当前位置: X-MOL 学术Pattern Recognit. Image Anal. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Investigation of Methods for Increasing the Efficiency of Convolutional Neural Networks in Identifying Tennis Players
Pattern Recognition and Image Analysis ( IF 0.7 ) Pub Date : 2021-09-21 , DOI: 10.1134/s1054661821030032
N. A. Andriyanov 1, 2 , V. E. Dementev 2 , K. K. Vasiliev 2 , A. G. Tashlinskii 2
Affiliation  

Abstract

The article is devoted to the study of the effectiveness of the convolutional neural networks (CNNs) application for solving the problem of tennis players face recognition. For ease of analysis, two players were selected: Roger Federer (Switzerland) and Rafael Nadal (Spain). To isolate faces from the publicly available images of the players, it is proposed to use the Haar cascades and the Viola–Jones method. These images are used to train and test convolutional networks with various parameters: architecture, including the number of layers; epochs of learning; optimization methods; and also when applying various regularization methods, including drop out and data augmentation. The use of regularization made it possible to reduce the effect of overfitting. In addition, the efficiency of networks with pretrained layers based on transfer learning methods is investigated. The VGG-16 convolutional network is chosen for the transfer learning. For a large number of different combinations of convolutional networks, metrics are calculated for precision, recall, and accuracy. The average gain for these parameters is 25% with the best set of characteristics for convolutional networks and training. It is also shown in the study that the patterns of applying certain modifications are universal for optical images. In particular, similar architectures and training approaches are also tested for the problem of recognizing cats and dogs on a much larger dataset. The study confirms the average increase in recognition metrics of 26%.



中文翻译:

提高卷积神经网络识别网球运动员效率的方法研究

摘要

本文致力于研究卷积神经网络 (CNN) 应用在解决网球运动员人脸识别问题方面的有效性。为了便于分析,选择了两名球员:罗杰·费德勒(瑞士)和拉斐尔·纳达尔(西班牙)。为了从公开的球员图像中分离出人脸,建议使用 Haar 级联和 Viola-Jones 方法。这些图像用于训练和测试具有各种参数的卷积网络:架构,包括层数;学习的时代;优化方法;以及应用各种正则化方法时,包括退出和数据增强。正则化的使用使得减少过拟合的影响成为可能。此外,研究了基于迁移学习方法的具有预训练层的网络的效率。选择 VGG-16 卷积网络进行迁移学习。对于卷积网络的大量不同组合,计算精度、召回率和准确度的指标。这些参数的平均增益为 25%,具有卷积网络和训练的最佳特征集。研究还表明,应用某些修改的模式对于光学图像是通用的。特别是,类似的架构和训练方法也针对在更大的数据集上识别猫和狗的问题进行了测试。该研究证实,识别指标平均提高了 26%。对于卷积网络的大量不同组合,计算精度、召回率和准确度的指标。这些参数的平均增益为 25%,具有卷积网络和训练的最佳特征集。研究还表明,应用某些修改的模式对于光学图像是通用的。特别是,类似的架构和训练方法也针对在更大的数据集上识别猫和狗的问题进行了测试。该研究证实,识别指标平均提高了 26%。对于卷积网络的大量不同组合,计算精度、召回率和准确度的指标。这些参数的平均增益为 25%,具有卷积网络和训练的最佳特征集。研究还表明,应用某些修改的模式对于光学图像是通用的。特别是,类似的架构和训练方法也针对在更大的数据集上识别猫和狗的问题进行了测试。该研究证实,识别指标平均提高了 26%。研究还表明,应用某些修改的模式对于光学图像是通用的。特别是,类似的架构和训练方法也针对在更大的数据集上识别猫和狗的问题进行了测试。该研究证实,识别指标平均提高了 26%。研究还表明,应用某些修改的模式对于光学图像是通用的。特别是,类似的架构和训练方法也针对在更大的数据集上识别猫和狗的问题进行了测试。该研究证实,识别指标平均提高了 26%。

更新日期:2021-09-21
down
wechat
bug