Abstract
Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN) as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.
Highlights
Objects classification is one of the most essential problems in computer vision
For improving the biological advantages of our computer automatic classification method, we combine the 3 dimension high-level features used in our visual attention model, including people, faces, and cars, with 648 dimension local features gained by our Convolutional neural network (CNN) network to classify objects
The present paper has introduced a new classification method which combines learning-based visual saliency model and CNN
Summary
Objects classification is one of the most essential problems in computer vision. It is the basis of many other complex vision problems, such as segmentation, tracking, and action analysis. If computer can mimic the ability of humans, computer automatic classification technology will be improved greatly To achieve this assumption, we combine simulation of human visual information processing mechanism and simulation of human neutral network (Figure 2). To simulate human visual information processing mechanism when they were asked to classify different objects, we used EDOC database as training and testing examples to learn a learning-based visual attention model based on low-level and high-level image features and analyzed and predicted the humans’ classification RoIs. seeing that the CNN is inspired by biological processes and has remarkable advantages, we established a CNN framework to simulate the human brain’s processing of classification. For improving the biological advantages of our computer automatic classification method, we combine the high-level features used in our visual attention model with local features gained by our CNN network to classify objects by SVM. All experimental results showed that our method made the efficiency of classification improve significantly
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
