Sparse coding based multi-option semantic composition

Bi, Xiaohan; Wu, Hao; Xu, Huating; Bie, Rongfang; Guo, Junqi

doi:10.1016/j.ijleo.2019.01.033

Cited by 2 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Selection of similar images becomes one challenge. Taking the accuracy and computational consumption into consideration, sparse coding representation model is used to fully express different images fully and calculate their similarity reasonably.…”

Section: Foe Optimization‐based Denoising Modelmentioning

confidence: 99%

“…It could contribute to the evaluation of the similarity between two images. Figure indicates the sketch map of image representation by one group of bases . For sure, given one image, we could optimize the following equation through multiiteration:

{normalmin}_{a, ϕ} {false\sum}_{i = 1}^{m} {(‖‖, x_{i} - \sum_{j = 1}^{k} a_{i, j} ϕ_{j})}^{2} + λ {false\sum}_{i = 1}^{m} {false\sum}_{j = 1}^{k} | a_{i, j} | .

…”

Section: Foe Optimization‐based Denoising Modelmentioning

confidence: 99%

“…Sketch map of image representation by one group of bases [Colour figure can be viewed at wileyonlinelibrary.com]…”

Section: Foe Optimization‐based Denoising Modelmentioning

confidence: 99%

“…Deep learning models convince researchers by overwhelming advantages compared with previous models. In most cases, deep learning models contain convolutional neural network (CNN)‐based methods, restricted Boltzmann machine (RBM)‐based methods, autoencoder‐based methods, and sparse coding‐based methods . Those models could contribute to achieve image hierarchical expression which gradually replaces other retrieval techniques.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Field of experts optimization‐based noisy image retrieval

et al. 2020

Self Cite

View full text Add to dashboard Cite

The value of image retrieval has become more and more prominent in the era of big data. However, large numbers of images are missed from current method since the image retrieval precision largely depends on the high quality of images. By common methodology, when the quality of images decreases a little, the accuracy of retrieval would decrease significantly. In particular, it is difficult to retrieve noisy images effectively by conventional approach. Yet large number of the noisy images could not be ignored at the age of data explosion. Aiming at the problem above, we proposed noisy image retrieval model based on field of experts (FoE) optimization. High-quality learning images could be selected by sparse coding, which is based on similarity calculation model, and the multioption filter combination model enhances the power of FoE model. We set up a database containing a large numbers of noisy images. Over this database, adequate groups of experiments are conducted. The verification of the method concluded its effectiveness and superiority.

show abstract

Section: Foe Optimization‐based Denoising Modelmentioning

confidence: 99%