Age prediction by Facial Features recognition using Yolo v4 Test phase, srs, design phase and source code final deliverable
Order Image Processing
Abstract/ Preface
YOLO is an algorithm that uses neural networks to give real- time object discovery. This algorithm is popular because of its speed and delicacy. It has been used in colorful operations to descry business signals, people, parking measures, and creatures. We’ll use yolo algorithm to prognosticate age of persons grounded on different facial features.
The first step will be to label the images, for this purpose we can use different available tools like LabelImg. Also we will setup terrain and train our model and prognosticate the age group.
Functional Conditions
• First step is to elect 500 images for each age group from the dataset total 7000 images, you can also elect images from different datasets and induce a combined dataset. • Following 14 age groups ( classes) must be manually generated
1-5 6-10 11-15
16-20 21-25 26-30
31-35 36-40 41-45
46-50 51-55 56-60
61-65 66-70
• You can write script to automatically copy the images to separate brochure so the images can be fluently annotated.
• Coming step is to annotate the images according to the different age groups in yolo format using LabelImg.
• Once the dataset is annotated yolo terrain will be set and model must be trained.
• You can set terrain on your own machine or use google coolab.
• Model must be retrained if asked delicacy isn’t achieved by enhancing dataset or changing training parameters. Tools
• Python
• jupyter tablet
• Yolo
DataSet
http//mmlab.ie.cuhk.edu.hk/ systems/ MegaAge/