Application of fusion of two classifiers based on principal component analysis method and time series comparison to recognize maritime objects upon FLIR images

Pietkiewicz, Tadeusz

doi:10.1117/12.2524975

Cited by 3 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper uses a different training set (a pattern database) than in [29], hence the results of the DTW classifier tests differ from the results contained therein.…”

Section: Results Of Maritime Objects Recognition Using Svm and Dtw CLmentioning

confidence: 99%

“…Similar topics were discussed in many papers, with different classification methods [7,9,12,13,15,16,27,29].…”

Section: Introductionmentioning

confidence: 82%

“…Two methods of classifying of maritime object silhouettes are used in the paper: a method based on multiclass classification using a support vector network SVM (SVM -Support Vector Machine) [1,2,3,4,5,6] called the SVM classifier in the paper and a DTW method of comparing time series (Date Time Warping), called the DTW classifier [17,18,21,29].…”

Section: Introductionmentioning

confidence: 99%

“…The second recognition method used in the paper is the classification by the DTW time series comparison method, described in detail in [17,18,21,29].…”

Section: Introductionmentioning

confidence: 99%

“…The image pre-processing process may include segmentation, brightness normalization, silhouette scaling, silhouette centering, silhouette leveling and extraction of distinctive features. Some problems of information pre-processing have been presented in [11,20,29].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Application of two classifiers fusion based on support vector machines method and time series comparison DTW to recognize maritime objects upon FLIR images

Pietkiewicz¹

2020

Radioelectronic Systems Conference 2019

Self Cite

View full text Add to dashboard Cite

Infrared image recognition by means of FLIR cameras (forward-looking infrared) is one of the elements of the recognition of the maritime situation and it supports in many situations the creation of so-called maritime picture. This paper presents results of two FLIR image classifiers research. The first part presents the use of SVM (Support Vector Machine) to classify images of maritime objects, while the second part presents the classifier using the time series comparison method DTW (data time warping). The SVM network uses to perform the multi-class classification the oneagainst-all method. Both classifiers use the histograms of vertical projection of pre-processed FLIR images as input data (for training and testing). These histograms are created as a result of FLIR color images processing, including, among others, transformation of color images into grayscale images, grayscale images segmentation using the Otsu algorithm with a possible manual correction, rescaling, centering and leveling. In the further part of the work a method of determining the basic belief assignment is proposed for both SVM and DTW classifiers. In the final part of the paper test results of the both classification methods and their fusion by the Dempster's method for a set of maritime objects FLIR images registered in the Baltic Sea are presented.

show abstract

“…This paper uses a different training set (a pattern database) than in [29], hence the results of the DTW classifier tests differ from the results contained therein.…”

Section: Results Of Maritime Objects Recognition Using Svm and Dtw CLmentioning

confidence: 99%

“…Similar topics were discussed in many papers, with different classification methods [7,9,12,13,15,16,27,29].…”

Section: Introductionmentioning

confidence: 82%

Section: Introductionmentioning

confidence: 99%

“…The second recognition method used in the paper is the classification by the DTW time series comparison method, described in detail in [17,18,21,29].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Application of two classifiers fusion based on support vector machines method and time series comparison DTW to recognize maritime objects upon FLIR images

Pietkiewicz¹

2020

Radioelectronic Systems Conference 2019

Self Cite

View full text Add to dashboard Cite

show abstract

Comparison of two classifiers based on neural networks and the DTW method of comparing time series to recognize maritime objects upon FLIR images

Pietkiewicz¹,

Sikorska-Łukasiewicz²

2019

XII Conference on Reconnaissance and Electronic Warfare Systems

View full text Add to dashboard Cite

Recognition of alphanumeric characters using artificial neuron networks and MSER algorithm

Matuszewski

Zając

2020

Radioelectronic Systems Conference 2019

View full text Add to dashboard Cite

The article presents a method of recognizing alphanumeric characters located in the image, based on a previously created database of patterns using neural networks. For this purpose the convolutional networks were used, which independently search for features that allow to distinguish characters in the image. A larger number of convolution layers allows us to recognize a greater number of features and thus to increase the probability of correctly recognized characters. The main purpose of the paper is to present software that recognizes the alphanumeric characters in images and to investigate the impact of the size of this database on the program's speed and character recognition efficiency. This software can also be used in more complex structures, such as automatic translators or as a computer reader. The calculation of the first program that recognizes single character and the second program that reads all the text from the image have been made in the MATLAB environment. The paper describes the components of this software, such as the learning subsystem and the character recognition subsystem. The results of the program were presented in the form of screenshots showing the results of the learning process and character recognition process. The speed of the software and the effectiveness of recognizing alphanumeric characters using the artificial neural networks and maximally stable extremal regions (MSER) algorithm are presented in the table and figures. Attention was also paid to the impact of the size of the database used to learn the network on the speed of calculations and recognition efficiency.

show abstract

Application of fusion of two classifiers based on principal component analysis method and time series comparison to recognize maritime objects upon FLIR images

Cited by 3 publications

References 9 publications

Application of two classifiers fusion based on support vector machines method and time series comparison DTW to recognize maritime objects upon FLIR images

Application of two classifiers fusion based on support vector machines method and time series comparison DTW to recognize maritime objects upon FLIR images

Comparison of two classifiers based on neural networks and the DTW method of comparing time series to recognize maritime objects upon FLIR images

Recognition of alphanumeric characters using artificial neuron networks and MSER algorithm

Contact Info

Product

Resources

About