Computer Vision Essentials

You will learn and understand edge detection and sharpening in the sampling technique of Computer Vision with example to represent an image in this section. 

This section explains the process and method of filtering with a demonstrated example. In this chapter, you will understand the filtering process in Computer vision. 

In this chapter, you will understand basic terminologies and techniques and the working of Computer Vision with demonstrated code with a greyscale image sample. 

This module discusses CNN in-depth. You will be introduced to a convolutional neural network and convolutional operations, thoroughly understand its mechanism, and go through ReLu and Max pooling with examples.
 

This chapter explains the importance of CNN with demonstrated examples.

This chapter begins by introducing you to the padding concept in Computer Vision, explains the padding process, and then continues with pooling, layers and max, ven pooling, and filtering concepts with examples. 

The chapter begins by explaining the architecture of CNN using LeNet-5. It explains the fully connected layer, the math, functions, and processes throughout CNN's different layers. 

This chapter, to begin with, explains the HDF format and then discusses the formation of convolution layers and fully connected neural layers. 

In this chapter, you will learn and understand the transfer learning concept by understanding the difference between traditional machine learning and transfer learning. 

This chapter explains the problem statement to work on Computer Vision. You will understand the process and requirements to theoretically and mathematically solve the problem. 

 You will learn and understand the Keras programming part to train and classify the dataset in this chapter.