Computer Vision – Patrick Buhagiar

This weekend I had the opportunity to attend yet another hackathon. This is my second MLH hackathon, with the previous one being Great Uni Hack 2017 in Manchester. Unlike at GUH however, I aimed to build something of value and challenge myself.

I was nervous at first, particularly because I was going alone and had no team. Fortunately, I met two other like-minded students and we immediately got along. Interestingly, we were all coming from different backgrounds and universities. One came from a computer engineering background, the other was more into high performance computing while I was coming from a service oriented/full stack development background. Nonetheless, we managed to work well as a team.

Continue reading “Hack Cambridge 2018” →

There have been many implementations in recent years for identifying the human form within a given photo frame, however one particular method stands out called Histograms of Oriented Gradient (HOG) descriptors. Given a training set, the HOG algorithm is capable of eliminating information irrelevant to human detection. The human form can be shown in many different poses, perspective, ambient lighting and backgrounds, however one of the most important characteristics that is common to all are edges and corners. The edge and gradient structure information is defined locally in small regions. The HOG technique consists of counting occurrences of gradient directions in localized cells (or pixel matrices). We then normalize these local histograms. It is suggested that the human form can be represented by using the distribution of local intensity gradients.

For my MATLAB implementation, check out my Github.

Implementation

The person identification system can be divided into two main functions which are:

TrainHOG – will compute the necessary weights from training data.
PredictHOG – will use the previously mentioned weights for predicting whether input images are human or not.

Continue reading “Person Identification” →