Clothing Recognition Based on Improved ResNet18 Model

At present, there are many researches on image classification and recognition, among which clothing recognition has more important application and research value in life. Image classification generally adopts convolutional neural network training and recognition. Convolutional neural network has better recognition performance, which is better than traditional machine learning algorithm and BP neural network. Convolutional neural network has various network models such as LeNet, AlexNet, VGG and ResNet. This paper takes clothing pictures as objects and proposes a clothing recognition method based on the improved ResNet18 model. The improved ResNet18 through experiments has an accuracy of 94.78% in identifying clothing, which is 1.01 percentage points higher than the original ResNet18 model, and is also higher than the accuracy of VGG and AlexNet, which can be well qualified for clothing recognition tasks.