Defect detection on videos using neural network
In this paper, we consider a method for defects detection in a video sequence, which consists of three main steps; frame compensation, preprocessing by a detector, which is base on the ranking of pixel values, and the classification of all pixels having anomalous values using convolutional neural ne...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2017-01-01
|
| Series: | MATEC Web of Conferences |
| Online Access: | https://doi.org/10.1051/matecconf/201713205014 |
| _version_ | 1818451236069834752 |
|---|---|
| author | Sizyakin Roman Gapon Nikolay Shraifel Igor Tokareva Svetlana Bezuglov Dmitriy |
| author_facet | Sizyakin Roman Gapon Nikolay Shraifel Igor Tokareva Svetlana Bezuglov Dmitriy |
| author_sort | Sizyakin Roman |
| collection | DOAJ |
| description | In this paper, we consider a method for defects detection in a video sequence, which consists of three main steps; frame compensation, preprocessing by a detector, which is base on the ranking of pixel values, and the classification of all pixels having anomalous values using convolutional neural networks. The effectiveness of the proposed method shown in comparison with the known techniques on several frames of the video sequence with damaged in natural conditions. The analysis of the obtained results indicates the high efficiency of the proposed method. The additional use of machine learning as postprocessing significantly reduce the likelihood of false alarm. |
| first_indexed | 2024-12-14T21:03:59Z |
| format | Article |
| id | doaj.art-1271c5bfe0f24363b59cf9f3d98469d6 |
| institution | Directory Open Access Journal |
| issn | 2261-236X |
| language | English |
| last_indexed | 2024-12-14T21:03:59Z |
| publishDate | 2017-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | MATEC Web of Conferences |
| spelling | doaj.art-1271c5bfe0f24363b59cf9f3d98469d62022-12-21T22:47:31ZengEDP SciencesMATEC Web of Conferences2261-236X2017-01-011320501410.1051/matecconf/201713205014matecconf_dts2017_05014Defect detection on videos using neural networkSizyakin RomanGapon NikolayShraifel IgorTokareva SvetlanaBezuglov DmitriyIn this paper, we consider a method for defects detection in a video sequence, which consists of three main steps; frame compensation, preprocessing by a detector, which is base on the ranking of pixel values, and the classification of all pixels having anomalous values using convolutional neural networks. The effectiveness of the proposed method shown in comparison with the known techniques on several frames of the video sequence with damaged in natural conditions. The analysis of the obtained results indicates the high efficiency of the proposed method. The additional use of machine learning as postprocessing significantly reduce the likelihood of false alarm.https://doi.org/10.1051/matecconf/201713205014 |
| spellingShingle | Sizyakin Roman Gapon Nikolay Shraifel Igor Tokareva Svetlana Bezuglov Dmitriy Defect detection on videos using neural network MATEC Web of Conferences |
| title | Defect detection on videos using neural network |
| title_full | Defect detection on videos using neural network |
| title_fullStr | Defect detection on videos using neural network |
| title_full_unstemmed | Defect detection on videos using neural network |
| title_short | Defect detection on videos using neural network |
| title_sort | defect detection on videos using neural network |
| url | https://doi.org/10.1051/matecconf/201713205014 |
| work_keys_str_mv | AT sizyakinroman defectdetectiononvideosusingneuralnetwork AT gaponnikolay defectdetectiononvideosusingneuralnetwork AT shraifeligor defectdetectiononvideosusingneuralnetwork AT tokarevasvetlana defectdetectiononvideosusingneuralnetwork AT bezuglovdmitriy defectdetectiononvideosusingneuralnetwork |