基于神经网络的运动视频图像分类和识别研究

Research on motion video image classification and recognition based on neural network

当前运动视频的图像分类和识别方法存在图像识别率低、识别不清晰图像较难的问题,为解决上述问题,文中提出基于神经网络的运动视频图像分类和识别研究。采用目标轮廓周长平方比轮廓面积的方法,提取运动目标图像特征,通过提取图像特征结果设计图像分类流程,建立神经网络图像分类模型完成图像识别。针对同一元素的不同角度进行拍摄获取,采用误差反向传播算法完成神经网络下的运动视频图像分类和识别。通过仿真实验验证设计方法的性能,实验结果表明,所提方法对运动视频图像的识别率较高,正确率在98%以上,且图像识别分类较全面。所提方法能够对运动视频图像中的元素进行分类,识别不清晰图像,提高了识别的精准度,为实际应用提供了一定的参考。

At present,there are some problems in the image classification and recognition of motion video,such as low recognition rate and unclear image.In order to solve the above problems,the research on motion video image classification and recognition based on neural network is proposed in this paper.The method of ratio between target contour perimeter square and contour area is used to extract the moving object image features.The image classification process is designed according to the extracted image features.The image classification model is established on the basis of neural network to complete the image recognition.A same element is photographed in different angles.The error back propagation algorithm is used to complete the classification and classification of moving video images by means of the neural network.The performance of the designed method is verified by simulation experiments.The experimental results show that the proposed method has a high recognition rate for moving video images,its correct rate is more than 98%,and the image recognition classification is more comprehensive.The proposed method can classify the elements in the motion video image,recognize the unclear images,improve the accuracy of recognition,and provide a certain reference for practical application.