计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2014年
24期
173-177
,共5页
王勇%赵俭辉%章登义%叶威
王勇%趙儉輝%章登義%葉威
왕용%조검휘%장등의%협위
稀疏自编码%无监督学习%卷积与池化%softmax回归
稀疏自編碼%無鑑督學習%捲積與池化%softmax迴歸
희소자편마%무감독학습%권적여지화%softmax회귀
sparse autoencoder%unsupervised learning%convolve and pooling%softmax regression
针对林火与相似目标很难区分的问题,提出一种基于稀疏自编码深度神经网络的林火图像分类新方法。采用无监督的特征学习算法稀疏自编码从无标签图像小块中学习特征参数,完成深度神经网络的训练;利用学习到的特征从原始大小分类图像中提取特征并卷积和均值池化特征;对卷积和池化后的特征采用softmax回归来训练最终softmax分类器。实验结果表明,跟传统的BP神经网络相比,新方法能够更有效区分林火与红旗、红叶等类似物体。
針對林火與相似目標很難區分的問題,提齣一種基于稀疏自編碼深度神經網絡的林火圖像分類新方法。採用無鑑督的特徵學習算法稀疏自編碼從無標籤圖像小塊中學習特徵參數,完成深度神經網絡的訓練;利用學習到的特徵從原始大小分類圖像中提取特徵併捲積和均值池化特徵;對捲積和池化後的特徵採用softmax迴歸來訓練最終softmax分類器。實驗結果錶明,跟傳統的BP神經網絡相比,新方法能夠更有效區分林火與紅旂、紅葉等類似物體。
침대림화여상사목표흔난구분적문제,제출일충기우희소자편마심도신경망락적림화도상분류신방법。채용무감독적특정학습산법희소자편마종무표첨도상소괴중학습특정삼수,완성심도신경망락적훈련;이용학습도적특정종원시대소분류도상중제취특정병권적화균치지화특정;대권적화지화후적특정채용softmax회귀래훈련최종softmax분류기。실험결과표명,근전통적BP신경망락상비,신방법능구경유효구분림화여홍기、홍협등유사물체。
With the problem that forest fire and its similar objects are difficult to distinguish, this paper presents a new forest fire image classification approach based on deep neural network of sparse autoencoder. Using an unsupervised learning algorithm sparse autoencoder to learn features of large number of small patches from some unlabeled images has completed the training for deep neural network, and then with the learned features, the features can be extracted from large scale images and be convolved and pooled. It uses pooled features to train the softmax classifier by softmax regression. Experimental results show that this new image classification approach can more effectively distinguish forest fire and its similar objects, red flag, red leaves, etc. than traditional neural network does.