In one session around computer vision, someone ask the question about which approach is better
Haar Cascades or DNN?
And the answer can be show using the video below
As you can see Haar Cascades works great for faces looking directly to the camera, with good lights and in optimal conditions. However, once my face stop looking at the camera, HC stop detecting faces; and the custom DNN model still working.
But, and this is important, the DNN model will rely only on the set of faces that has been used for training. If the model doesn’t include any demographics, in example Asian friends, the model won’t work with Asian subjects.
At the end, DNN models usually works great than Haar Cascades, however it’s really important to know the limitations of each model.
- OpenCVSharp, https://github.com/shimat/opencvsharp
- Wikipedia, Canny Edge Detector
- OpenCV, Canny tutorial
- OpenCV, FAST tutorial
- Wikipedia, FAST
- OpenCV, Perform face detection using Haar Cascades
Net 5 and OpenCV
- 13 lines to display a 🎦 camera feed with OpenCV and Net5
- Detecting edges on the 🎦 camera feed with Canny algorithm, OpenCV and Net5
- Detecting corners on the 🎦 camera feed with FAST algorithm, OpenCV and Net 5
- Display the 🎦 camera feed in a WinForm using OpenCV and Net5
- Face Detection using Face Cascades on the 🎦 camera feed using OpenCV and Net 5
- Face Detection using DNN on the 🎦 camera feed using OpenCV and Net 5
- Face Detection, DNN vs Haar Cascades on the 🎦 camera feed using OpenCV and Net 5
- Age and Gender estimation on the 🎦 camera feed using OpenCV and Net 5
- Caffe Model Zoo (GoogleNet) detection from the 🎦 camera feed using OpenCV and Net5
- Pose detection from the 🎦 camera feed using OpenCV and Net5
- Packaging a WinForm OpenCV and Net5 App in a one-self contained file
- (Coming Soon) QR Codes detection on the 🎦 camera feed using OpenCV and Net 5