Face Detection Using OpenCV with CUDA GPU Acceleration | Images, Videos

Face detection using Python OpenCV in images and videos with speedup using CUDA GPU acceleration. Face detection is the first step to implement a face recognition system. In this quick tutorial, I explain step by step how to detect faces in images and videos using OpenCV, which might come in handy for a face recognition system or facial expression recognition system. I am using Python 3.8 on Windows 10. You can use it on Linux as well. However, the CUDA Acceleration while detecting faces on videos requires building OpenCV from the source.

*Code is available for our Patreon supporters*
---------------------------------------------
► Time Stamps:
Introduction: (0:00)
Face Detection on Images: (0:18)
Face Detection on Videos: (5:42)
Enabling CUDA Acceleration: (5:58)

---------------------------------------------
Want to discuss more?

#TheCodingBug
#FaceDetection
#OpenCV
---------------------------------------------
► My Other Tutorials:
---------------------------------------------
---------------------------------------------
DISCLAIMER: Links included in this description might be affiliate links. If you purchase a product or service with the links that I provide I may receive a small commission. There is no additional charge to you!

[TheCodingBug]

► My Other Tutorials:
Build and Install OpenCV 4.5.1 With CUDA GPU Support on Windows 10

YOLOv4 On Android Using TFLite

Custom YOLOv4 Object Detection with TensorFlow and TFLite

Darknet YOLOv4 Custom Object Detection: Part 2 (Training YOLOv4 Darknet)

Darknet YOLOv4 Custom Object Detection: Part 1 (Preparing Custom Dataset)

YOLOv4 Object Detection with TensorFlow, TFLite and TensorRT

Darknet YOLOv4 Object Detection for Windows 10 on Images, Videos, and Webcams

Real Time Object Detection on Webcam and Videos Using OpenCV With YOLOv3 and YOLOv4 | Windows Linux

Build and Install OpenCV 4.4.0 with CUDA (GPU) Support on Windows 10

Install TensorFlow GPU and PyTorch with CUDA on Windows 10 Anaconda | CUDA 10.1 cuDNN 7.6

Real-time Multiple Object Tracking with YOLOv4 TensorFlow and Deep Sort | Linux, Windows

[jorgeluv]

This is so great. Your quick and very well explained tutorial is great.Thanks. i used your Class and expanded it to motorize the camera, so i chase the detection on a Jetson Nano 2gb. Any good tutorial for face Recognition Cuda acelerated?

[kushalkumarrajak]

I am trying this same at my ubuntu system but not able to build opencv for cuda can you please help....

[stevesmith-byyi]

I have made a face recognition module in python. Now I want to use nvidia GPU GTX 1070. I have made a virtual env in anaconda with tensorflow, cuda and cudnn installed in it. Can I run my same code from anaconda or do I need to add some cuda code in it to enable training on gpu?

[taqikhan]

Please make video on face recognition also. Thanks

[anto__]

Hi!! does it work just with faces or with other objects? (cars, bycicles, etc)... Thanks, great tutorial!!

[nghiadaihiep]

hello help me
AttributeError: 'detector' object has no attribute 'faceModel'

[amadeus]

It worked fine with a video-file, but not when I tested with my webcam. I got lower fps with GPU than CPU.
CPU = 29fps, GPU = 25fps
Could it be my graphics card? GTX970?

Hi dear. Is possible make operations like segmentation, apply filters or any other technique of image processing but using the GPU? is possible it? I want to accelerate this process, is possible it or only this techniques are doing by using the CPU?. Thanks so much.

[pizzalover]

does this need setup such as configuring your project with cmake?

[germancruz]

Has anyone compiled opencv for Geforce RTX 4000 generation GPUs?