Scribd
Upload
65 views16 pages

Seminar

Convolutional neural networks are deep artificial neural networks primarily used for image classification, clustering images by similarity, and object recognition in scenes. CNNs can identify faces, individuals, signs, tumors and other visual aspects. CNNs are complex feed forward networks that are highly accurate for image classification and recognition. CNNs follow a hierarchical model that builds a network like a funnel and outputs a fully connected layer where all neurons are connected. CNN layers learn filters that detect basic features in early layers and more complex parts and objects in later layers. CNNs can be applied to problems like detecting cracks in sewer pipes from images.

Uploaded by

Pallavi Bharti
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
65 views16 pages

Seminar

Convolutional neural networks are deep artificial neural networks primarily used for image classification, clustering images by similarity, and object recognition in scenes. CNNs can identify faces, individuals, signs, tumors and other visual aspects. CNNs are complex feed forward networks that are highly accurate for image classification and recognition. CNNs follow a hierarchical model that builds a network like a funnel and outputs a fully connected layer where all neurons are connected. CNN layers learn filters that detect basic features in early layers and more complex parts and objects in later layers. CNNs can be applied to problems like detecting cracks in sewer pipes from images.

Uploaded by

Pallavi Bharti
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/ 16

Convolutional Neural Networks for

Image Processing

Presented By –
Pallavi Arjun Bharati
Roll No – 18141112

Guidance By –
1) Dr. S. J. Wagh Sir
2) Prof. N. S. Deokule Sir
Convolution
Convolutional neural networks are deep artificial
neural networks that are used primarily to classify
images, cluster them by similarity (photo search),
and perform object recognition within scenes. By
use of CNNs it can identify faces, individuals, any
signs, tumors and many other aspects of visual
data.
Importance of CNN

Convolutional Neural Networks are complex feed forward


neural networks. CNNs are used for image classification and
recognition because of its high accuracy.
It was proposed by computer scientist Yann LeCun in the
late 90s, when he was inspired from the human visual
perception of recognizing things.
The CNN follows a hierarchical model which works on
building a network, like a funnel, and finally gives out a fully-
connected layer where all the neurons are connected to
each other and the output is processed.
Architecture of Convolution Neural Network
Types of layers
• Convolutional layers
▫ Feature Map or filter
▫ Shared weights
• Subsampling or Max pooling
• Full connected layer (classification)
Convolutional layer
1. First step is to extract features from an input
image.
2. In second step, Convolution preserves the
relationship between pixels by learning image
features using small squares of input data.
3. Third step is a mathematical operation that
takes two inputs such as image matrix and a filter
or say kernal.
Max pooling layer
• Takes smaller blocks from convolutional layer
• Subsamples to produce single output from that
block
• Several ways- average or maximum or learned
linear combination of neurons
• Max pooling layers take maximum out of that
block
Full-connected layer
• High level reasoning in NN
• Takes all neurons from previous layer and
connects it to every single neuron it has
• These are not spatially located (visualize as one-
dimensional)
• Therefore, no convolutional layers after fully
connected layer
What do CNN layers learn?
• Each CNN layer learns filters of increasing
complexity.
• The first layers learn basic feature detection filters:
edges, corners, etc
• The middle layers learn filters that detect parts of
objects. For faces, they might learn to respond to eyes,
noses, etc
• The last layers have higher representations: they learn
to recognize full objects, in different shapes and
positions.
Applying CNN to real-world problems
• Image processing system on mobile robot
• Task – detect and characterize cracks and
damage in sewer pipe walls.
• CNNs are used for image classification and
recognition because of its high accuracy.
• Task of CNN-
▫ filter raw data
▫ Identify spatial location of cracks
▫ Enable characterization of length, width of
damage
References
https://www.scribd.com/document/364932507/convolutional-neural-network-pdf
https://jivp-eurasipjournals.springeropen.com/articles/10.1186/s13640-019-0417-8
https://www.researchgate.net/publication/325663368_An_Analysis_Of_Convolutio
nal_Neural_Networks_For_Image_Classification
https://ieeexplore.ieee.org/document/8379889
https://www.ijert.org/an-analysis-of-convolution-neural-network-for-image-classifi
cation-using-different-models
https://www.ripublication.com/irph/ijert19/ijertv12n4_16.pdf
https://downloads.hindawi.com/journals/mpe/2020/1245924.pdf

You might also like