3. What
In the late 1960s, computer vision began at universities
that were pioneering artificial intelligence. It was meant to
mimic the human visual system, as a stepping stone to
endowing robots with intelligent behavior.
In 1966, it was believed that this could be achieved
through a summer project, by attaching a camera to a
computer and having it "describe what it saw".
4. What
What distinguished computer vision from the prevalent field
of digital image processing at that time was a desire to extract
three-dimensional structure from images with the goal of
achieving full scene understanding.
Studies in the 1970s formed the early foundations for many
computer vision today.
5. What
The scientific discipline of computer vision is concerned
with the theory behind how machines interpret images .
The image data can take many forms, such as video
sequences, views from multiple cameras, multi-dimensional
data from a 3D scanner, or medical scanning devices.
6. Expectations
Understand how a computer interprets pixels to symbols
Understand object detection, classification, and segmentation.
Put computer vision to practice by writing a script to identify and
segment images in Python.
Bonus: Hackathon - Create Amazon Rekognition Custom Labels
Project using Images in Amazon S3
8. What
The scientific discipline of computer vision is concerned
with the theory behind artificial systems that extract
information from images.
The image data can take many forms, such as video
sequences, views from multiple cameras, multi-dimensional
data from a 3D scanner, or medical scanning devices.
9.
10.
11. Pixel To Symbol
The image data can take many forms, such as video
sequences, views from multiple cameras, multi-dimensional
data from a 3D scanner, or medical scanning devices.
13. Pixel To Symbol
Let’s recap what we just learned:
A color image is comprised of three channels: red, green, and blue.
These channels correspond to those in a single pixel.
When a computer reads (or writes) an image, it takes the intensity
values of each channel in a pixel and stores them in corresponding
cells of a 3D array.
14. Pixel To Symbol
Thus, what a computer “sees” is the array!
The task of computer vision, then, is to train an algorithm to recognize
patterns in the 3D array and associate that pattern with an object or
shape.
17. Pixel To Symbol
To navigate the above image we’ll use an index that will follow this
pattern: [Channel #, Row #, Column #].
“what is the value stored at [1, 0, 2]?”, you would go to the green
channel (channel 1), find the cell on the top row (row 0) and the 3rd
column (column 2), and report that the answer is 0.376.
With that, let’s compare the values of a single pixel. What are the
values in the following cells: [0, 0, 1], [1, 0, 1], and [2, 0, 1]?
18. Pixel To Symbol
With that, let’s compare the values of a single pixel. What are the
values in the following cells: [0, 0, 1], [1, 0, 1], and [2, 0, 1]?
23. How
Object classification: Object classification is a computer vision
technique/task used to classify an image, such as whether an image
contains a dog, a person's face, or a banana.
It analyzes the visual content (videos & images) and classifies the
object into the defined category. It means that we can accurately
predict the class of an object present in an image with image
classification.
24. How
Object Verification: The system processes videos, finds the objects
based on search criteria, and tracks their movement.
Object Landmark Detection: The system defines the key points for
the given object in the image data.
25. How
Image Segmentation: Image segmentation not only detects the
classes in an image as image classification; instead, it classifies each
pixel of an image to specify what objects it has. It tries to determine
the role of each pixel in the image.
28. create your own object detection
program using Python
requirements:
opencv-python
cvlib
matplotlib
tensorflow
29. read an image from storage,
perform object detection on the image
display the image with a bounding box
label the detected objects.
Here is the code to import the required Python libraries;
30. import cv2
import matplotlib.pyplot as plt
import cvlib as cv
from cvlib.object_detection import draw_bbox
im = cv2.imread('apple-256261_640.jpg')
bbox, label, conf = cv.detect_common_objects(im)
output_image = draw_bbox(im, bbox, label, conf)
plt.imshow(output_image)
plt.show()
31. To know about all the objects that can be detected using this library, you can
visit the link below.
Github
32. "Just as to hear is not to listen,
to take pictures is not to see."
Fei-Fei Lee
Sequoia Capital Professor of Computer
Science at Stanford University and former
board director at Twitter.