Notice: Undefined index: linkPowrot in C:\wwwroot\wwwroot\publikacje\publikacje.php on line 1275
Strona główna > Publikacje
Publikacje
Pomoc (F2)
Dane niepełne - brak identyfikatora "Web of Science" !

[121100] Artykuł:

A New Approach to Enhance Learning Data Sets for Object Classification

Czasopismo: 26th International Conference on Circuits, Systems, Communications and Computers (CSCC)   Strony: 77-84
Opublikowano: Lipiec 2022
 
  Autorzy / Redaktorzy / Twórcy
Imię i nazwisko Wydział Katedra Do oświadczenia
nr 3		 Grupa
przynależności		 Dyscyplina
naukowa		 Procent
udziału		 Liczba
punktów
do oceny pracownika		 Liczba
punktów wg
kryteriów ewaluacji
Andrzej Dziech Niespoza "N" jednostki017.00.00  
Jacob Wassermann Niespoza "N" jednostki017.00.00  
M. Windisch Niespoza "N" jednostki017.00.00  
Remigiusz Baran orcid logo WEAiIKatedra Informatyki, Elektroniki i Elektrotechniki *Takzaliczony do "N"Automatyka, elektronika, elektrotechnika i technologie kosmiczne17.00.00  
Andrzej Zeja Niespoza "N" jednostki017.00.00  
Piotr Bogacki Niespoza "N" jednostki017.00.00  

Grupa MNiSW:  Materiały z konferencji międzynarodowej (zarejestrowane w Web of Science)
Punkty MNiSW: 0

Pełny tekstPełny tekst     DOI LogoDOI    
Keywords:

poor dataset quality  CNN  SVT  shape descriptor  incremental learning  3D models 


Abstract:

In this paper, we propose a novel solution to the problem of insufficient training data in complex image classification tasks. The presented method efficiently recommends new learning samples with the use of contour-based descriptors and Scalable Vocabulary Tree (SVT) technique. The SVT is built from SIFT features and may be used for identification and localization of objects of interest in the analyzed query images. In conditions where the training data set is not large enough, the SVT's classification accuracy is satisfactory and comparable to that achieved by the dedicated CNN network. However, the SVT approach surpasses the classic convnet approaches due to its incremental learning capability. The classification certainty is further increased thanks to contour-based analysis using Point Distance Histogram (PDH) descriptor. At this stage, the PDH representation of the analyzed object is matched with the information stored in the pattern database. This database contains a set of 360 shape outlines for each object that are extracted from its 3D model. This leads to higher classification accuracy of the presented approach.


B   I   B   L   I   O   G   R   A   F   I   A
1. http://www.live-counter.com/how-big-is-the-internet/.
2. Y. Taigman, M. Yang, M. Ranzato and L. Wolf, "DeepFace: Closing the Gap to Human-Level Performance in Face Verification", 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701-1708, 2014.
3. F. Chollet, "Deep Learning with Python", Manning Publications Co. New York, 2018.
4. M. Worring and C. Snoek, "Visual Content Analysis" in Encyclopedia of Database Systems, Boston, MA:Springer US, pp. 3360-3365, 2009.
5. Z. Li and D. Hoiem, "Learning without forgetting", PAMI, 2018.
6. Y. Tao, Y. Tu and M. Shyu, "Efficient Incremental Training for Deep Convolutional Neural Networks", 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 286-291, 2019.
7. Y. Cheng, D. Wang, P. Zhou and T. Zhang, "A survey of model compression and acceleration for deep neural networks", CoRR, vol. abs/1710.09282, 2017.
8. D. Roy, P. Panda and K. Roy, "Tree-CNN: A hierarchical Deep Convolutional Neural Network for incremental learning", Neural networks, vol. 121, pp. 148-160, 2018.
9. F.M. Castro, M.J. Marín-Jiménez, N. Guil, C. Schmid and K. Alahari, "End-to-End Incre-mental Learning" in Computer Vision - ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, Cham:Springer, vol. 11216, 2018.
10. Murphy and P. Kevin, "Machine learning: a probabilistic perspective" in Mass, [u.a.]: MIT Press, 2013.
11. G. Hinton, O. Vinyals and J. Dean, "Distilling the knowledge in a neural network", NIPS 2014 Deep Learning and Representation Learning Workshop.
12. D. Nister and H. Stewenius, "Scalable recognition with a vocabulary tree", Conference on Computer Vision and Pattern Recognition, pp. 2161{2168, 2006.
13. https://github.com/snavely/VocabTree2.
14. D.G. Lowe, "Distinctive Image Features from Scale-Invariant Key-points", International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
15. S. Wang, Z. Guo and Y. Liu, "An Image Matching Method Based on SIFT Feature Extraction and FLANN Search Algorithm Improvement", 2021 J. Phys.: Conf. Ser., vol. 2037, pp. 012122.
16. C. Rother, V. Kolmogorov and A. Blake, "GrabCut - Interactive Foreground Extraction using Iterated Graph Cuts", ACM Transactions on Graphics, vol. 23, no. 3, pp. 309-314, 2004.
17. N. Otsu, "A Threshold Selection Method from Gray-Level Histograms", IEEE Transactions on Systems Man and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979.
18. R. Baran and A. Kleszcz, "The Efficient Spatial Methods of Contour Approximation", Proceedings of the 2014 IEEE Int. Conf. on Signal Processing: Algorithms, pp. 116-121, 2014.
19. A. Dziech and W. Besbas, "Fast Algorithm for Closed Contour Extraction", Proc. of the Int. Workshop on Systems Signals and Image Processing Poznan, pp. 203-206, 1997.
20. H. Freeman, "Techniques for The Digital Computer Analysis of Chain Encoded Arbitrary Plane Curves", Proc. of the National Electrician Conference, pp. 421-432, 1961.
21. D. Frejlichowski, "Shape representation using point distance histogram", Polish Journal of Environmental Studies, vol. 16, no. 4A, 2007.

POWRÓT
Strona główna > Publikacje