5. INTRODUCTION
“The field of digital image processing refers to
processing digital images by means of a digital
computer” (Gonzalez, 2008).
First digital image.
Created by Russell Kirsch in 1957.
6. PRINCIPAL APPLICATION
Improvement of pictorial information
for human interpretation.
Filtragem por contúdo
Processing of image data for storage,
transmission, and representation for
autonomous machine perception.
Objetivos
8. DIGITAL IMAGE
Introdução
Com a meta de alcance da acurácia de 99.8% do estoque, esta apresentação irá
trazer os cenários encontrados, os processos que podem ser melhorados e as
soluções propostas pela Reply.
Filtragem por contúdo
Objetivos
An image may be defined as a two-dimensional function, f(x,y), where x
and y are spatial (plane) coordinates, and the amplitude of f at any pair of
coordinates (x,y) is called the intensity of gray level of the image at that
point (pixel).
When x, y and the intensity values of f are all finite, discrete quantities,
we call the image a digital image.
Typically each pixel is composed by a triple colors and the proportion of
each one is translated into numeric values that allow be recuperated. The
most famous is RGB.
9. DIGITAL IMAGE
Introdução
Com a meta de alcance da acurácia de 99.8% do estoque, esta apresentação irá
trazer os cenários encontrados, os processos que podem ser melhorados e as
soluções propostas pela Reply.
Filtragem por contúdo
Objetivos
10. DIGITAL IMAGE REPRESENTATION
Introdução
Com a meta de alcance da acurácia de 99.8% do estoque, esta apresentação irá
trazer os cenários encontrados, os processos que podem ser melhorados e as
soluções propostas pela Reply.
Filtragem por contúdo
Objetivos
Bitmap - the image is stored as a series of tiny dots called pixels. When
we zoom in on a bitmap image we can see the individual pixels that make
up that image.
11. DIGITAL IMAGE REPRESENTATION
Introdução
Com a meta de alcance da acurácia de 99.8% do estoque, esta apresentação irá
trazer os cenários encontrados, os processos que podem ser melhorados e as
soluções propostas pela Reply.
Filtragem por contúdo
Objetivos
Vector images - are not based on pixel patterns, but instead use
mathematical formulas to draw lines and curves that can be combined to
create an image from geometric objects such as circles and polygons.
12. RESOLUTION
Introdução
Com a meta de alcance da acurácia de 99.8% do estoque, esta apresentação irá
trazer os cenários encontrados, os processos que podem ser melhorados e as
soluções propostas pela Reply.
Filtragem por contúdo
Objetivos
The resolution can be used to describe the size of a screen and it’s describe
the number of pixels per row and columns. It’s important to remember that
it’s not the number of pixels that determines the sharpness, it’s the size of
the pixels - smaller the better.
14. IMAGE PROCESSING
There is no agreement about what is image processing in the academy.
Some defines that it is “a discipline in which both the input and output of
process are image”.
On the other hand, there are fields such as computer vision whose
ultimate goal is to use computers to emulate human vision, including
learning and being able to make inferences and take actions based on
visual inputs. This area itself is a branch of Artificial Intelligence (AI). The
area of Image Analysis (also called image understanding) is in between
image processing and computer vision.
18. MID-LEVEL
Embalagens não
padronizadas.
It is characterized by the fact that its inputs generally are images, but its
output are attributes extracted from those images (e.g., edges, contours,
and the identify of individual objects).
Local
descriptor
Pre-
processing
Codebook
Codification
of features
Grouping and
normalization
Dimensional
Vector
19. HIGH-LEVEL
Embalagens não
padronizadas.
Involves “making sense” of an ensemble of recognized objects, as in
image analysis, and, at the far end of the continuum, performing the
cognitive functions normally associated with vision.
20.
21. OPENCV
Embalagens não
padronizadas.
Open Source Computer Vision Library (OpenCV) is an open source
computer vision and machine learning software library. OpenCV was built
to provide a common infrastructure for computer vision applications and to
accelerate the use of machine perception in the commercial products;
More than 2500 optimized algorithms;
More than 47K people of user community;
Estimated number of downloads exceeding 18 million;
It has C++, Python, Java and MATLAB interfaces;
Supports Windows, Linux, Android and Mac OS;