Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network

Figure 10

The whole processing of comparing the classification results when using humans’ classification RoIs as input of classification and when using original images as input of classification. Different from traditional classification method using original images for classification, our classification method uses humans’ classification RoIs as input of classification. After extracting features by CNN, we use SVM model to classify objects and then use the error rate of classification and convergence rate as evaluation criterion.