. The simulated images with artifacts could be used for training classifier, detector and corrector networks for printed image quality. Another essential preprocessing step for printed image quality assessment is image registration, which can detect the defect and difference between two input images. This research proposes to use the deep learning framework for global image registration by parallel computation acceleration. For deformable local registration, we implement the U-Net VoxelMorph-based method for printed image registration. Then we further propose the recurrent network-based method, R-RegNet. The experimental results show that the proposed R-RegNet method outperforms the U-Net VoxelMorph-based method in all three datasets that we considered. Finally, we propose a photorealistic image dataset simulation method for training deep neural networks. A new dataset with simulated images, named Extra FAT, is introduced for object detection and 6D pose estimation.

Submitted by JÚLIO HEBER SILVA (julioheber@yahoo.com.br) on 2017-03-24T17:48:37Z No. of bitstreams: 2 Dissertação - Alan Henrique Ferreira Silva - 2016.pdf: 10881029 bytes, checksum: 1c411277f8b103cc8a55709053ed7f9b (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-03-27T15:13:01Z (GMT) No. of bitstreams: 2 Dissertação - Alan Henrique Ferreira Silva - 2016.pdf: 10881029 bytes, checksum: 1c411277f8b103cc8a55709053ed7f9b (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-03-27T15:13:01Z (GMT). No. of bitstreams: 2 Dissertação - Alan Henrique Ferreira Silva - 2016.pdf: 10881029 bytes, checksum: 1c411277f8b103cc8a55709053ed7f9b (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2016-03-31 / This work proposes method to encode and decode imas using conformal mapping. Conformal mapping modifies domains without modifyung physical characteristics between them. Real images are processed between these domains using encoding keys, also called transforming functions. The advantage of this methodology is the ability to carry the message as an encoded image in printed media for posterior-decoding. / Este trabalho propõe método que utiliza transformações conformes para codificar e decodificar imagens. As transformações conformes modificam os domínios em estudos sem modificar as características físicas entre eles. As imagens reais são transformadas entre estes domínios utilizando chaves, que são funções transformadoras. o diferencial desta metodologia é a capacidade de transportar a mensagem contida na imagem em meio impresso codificado e depois, decodificá-la.