A survey: Comparison between Convolutional Neural Network and YOLO in image identification
Richeng Cheng
Abstract
Abstract The main purpose of this paper is discussing Convolutional Neural Network (CNN) family and You Only Look Once (YOLO) family, comparing with the structure of the frame, speed of calculating and efficiency of identifying objects. There are two main summaries. The first summary is that training Faster Region-based Convolutional Neural Networks (Faster R-CNN) can achieve excellent detection effect, which not only reduces the time cost but also improves the quality of the proposal. Therefore, the method of alternating training Region Proposal Network (RPN) + Faster R-CNN in the Faster R-CNN is more advanced than the original SlectiveSeach + Faster R-CNN. Another summary is that YOLO is a convolutional neural network that supports end-to-end training and testing and can detect and recognize multiple targets in images with certain accuracy.