Talk: A Girls Guide to Growing a Moustache

Speaker: Heidi Thorpe (Heidi)

Language: English (with English Slides)

Intermediate
Photo of Heidi Thorpe

About Speaker

Heidi graduated with Honors in Chemistry from the University of Leeds before taking up a position as an Industrial Chemist with ICI (ORICA). This led to a career in software development working in UK, Aus and USA.

In 2000 she became an author by the publication by Addison Wesley of Oracle8i tuning and administration: the essential reference ASIN: B007EIZGOG this was a sales success and translated into German. In her spare time she uses python to write software that allows her to train object classifiers to steal mens' mustaches and put them on the face of Taylor Swift.

About the Topic

The objective is to showcase the power and flexibility of combining preexisting python modules and apply them to the field of facial detection and machine learning. Correctly positioning a mustache on any given face in a straight forward and fun example of applying the technology in a 30 min presentation To use an elementary task as a vehicle for explaining and demonstrating the complexities of shape recognition, object classifiers and machine learning. I will demonstrate the use of image pyramids for image scaling and blending. The histogram of oriented gradients (HOG) is a feature descriptor used in computer vision and image processing for the purpose of object detection. Finding the location of different facial features (e.g. corners of the eyes, eyebrows, and the mouth, the tip of the nose etc.) accurately will be described. Facial landmarks are used to align facial images to a mean face shape. How this allows the blending of images will be described and demonstrated. If you are a girl and want a mustache, you can’t just grow one, so you have to steal one. I developed this project on raspberry pi and python. I wanted to do something different on that platform. I felt there were too many people who used their Rpi to feed their dog, water their plants or play MP3. I knew the platform had more potential than that. Hopefully this talk will help people think differently about Rpi3. Attendees will learn tips on image processing, as well as training your own object classifier. Showcasing the power of python in a fun, lighthearted way. Hopefully, being informative and entertaining.

Tags: Python, Machine Learning, Tswifty