Multi-label images classification based on convolutional neural network

被引：0

作者：

Chen M.-S. ^{[1
]}

Yu L.-L. ^{[1
]}

Su Y. ^{[1
]}

Sang A.-J. ^{[1
]}

Zhao Y. ^{[1
]}

机构：

[1] College of Communication Engineering, Jilin University, Changchun

来源：

Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) | 2020年 / 50卷 / 03期

关键词：

Artificial intelligence; Classification; Convolutional neural network; Multi-label;

D O I：

10.13229/j.cnki.jdxbgxb20190288

中图分类号：

学科分类号：

摘要：

In order to overcome the shortcoming of Binarized normed gradients (BING) algorithm in object modeling, a multi-BING algorithm is put forward. First, the Center-Symmetric Local Binary Pattern (CS-LBP) features of the training examples are calculated and clustering is performed. Then, different BING feature model is established based on different class of data. During the cause of object detection, all the results are emerged to find the candidates. The experiments show that the proposed method is significantly better than BING algorithm and Objectness (OBN) algorithm. In this, the problem of multi-label image classification is converted into the classification of many single-label images. Based on the Fast R-CNN model, the gained candidate box is taken as the input. At the same time, Leaky rectified linear unit (LReLU) function is considered as the activation function of the Fast R-CNN model. Thus, Average precision (AP) of the algorithm is promoted without more computing time cost and calculation overload. © 2020, Jilin University Press. All right reserved.

引用

页码：1077 / 1084

页数：7

共 13 条

[1] Wu F., Wang Z., Zhang Z., Et al., Weakly semi-supervised deep learning for multi-label image annotation, IEEE Transactions on Big Data, 1, 3, pp. 109-122, (2017)
[2] Mahapatra D., Roy P.K., Sedai S., Et al., Retinal image quality classification using saliency maps and CNNs, Machine Learning in Medical Imaging, 10, 4, pp. 172-179, (2016)
[3] Girshick R., Donahue J., Darrell T., Et al., Rich feature hierarchies for accurate object detection and semantic segmentation, IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
[4] He K., Zhang X., Ren S., Et al., Spatial pyramid pooling in deep convolutional networks for visual recognition, IEEE Transactions on Pattern Analysis & Machine Intelligence, 37, 9, pp. 1904-1916, (2015)
[5] Girshick R., Fast R-CNN, IEEE International Conference on Computer Vision, pp. 1440-1448, (2015)
[6] Mass A.L., Hannun A.Y., Ng A.Y., Rectifier nonlinearities improve neural network acoustic models
[7] Cheng M.M., Liu Y., Lin W.Y., Et al., BING: binarized normed gradients for objectness estimation at 300fps, Computer Vision and Pattern Recognition, 8, 4, pp. 3286-3293, (2014)
[8] Su Y., Chen M.-S., Sang A.-J., Et al., Objects detection based on multi-BING feature model, The 2nd International Conference on Information Technology and Intelligent Transportation Systems, pp. 212-221, (2017)
[9] Zhang S.-W., Zhang Q.-Q., Zhang Y.-L., Et al., Palmprint recognition by combining weighted adaptive CS-LBP and local discriminant projection, Application Research of Computers, 34, 11, pp. 3482-3485, (2017)
[10] Zhang Z.-Y., Zhou M.-Q., Shui W.-Y., Et al., Color transfer based on K-means clustering algorithm and region matching, Journal of System Simulation, 27, 10, pp. 2359-2364, (2015)

← 1 2 →