The good thing about doing research is that there is a possibility that you can come across a new technique/method everyday. Recently I have been working with a lot of information from different datasets and trying to extract the useful information content, which can be eventually used to describe the major trend in the dataset.
A major hurdle in this is to quantify that how much information is actually informative. One possible method which is widely used to achieve this is called Singular Value Decomposition (SVD). As this is a widely used technique, the details of this method can be easily found across the web. This blog post will visualize the content information and try to comprehend how much is required for computer vision applications. Here I am using one of the applications of SVD, which is to compress the content of an image. Although there exist better approaches to achieve this, the content used can be quantified easily using SVD.
Below is a sample grayscale image that I have used for this blog post. This is the original image, without any compression using SVD. Notice that there are a lot of regions in the image that look similar.
A major hurdle in this is to quantify that how much information is actually informative. One possible method which is widely used to achieve this is called Singular Value Decomposition (SVD). As this is a widely used technique, the details of this method can be easily found across the web. This blog post will visualize the content information and try to comprehend how much is required for computer vision applications. Here I am using one of the applications of SVD, which is to compress the content of an image. Although there exist better approaches to achieve this, the content used can be quantified easily using SVD.
Below is a sample grayscale image that I have used for this blog post. This is the original image, without any compression using SVD. Notice that there are a lot of regions in the image that look similar.
