4. A computer doesn’t see an image, but a matrix of pixels, each
of which has three components: red, green and blue.
It will then assign a value, or intensity, to each of those
pixels.
5. MC^2 : hey, T-800 what about my
pic??
T-800 :bro, it’s a diagonal matrix.
6. Computer Vision
Computer vision is a field that includes method for acquiring,
processing, analyzing, and understanding images
An algorithm do understand images content in the same way
human brain does.
And to make this work we use algorithm very similar to how
the human brain operates using ML
ML allows us to effectively train the context for a dataset so that
an algorithm can understand what all those massive array integer in a
specific organization represent.
7. • And what if we have image that are difficult for a human to classify??
• Can ML achieve better accuracy??
8. Convolution Neural Network(CNN)
CNNs works by breaking an image down into smaller groups
of pixels called filters.
Each filters is a matrix of pixels and the network
does a series of calculation on these comparing
them against pixels in a specific pattern the network is looking for.
First layer of a CNN is able to detect pattern like rough edge
and curve
9. RECURRENT NEURAL NETWORK(RNN)
• Where CNN fails ,RNN comes in the picture because RNN deals with
dynamic image means videos.
• Feed large amount of data of millions of objects across
1000 of angle and properly defined.