{"id":10952,"date":"2019-08-30T09:00:51","date_gmt":"2019-08-30T13:00:51","guid":{"rendered":"https:\/\/blogs.mathworks.com\/pick\/?p=10952"},"modified":"2019-08-29T23:09:07","modified_gmt":"2019-08-30T03:09:07","slug":"how-old-do-i-look","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/pick\/2019\/08\/30\/how-old-do-i-look\/","title":{"rendered":"How Old Do I Look?"},"content":{"rendered":"
<\/p>\n

Brett<\/a>‘s Pick this week is Age and Gender Estimation from Face<\/tt><\/a>, by Masayuki Tanaka<\/a>.<\/p>\n

<\/p>\n

Back in 2014, I “co-selected” one of Masayuki’s files<\/a> as a Pick of the Week when I was looking for ways to quantify blur–I was (rightly) taken to task for calling it “noise”– in single images. Today, I return to his oeuvre to highlight a fun new submission that estimates age and gender from a photo.<\/p>\n

Downloading and installing Masayuki’s code will lead you to another of his submissions<\/a> that detects face parts–eyes, nose, mouth–in images. (That code primarily modifies the defaults of the “face-parts detector” in vision.CascadeObjectDetector<\/a>, purportedly with better results.) Then his code will automatically install a pre-trained vgg-based<\/a> neural network that does the classification (gender) and regression (age).<\/p>\n

I really like that Masayuki provided sample code for training a network, even though he provided pre-trained models. And I like that his code predicts both age and<\/i> gender. But mostly I just like how much fun I had playing around with it!<\/p>\n

Here I was a few years ago; the age-gender predictor got it pretty right:<\/p>\n

\"\" <\/p>\n

Apparently, I look a year older if I flip the image left-to-right:<\/p>\n

\"\" <\/p>\n

Try it on some of your own images–it’s fun! Just be sure to shield it from your partner if it turns out to predict that she is a he, and that “he” is a few years older than she really is!<\/p>\n

Oh, and you’ll need the Deep Learning Toolbox<\/a> to run Masayuki’s code.<\/p>\n

As always, I welcome your thoughts and comments<\/a>.<\/p>\n