The high requirements for computing and memory are the biggest challenges in deploying existing object detection networks to embedded devices. Living lightweight object detectors directly use lightweight neural network architectures such as MobileNet or ShuffleNet pre-trained on large-scale classification datasets, which results in poor network structure flexibility and is not suitable for some specific scenarios. In this paper, we propose a lightweight object detection network Single-Shot MultiBox Detector (SSD)7-Feature Fusion and Attention Mechanism (FFAM), which saves storage space and reduces the amount of calculation by reducing the number of convolutional layers. We offer a novel Feature Fusion and Attention Mechanism (FFAM) method to improve detection accuracy. Firstly, the FFAM method fuses high-level semantic information-rich feature maps with low-level feature maps to improve small objects’ detection accuracy. The lightweight attention mechanism cascaded by channels and spatial attention modules is employed to enhance the target’s contextual information and guide the network to focus on its easy-to-recognize features. The SSD7-FFAM achieves 83.7% mean Average Precision (mAP), 1.66 MB parameters, and 0.033 s average running time on the NWPU VHR-10 dataset. The results indicate that the proposed SSD7-FFAM is more suitable for deployment to embedded devices for real-time object detection.

Verification code is a human-machine test method that is widely used in the Internet. It can essentially distinguish between human and network robots. However, with the development of technology, more and more problems has been found in the verification code. This paper takes the digital verification codes commonly used in university student management system as the research object. The verification code after scaling and graying is used as the data set. The eight-layer ALexNet convolutional neural network is constructed by using the Google deep learning framework TensorFlow to train the verification code. The data set is tested to obtain a network model that can identify different complexity digital verification codes. The recognition rate of digital verification codes commonly used in college student management systems can reach 99%.