A presentation about image processing and a tutorial of hands-on using OpenCV.

1. WORKING WITH
IMAGE
PROCESSING
JUN 25, 2019
Renato Souza | Logistics BR

2. AGENDA
1 Introduction
2 Understand how a digital image is formed
3 Image processing
1 low-level;
2 mid-level;
3 high-level;
4 OpenCV
5 Tutorial

3. INTRODUCTION

4. Drone for cycle count

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

7. UNDERSTAND
HOW A DIGITAL
IMAGE IS
FORMED

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.

13. IMAGE
PROCESSING

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.

15. IMAGE PROCESSING
Problem Domain
Image
acquisition
Image
enhancement
Image
restoration
Morphological
processing
Segmentation
Object
Recognition
Representation
& Description
Colour image
processing
Image
compression

16. IMAGE PROCESSING
Embalagens não
padronizadas.
Image AnalysisImage
Processing
Vision
Low-Level
 Restoration
 Contrast Enhancement
 Image Sharpening
Mid-Level
 Segmentation
• Classification
High-Level
 Making sense of
ensemble
recognized
objects

17. LOW-LEVEL
Embalagens não
padronizadas.
 It is characterized by the fact that both its inputs and output are images.

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.

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;

22. RESOURCES
Embalagens não
padronizadas.
 Homepage: https://opencv.org
 Docs: https://docs.opencv.org/master/
 Q&A forum: http://answers.opencv.org
 Issue tracking: https://github.com/opencv/opencv/issues
 GitHub: https://github.com/opencv/opencv

23. DOWNLOAD
 Link: https://opencv.org/releases/

24. TUTORIAL

25. Environment
 Eclipse: https://www.eclipse.org/downloads/
 E(FX) eclipse: https://download.eclipse.org/efxclipse/updates-
released/1.2.0/site/
 OpenCV: https://opencv.org/releases/

26. OpenCV on Eclipse

27. OpenCV on Eclipse

28. Exercise 1
 Check if the OpenCV is working on Eclipse.
opencv_java410 Output:

29. Exercise 2
 Create an Webcam application.

30. Exercise 3
 Create an Webcam application with face detection.