Scribd
Upload
26 views30 pages

Chapter 15-Computer VIsion

Chapter 15-Computer VIsion

Uploaded by

vibhay vibhay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
26 views30 pages

Chapter 15-Computer VIsion

Chapter 15-Computer VIsion

Uploaded by

vibhay vibhay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 30

Computer Vision

Convolution

• before the concept of convolution was


presented by Yann LeCun in 1998 for digit
classification, people used other methods
like support vector machine, knn, logistic
regression, etc to classify images.
• In those algorithms, pixel values were
considered as features i.e. for a 28x28
image there would be 784 features.
• There are a lot of algorithms that people
used for image classification before
convolution became popular.
• People used to create features from
images and then feed those features into
some classification algorithm like SVM.
• Some algorithms also used the pixel level
values of images as a feature vector.
• Convolution layer uses information from
adjacent pixels to down-sample the image
into features by convolution and then use
prediction layers to predict the target
values.
How does a Convolution layer work?

• We use multiple convolution filters or kernels


that run over the image and compute a dot
product.
• Lets consider a filter of size 3x3 and an image
of size 5x5.
• We perform an element wise multiplication
between the image pixel values that match the
size of the kernel and the kernel itself and sum
them up.
• This provides us a single value for the feature
cell.cts different features from the image.
Video- Working of Convolution
network
• https://www.youtube.com/watch?v=KiftWz
544_8&t=11s
• https://www.youtube.com/watch?v=f0t-OC
G79-U
Max Pooling Layer
• Max pooling layer helps reduce the spatial size
of the convolved features and also helps
reduce over-fitting by providing an abstracted
representation of them.
• It is similar to the convolution layer but instead
of taking a dot product between the input and
the kernel we take the max of the region from
the input overlapped by the kernel.
• Below is an example which shows a max pool
layer’s operation with a kernel having size of 2
and stride of 1.
Convolution Layer
• It is the first layer of a CNN.
• The objective of the Convolution Operation is to
extract the high-level features such as
edges, from the input image.
• It uses convolution operation on the images. In
the convolution layer, there are several kernels
that are used to produce several features.
• The output of this layer is called the feature
map.
• A feature map is also called the activation map.
• There’s several uses we derive from the
feature map:
▫ We reduce the image size so that it can
be processed more efficiently.
▫ We only focus on the features of the image
that can help us in processing the image
further.
Rectified Linear Unit Function
• Rectified Linear Unit function or the ReLU
layer.
• After we get the feature map, it is then
passed onto the ReLU layer.
• This layer simply gets rid of all the
negative numbers in the feature map and
lets the positive number stay as it is.
The process of passing it to the ReLU layer introduces non – linearity in
the feature map.
Now the question arises, why do we pass the
feature map to the ReLU layer? it is to make the
colour change more obvious and more abrupt?
Pooling Layer
• Similar to the Convolutional Layer.
• The Pooling layer is responsible for reducing the
spatial size of the Convolved Feature while still
retaining the important features.
• There are two types of pooling which can be
performed on an image.
▫ Max Pooling : Max Pooling returns the maximum
value from the portion of the image covered by the
Kernel.
▫ Average Pooling: Max Pooling returns the maximum
value from the portion of the image covered by the
Kernel.
• The pooling layer is an important layer in
the CNN as it performs a series of tasks
which are as follows :
▫ Makes the image smaller and more
manageable
▫ Makes the image more resistant to small
transformations, distortions and
translations in the input image.
Fully Connected Layer
• The final layer in the CNN is the Fully Connected
Layer (FCP).
• The objective of a fully connected layer is to take
the results of the convolution/pooling process and
use them to classify the image into a label.
• The final layer in the CNN is the Fully Connected
Layer (FCP).
• The objective of a fully connected layer is to take
the results of the convolution/pooling process and
use them to classify the image into a label

You might also like