Ship detection in navigation based on broad learning system
Hui Su, Yi Zuo, Tieshan Li · 2021 International Conference on Security, Pattern Analysis, and Cybernetics（SPAC) · 2021
Based on the broad learning system(BLS), this paper carries out the detection of ships in navigation. Firstly, grayscale, and histogram equalization are used to preprocess the image to enhance the detail of the image and improve the training accuracy. Secondly, randomly select a part of the photo set as the test set. Finally, BLS is introduced to train and test the data set. Two training methods, back propagation neural network(BPNN) and support vector machine (SVM), are used to compare the proposed method with the navigation ship data set. From the experimental results, it can be seen that the BLS in this paper has a better detection effect in ship detection. By applying the comparison on the face detection data set, the universality of BLS for image recognition is proved.