Great Tech Reads

Learning a brand new concept like computer vision made me want to gather plenty of resources that could be useful up until my thesis is complete. When I return to school, I will need to write out some MATLAB code that is the most useful for taking non-intrusive measurements during falls prevention tests. Based on the above information, here is what I have in store:

Source 1: The Image Processing Handbook, 7th Edition (2016)

Chapter 7 of the above book describes a variety of methods in segmentation and thresholding. To clarify, segmentation is the problem of dividing a data set into parts according to a given set of rules. We assume that different segments correspond to different structures in the original input domain observed in the image.

Wrap Up Post 1 Figure 1. Example of segmentation, which shows the dividing of objects into parts in the whole image

Thresholding, on the other hand, is simply the processing of color or grayscale images into pure black and white (binary), particularly the sorting of pixels according to maximum threshold value applied to that image.

Wrap Up Post 1BFigure 2. Example of thresholding

The ideas for Chapter 7 were largely emphasized in my group talks in Small Hall, and thresholding appears to help me detect the most important aspects of Williamsburg Landing videos. For instance, my advisor and I worked to fully detect the black circles on the patient so we can extract information from them and make conclusions about the measurements we will make during the next two semesters. I will provide the videos in future posts so you can see what I mean.

Source 2: Image Processing and Acquisition using Python (2014)

This book is focused on my summer work with Python to analyze images and videos. Because Python is an easy-to-understand, object-oriented programming language, this book above is able to provide the fundamentals of image processing and acquisition. If I have found this book, I would have conducted my experiments more effectively in order to produce more accurate data. Such chapters include Fourier transform, image enhancement, and electron microscopes.

Source 3: Dictionary of Computer Vision and Image Processing (2005)

This dictionary is very helpful for defining unfamiliar computer science terms. Developments in image analysis are growing popular overtime, and the scientists in this and other fields should be able to navigate the latest terminology and technical concepts that come with image data. Key terms with a small portion containing illustrations can help guide readers, including computer-vision practitioners, through new terms in a comprehensive and credible reference.

Other Cool Reads

  • Digital Image Processing for Medical Applications (2009)
  • 2-D and 3-D Image Registration (2005)
  • Computer Vision Beyond the Visible Spectrum (2005)
  • Introduction to Digital Image Processing with MATLAB (2004)
  • Digital Signal Processing using MATLAB for Students and Researchers (2011)
  • Discrete Fourier Analysis and Wavelets: Applications to Signal and Image Processing (2009)

The above list seems to represent a lot of reading and skimming to do throughout the year. Even if I am not an avid reader, I should expect to make every effort to understand the jargon and surround my thesis with shorter but more significant readings. Catch you later in the next post!

Speak Your Mind