基于卷积神经网络的图像识别研究

Research on Image Recognition Based on Convolutional Neural Network

为提高图像识别的准确率,提出了一种基于卷积神经网络的图像识别模型.本实验使用Python编程语言实现模型的训练与测试.对图像数据集cifar-10进行预处理后,使用Python中的Keras框架进行模型的构建与训练,模型训练完毕后,对识别准确率进行评估,最后对测试集中的图片进行识别,获得预测准确率和混淆矩阵.通过增加卷积运算的次数,提高图像识别的准确率.

Inorder to improve the accuracy of imagere cognition,an image recognition model Based on convolutional neural network is proposed.Model training and testing is achieved by using the Python programming language.After preprocessing the image dataset ci far-10,the Keras framework in Python is used to construct and train the model.After the model is trained,We need to evaluate the accu racy of the model predictions.Finally identify the pictures in the test set,and get the prediction accuracy and confusion matrix.By in creasing the number of convolution operations,the accuracy of image recognition can beimproved.