Shape retrieval using deep autoencoder learning representation

Xu, Guozhen; Fang, Weiwei

doi:10.1109/iccwamtip.2016.8079843

Cited by 8 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each shape in the database is set as a query in turn, then the similar shapes are retrieved in this database. In the retrieval results, the precision is calculated when 10 (recall rate is 13.33%), 20 (recall rate is 26.7%), 30 (recall rate is 40.0%), 40 (recall rate is 53.3%), 50 (recall rate is 66.7%), 60 (recall rate is 80.0%), 70 (recall rate is 93.3%), and 75 (recall rate is 100%) shapes are retrieved correctly [21]. The average precision is used to evaluate the performance of the proposed FMSCCD+FASD compared to some state-of-the-art methods.…”

Section: Resultsmentioning

confidence: 99%

“…In this experiment, the descriptor DALR (deep autoencoder learning representation) [21] based on the autoencoder is also selected to be compared. The experimental results of some state-of-the-art descriptors and the proposed FMSCCD in this paper are shown in Table 4.…”

Section: Resultsmentioning

confidence: 99%

“…Some descriptors based on matching learning [21,22] have appeared in recent years. Sometimes these methods are used in medical images analysis [23].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Fourier Descriptor of 2D Shapes Based on Multiscale Centroid Contour Distances Used in Object Recognition in Remote Sensing Images

Zheng

Guo

Chen

et al. 2019

Sensors

View full text Add to dashboard Cite

A shape descriptor is an effective tool for describing the shape feature of an object in remote sensing images. Researchers have put forward a lot of excellent descriptors. The discriminability of some descriptors is very strong in the experiments, but usually their computational cost is large, which makes them unsuitable to be used in practical applications. This paper proposes a new descriptor-FMSCCD (Fourier descriptor based on multiscale centroid contour distance)—which is a frequency domain descriptor based on the CCD (centroid contour distance) method, multiscale description, and Fourier transform. The principle of FMSCCD is simple, and the computational cost is very low. What is commendable is that its discriminability is still strong, and its compatibility with other features is also great. Experiments on three databases demonstrate its strong discriminability and operational efficiency.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Fourier Descriptor of 2D Shapes Based on Multiscale Centroid Contour Distances Used in Object Recognition in Remote Sensing Images

Zheng

Guo

Chen

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…In this study, we also applied the logistic sigmoid function 1/(1 + exp(−x)) to f (x) and g(x). An autoencoder is a type of neural network that encodes input data for reconstruction as output data [44]. To begin this process, the autoencoder must learn to capture the significant features of the input.…”

Section: Lstm Modelsmentioning

confidence: 99%

Air Pollution Prediction Using Long Short-Term Memory (LSTM) and Deep Autoencoder (DAE) Models

2020

View full text Add to dashboard Cite

Many countries worldwide have poor air quality due to the emission of particulate matter (i.e., PM10 and PM2.5), which has led to concerns about human health impacts in urban areas. In this study, we developed models to predict fine PM concentrations using long short-term memory (LSTM) and deep autoencoder (DAE) methods, and compared the model results in terms of root mean square error (RMSE). We applied the models to hourly air quality data from 25 stations in Seoul, South Korea, for the period from 1 January 2015, to 31 December 2018. Fine PM concentrations were predicted for the 10 days following this period, at an optimal learning rate of 0.01 for 100 epochs with batch sizes of 32 for LSTM model, and DAEs model performed best with batch size 64. The proposed models effectively predicted fine PM concentrations, with the LSTM model showing slightly better performance. With our forecasting model, it is possible to give reliable fine dust prediction information for the area where the user is located.

show abstract

“…The optimization job in SVM includes the explanation of a convex optimization problem for which an actual enjoyable theory and effectual techniques are obtainable [2]. The SVM practice has been effectively used to a huge diversity of pattern recognition problems such as., face recognition [3], confirmation and classification [4], object recognition and classification [5], handwritten character and digit classification [6], text classification [7], speech identification, etc. Machine learning (ML) approaches have been used in a number of problems in materials physics, lately [8].…”

Section: Introductionmentioning

confidence: 99%

Support vector machine based on power of signal for solving high-energy physics problem

Khudheyer¹,

Jashami²

2019

IJREI

View full text Add to dashboard Cite

In this paper, a new method proposed combining support vector machine (SVM) based on power of signal for high-energy physics problem. In the first stage, the high-energy physics are analyzed by using Power of signal, which produce number of sensitive features. The aim of this stage reduce the number of features and improve the quality of them. In the second stage, SVM applied to classify the new features into two categories and presented remarkable results.

show abstract

Shape retrieval using deep autoencoder learning representation

Cited by 8 publications

References 11 publications

A Fourier Descriptor of 2D Shapes Based on Multiscale Centroid Contour Distances Used in Object Recognition in Remote Sensing Images

A Fourier Descriptor of 2D Shapes Based on Multiscale Centroid Contour Distances Used in Object Recognition in Remote Sensing Images

Air Pollution Prediction Using Long Short-Term Memory (LSTM) and Deep Autoencoder (DAE) Models

Support vector machine based on power of signal for solving high-energy physics problem

Contact Info

Product

Resources

About