Browsing by Author "Jordán Bolaños, Carlos Rodrigo"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Modelo matemático basado en las técnicas de detección de bordes y propagación de texturas para restaurar imágenes fotográficas documentales RGB
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Matemática Aplicada, 2021) Jordán Bolaños, Carlos Rodrigo; Gordón Gallegos, Carlos Diego
    EXECUTIVE SUMMARY The restoration of RGB documentary photographic images, using a mathematical model based on two fundamental techniques texture propagation and edge detection seek to give balanced priority to the two techniques, that is, neither should prevail over the other, using the notation for image restoration: I = Image, ɸ = source region. It is the known region of the image, Ω = target region. It is the region to restore and 𝛿Ω = border. RGB (color) documentary photographic images focus on people and social groups, to show aspects of their daily lives and are born with the intention of capturing reality in a still image. Edge detection is a technique that facilitates the identification of image objects and therefore their recognition. If the purpose of edge detection algorithms is to obtain as a result an image where the pixels of those points of the original image where sudden changes in intensity are presented are highlighted. In this respect it is worth highlighting, among others, the techniques related to zero crossing (“Zero crossing”) and level set (“level set”). On the other hand, texture propagation is a technique that consists of building from a small sample image, a large image that preserves the structure of the sample. An important part of the model that is proposed in this work, consists in filling the image by pixels, first of all, you must count on the area to be restored is well defined so that the neighboring textures maintain balance and harmony in the final result. The proposed mathematical model is designed to obtain from the original image, first the gradient of the image followed by the extraction map which is nothing more than the silhouette of the object to be extracted; then the energy map of the image is created to proceed with the removal of seams. Seam after seam will be removed until you create a resulting image similar in size and characteristics to the original. Finally the restoration will be done considering the edges and textures of the original image, with this it will be evaluated if the restored documentary photographic image is visually satisfactory. The similarity criterion to make the comparison between the original and resulting image has to be of mathematical type, that is, an algorithm will compare pixel by pixel the two images showing on screen how efficient the algorithm is. Under the above context it is said that the restoration of images through mathematical modelling seeks to refine the amendment in an intelligent way, that is to say, that at the end of the restore process, the image is visually pleasing to the observer, where the subtraction of elements or the size modification does not harm the harmony of colors, shapes and textures.