-
Notifications
You must be signed in to change notification settings - Fork 208
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
FaceRecognizer demo for Java #195
Comments
What is your problem? |
1 similar comment
What is your problem? |
No problem. |
Is this demo working well? |
1 similar comment
Is this demo working well? |
very good |
You are welcome to submit this java demo to our repo. If you plan to do so, please, use English for comments. |
1 similar comment
You are welcome to submit this java demo to our repo. If you plan to do so, please, use English for comments. |
ok |
Hello, I've tried this demo. The faceRecognizer works well, but the faceDetector is not working for me. When I run 'faceDetector.detect(imgA, faceA)', I'cant get the face.(The result is a (-1,-1)). I promise my image contains face. I use the same image and change another face detect method, i.e.,cascadeClassifier. I get the right face. The faceDetector is loaded successfully. The model for faceDetector is downloaded from the original repository. |
Please ensure:
|
hello ,I use your code in my android project.
|
@weeleng Try a different size but larger than 240x240. |
@12341234-yangboran Excellent work! It works. I find that this model identifies body parts, such as ears and hands of all things, for some reason, even if you set the threshold to 0.9f. In that sense the "regular" DNN detectors are still very good. I found another goldmine of examples for this here. Update: Much better results with reasonably-sized images, somewhere around 600 - which probably makes sense as that's a common training set image dimension. With LARGE portraits, the model goes off the rails. |
The text was updated successfully, but these errors were encountered: