Image processing (part 3) Image Thresholding
In this article (which is the 3rd episode of the image processing series) we will see how to use the image histograms we discussed in article 2 to do some basic editing.
All to understand and practice A.I. in a simple way
Image processing posts
In this article (which is the 3rd episode of the image processing series) we will see how to use the image histograms we discussed in article 2 to do some basic editing.
In the previous article we saw how our digital images were built and stored. This naturally brings us to the image histograms. Of course we don’t manage an image like we do for a text . Images are in fact just matrix (like a pixel map ), so first of all we need to analyse the image, and to do that we’ll take a look on the pixel histograms.
In this article we will see and especially understand how images are stored in a computer just to make it usable by other softwares. In fact, this post is the first within a series that will allow us to approach image processing in general but also subsequently the place of Artificial Intelligence and especially Deep Learning in this discipline which is part of a set known as computer vision.
In this article we will see how to automate image straightening with blue Prism and Python.
In this article I show you how in a few lines of Python code you can straighten a document that has for example been scanned crooked.
In this article we will see how we will be able to recover information (photo, and other information) from a scanned identity card. In this article we will use the OpenCV and tesseract libraries with Python.
Find out in this article how to use OpenCV to easily do facial recognition in a image.
In this post, I suggest you create a web service (RESTFul) in Python which will retrieve an image (JPEG) to analyze and process it in order to return the constituent elements.
In this second part on MNSIT data, we will see how to edit and prepare the data to reach 97%.