13.4 azface detect many faces

20210406

Here’s a photo with quite a few more faces. The model will output a line for each and every face that it finds. We don’t include them all here but there are quite a few listed.

$ ml detect azface https://bit.ly/3sYTz2F

591 846 591 969 714 969 7...,27.0,female,no glasses,happiness,no occlusion
892 655 892 777 1014 777 ...,65.0,male,no glasses,happiness,no occlusion
686 539 686 660 807 660 8...,38.0,male,no glasses,happiness,no occlusion

1635 745 1635 865 1755 86...,25.0,female,no glasses,happiness,forehead_occluded
1065 505 1065 625 1185 62...,60.0,male,no glasses,happiness,no occlusion
1182 675 1182 795 1302 79...,28.0,female,no glasses,happiness,no occlusion
359 672 359 791 478 791 4...,29.0,female,no glasses,happiness,forehead_occluded

1420 797 1420 915 1538 91...,50.0,female,no glasses,happiness,forehead_occluded
1690 504 1690 621 1807 62...,34.0,male,readingGlasses,happiness,no occlusion
1378 569 1378 675 1484 67...,35.0,female,no glasses,happiness,no occlusion

731 162 731 243 812 243 8...,33.0,female,no glasses,neutral,no occlusion

1474 153 1474 228 1549 22...,30.0,female,no glasses,happiness,mouth_occluded

Notice the occlusion column includes forehead_occluded and mouth_occluded. We make use of that in Section 13.7 where we identify those people who are possibly wearing hats.

Can you also see the entry that has identified reading classes? Notice that the x coordinates for that entry are large numbers, probably corresponding to the person in the photo on the far right.



Your donation will support ongoing availability and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2022 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0