Feifei Wang, Yutong Zhang
Emotion Classification of Cartoon Characters of different style (anime vs. 3D cartoon)
- Transfer learning and fine-tuning
- Compare the accuracy of different pretrained models & baseline CNNs
- Few studies explored this subject before => improve image search result quality
- Understand how neural networks differentiate emotions of fictional figures, whose characteristics vary dramatically between artists
- Animated faces have different characteristics from real human faces
- The cartoon facial emotion datasets are limited, with small sizes that is susceptible to overfitting
55767 annotated face images of 6 characters
{'angry': 0,
'crying': 1,
'embarrassed': 2,
'happy': 3,
'pleased': 4,
'sad': 5,
'shock': 6 }
{'anger': 0,
'disgust': 1,
'fear': 2,
'joy': 3,
'neutral': 4,
'sadness': 5,
'surprise': 6 }
all in .ipynb, separated by models and datasets
- trained-from-scratch CNN (作为baseline model,其他的accuracy可以和它compare)
- GoogleNet
- ResNet50
- Use
’val_categorical_accuracy’
to evaluate accuracy - Overall top 3 performance:
- L2 Regularization
- baseline + Batch Norm + 2 Dense 64 Layer
- baseline
- When the dataset is small
- Changing the structure of the model is able to increase the accuracy and control overfitting, with mild effect on runtime
- When the dataset is large:
- GoogleNet is faster the baseline