Similarity learning for object recognition based on derived kernel

Li, Hong; Wei, Yantao; Li, Luoqing; Yuan, Yuan

doi:10.1016/j.neucom.2011.12.005

Cited by 22 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That algorithm is firstly proposed by [17], under development of [18] [19], and it is encouraged to read them for a more detailed introduction and treatment.…”

Section: Character Recognition Based On Derived Kernelmentioning

confidence: 99%

License Plate Recognition algorithm based on derived kernel

Zhang

Tang

2012

2012 International Conference on Wavelet Analysis and Pattern Recognition

View full text Add to dashboard Cite

License Plate Recognition (LPR) plays an important role on the traffic monitoring and parking management. In this paper, an updated algorithm is applied into the vehicle license plate identification, which is mainly based on derived kernel through visual cortex. With the two-layer derived kernel on neural response and first nearest classification method applied to character and numeral recognition, the errors caused by blur and noise can be reduced, so that the recognition accuracy can be improved on a certain of complex and unclear circumstance.

show abstract

“…That algorithm is firstly proposed by [17], under development of [18] [19], and it is encouraged to read them for a more detailed introduction and treatment.…”

Section: Character Recognition Based On Derived Kernelmentioning

confidence: 99%

License Plate Recognition algorithm based on derived kernel

Zhang

Tang

2012

2012 International Conference on Wavelet Analysis and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…These are important factors and challenging tasks in the image organization. Consequently, the main thing is the selection of more effective measure is to make the error rate of classification method lesser [10][11][12]. So many different studies have attracted them to the similarity measure among features in the last few decades.…”

Section: Introductionmentioning

confidence: 99%

“…Researcher has been attracted by Derived kernel based neural response (NR), and it has verified to be a powerful solution to a wide range of application fields, specifically, in image processing, machine learning, and computer vision. In [11], Hong Li et al suggested a pattern selection technique for the similarity measure capability of the derived kernel based neural response, when [23] presenting a hierarchical feature extraction method called local neural response (LNR) to recognize. Another technique is suggested in [24,25] to a feature extraction scheme using neural response by linking the hierarchical architectures with the sparse coding.…”

Section: Introductionmentioning

confidence: 99%

Using Derived kernel as a new Method for Recognition a Similarity Learning.

Alsaidi,

Alanzi,

Alenazi

et al. 2020

IJEAT

View full text Add to dashboard Cite

A new technique for feature withdrawal by neural response is going to be familiarized in this research work by merging an entropy measure with Squared Pearson correlation Coefficient (SPCC) method. The process of choosing effective models on the basis of entropy measures was proposed further to enhance the ability to select templates. For more accurate similarity measure we used the statistical significant relationship between functions. The research illustrate that the proposed method is proficiently compared with the state-of-the-art methods.

show abstract

“…Theoretical analysis and experimental results show that the NR model is an effective feature extraction method. It has the potential to be further improved and enhanced in many applications [17,[23][24][25]. Most important of all, the NR model has a key semantic component: a system of templates which can fuse the visual features and the semantic features of an image together and which is very important in CBIR.…”

Section: Introductionmentioning

confidence: 99%

Features Conduction Neural Response and Its Application in Content-Based Image Retrieval

Hu¹,

Tian²,

Xiao³

2016

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A novel image representation is proposed for content-based image retrieval (CBIR). The core idea of the proposed method is to do deep learning for the local features of image and to melt semantic component into the representation through a hierarchical architecture which is built to simulate human visual perception system, and then a new image descriptor of features conduction neural response (FCNR) is constructed. Compared with the classical neural response (NR), FCNR has lower computational complexity and is more suitable for CBIR tasks. The results of experiments on a commonly used image database demonstrate that, compared with those of NR related methods or some other image descriptors that were originally developed for CBIR, the proposed method has wonderful performance on retrieval efficiency and effectiveness.

show abstract

Similarity learning for object recognition based on derived kernel

Cited by 22 publications

References 22 publications

License Plate Recognition algorithm based on derived kernel

License Plate Recognition algorithm based on derived kernel

Using Derived kernel as a new Method for Recognition a Similarity Learning.

Features Conduction Neural Response and Its Application in Content-Based Image Retrieval

Contact Info

Product

Resources

About