Patent
Convolutional neural network feature extraction method based on principal component analysis
Tieyong Cao,Zheng Fang,Zhang Xiongwei,Zheng Yunfei,Yang Jibin,Sun Meng,Zhao Fei,Huang Hui +7 more
- 27 Mar 2018
4
TL;DR: In this article, a convolutional neural network feature extraction method based on principal component analysis (PCA) is proposed for image feature extraction, which can be used for various tasks of identification and classification of images.
read more
Abstract: The invention discloses a convolutional neural network feature extraction method based on principal component analysis The convolutional neural network feature extraction method based on principal component analysis includes the steps: selecting the convolutional neural network which has been trained on an Imagenet data set, taking the convolutional neural network as the feature extractor of an image, extracting the feature mapping graph from the output of each pooling layer of the convolutional neural network, taking all the extracted feature mapping graphs of each layer as the deep featuresof the image, utilizing principal component analysis to perform dimensionality reduction on the deep features, and utilizing bilinear interpolation to reset the final result feature mapping graph tothe original image size to obtain the efficient image deep features The deep features obtained through convolutional neural network feature extraction method based on principal component analysis have rich semantic information of the image, are low in the feature dimension and small in data size, and can be used for various tasks of identification and classification of images
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Improved high-resolution remote sensing image classification method based on deep learning
TL;DR: Wang et al. as mentioned in this paper proposed an improved high-resolution remote sensing image classification method based on deep learning, in which a seven-layer convolutional neural network is designed, and a high-res sensing image sample is inputted into the network to carry out network training and last two full connection layers obtained by learning are outputted as two different high-level features of the remote sensing images.
12
Patent
An image classification method based on bi-directional neural network structure
Wu Chuanying,Li Fanping,Shi Zhuguo +2 more
- 28 Dec 2018
TL;DR: In this article, the authors proposed an image classification method based on a bi-directional neural network structure, comprising the following steps: 1 The Directional layer replaces the full-connection layer in a traditional convolution network, 2 network forward propagation is performed, and by adding transformation matricesL and R, the rectangular structure of the last convolution layer is preserved, 3 steps 2, 3 are repeated, the Bi-DNN is fine-tuned until the classification network converges, 4 the class number of the image is obtained through forward propagation on the trained model
1
Patent
Image processing method and device, electronic device and storage medium
Wang Huanpeng,Wang Hongjun,Xiao Shibin +2 more
- 14 May 2019
TL;DR: The image characteristic gene coding method is fast and simple, can perform calculation by using relatively few calculation resources, and has excellent field applicability as discussed by the authors, but it requires a large number of calculation resources.
Patent
Comfort quality evaluation method and system of stereoscopic image based on convolution self-encoder
TL;DR: In this article, a method and a system for evaluating the quality of stereoscopic image comfort based on a convolutional self-encoder is proposed. But the method is limited to stereo images of left and right viewpoints.