Leaf Classification Methods Based on SVM and SIFT

Ye, Yida

doi:10.1007/978-3-642-38466-0_38

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To identify models of mobile phones in images, a great number of methods have been studied [12,13]. The processes of mainstream methods are generally as follows: (i) artificially designed feature extraction methods such as scaleinvariant feature transform (SIFT) [14], local binary pattern (LBP) [15] and histogram of oriented gradient (HOG) [16] are used to extract the input images into a set of feature vectors; (ii) the model is then trained by using the feature vectors and classifiers, such as support vector machines (SVM) [17], adaboost [18] and random forest [19]. However, in mobile phone recognition tasks, the differences between different image categories are often subtle, and therefore, it is still a rather challenging task to extract sufficient information with the above methods.…”

Section: Introductionmentioning

confidence: 99%

Mobile phone recognition method based on bilinear convolutional neural network

Han

Zhang

Yang

et al. 2021

Sci. China Technol. Sci.

View full text Add to dashboard Cite

Model recognition of second-hand mobile phones has been considered as an essential process to improve the efficiency of phone recycling. However, due to the diversity of mobile phone appearances, it is difficult to realize accurate recognition. To solve this problem, a mobile phone recognition method based on bilinear-convolutional neural network (B-CNN) is proposed in this paper. First, a feature extraction model, based on B-CNN, is designed to adaptively extract local features from the images of secondhand mobile phones. Second, a joint loss function, constructed by center distance and softmax, is developed to reduce the interclass feature distance during the training process. Third, a parameter downscaling method, derived from the kernel discriminant analysis algorithm, is introduced to eliminate redundant features in B-CNN. Finally, the experimental results demonstrate that the B-CNN method can achieve higher accuracy than some existing methods.

show abstract