Python face_recognition 为什么不能识别卡通图像？

Question

I am trying to face recognise by python Face-recognition library

I have tried below code for below image

Code:

import face_recognition

image = face_recognition.load_image_file("img/bill.jpeg")
property(image)
face_locations = face_recognition.face_locations(image)

print(len(face_locations))

For below image I am getting output for total face: 6

Image:

But When I am trying by a cartoon image

I am getting output: 0

How can I recognise cartoon face by face-recognition?

Answer 1

Sorry to say but if the face recognition is good it should not recognize cartoon faces, it's designed to recognize human faces and therefore should only tell you how many human faces it is on the image, otherwise it's a bad designed algorithm. If you want a machine-learning algorithm to recognize cartoon faces you would have to train it your self for that specific test.

I did a quick search on google and the first things I found was an article named "Cartoon Face Recognition: A Benchmark Dataset" at https://arxiv.org/pdf/1907.13394.pdf . Maybe you can find an already existing machine-learning algorithm that have been trained to recognize cartoon faces.

Hope this helped and I hope you find what you're looking for.

--------------------------------EDIT--------------------------------

I found these two git repositories, could be worth looking into more

https://github.com/srvCodes/Cartoon-Face-Detection-and-Recognition https://github.com/hako/dissertation

The last link is a link for emotions of cartoon character.

Answer 2

Short answer: You need to train a new model to detect cartoon characters.

Long explanation:

• Because cartoon characters have different facial features from normal human faces. For cartoons, the face edges are smooth, perfectly round eyes, smooth-shaped mouth, and cartoonish face structure.
• The pre-trained model that you are using doesn't know to identify these structures, it hasn't seen such images during training.
• A model detects a face using a lot of filters, these filters could detect lines and shapes in an image. If all these filters combine and give a high output, then there is a face in that location.
• So, you either have to look for models that are trained on cartoons, or label and train a model by your self.