With the development of deep learning theory, the application of Yolov3 in fruit detection has been widely studied. Aiming at the problem that Yolov3 loses information during network transmission and the semantic feature extraction of small targets is not rich, this article proposed an improved Yolov3 cherry tomato detection algorithm. Firstly, the proposed algorithm uses dual path network as a feature extraction network to extract richer small target semantic features. Second, four feature layers with different scales are established for multiscale prediction. Finally, the improved K-means++ clustering algorithm is used to calculate the scale of anchor boxes.Experiments showed that the algorithm has a precision rate of 94.29%, a recall rate of 94.07%, and an F1 value of 94.18%. The F1 value is 1.54% higher than Faster R-CNN and 3.45% higher than Yolov3. It takes 58 ms on average to recognize an image, which provides a theoretical basis for the fruit detection.

No abstract

No abstract

The development of computer and information technology enables the in-depth application for human beings in the network and information application, and accordingly, more and more fields in human society are deeply associated with computer networks. The emergence of computer network enables human beings to obtain higher efficiency in information processing and transaction. However, computer network is endowed with virtuality, complexity and openness, which pose itself in internal and external security threats. At the same time, the speed of technological development is always faster than the updating and optimization of administrative regulations, which makes it difficult to guarantee cyber security in terms of legal basis. This paper discusses the legal basis of computer cyber security review with the hope to provide support for the relevant work and theoretical research of computer cyber security review.