METHOD FOR DETECTING FEATURE POINTS OF AN IMAGE USING A SIGN REPRESENTATIONS
Abstract
The aim of the study is to develop a method for detecting feature points of a digital image
that is stable with respect to a certain class of brightness transformations. The need for such a
method is due to the needs of detecting feature points of images in video surveillance systems and
face recognition, often working in a changing light environment. A feature of the proposed method
that distinguishes it from a number of well-known approaches to the problem of distinguishing
characteristic points is the use of the so-called sign representation of images. In contrast to the
usual defining of a digital image by a discrete brightness function, with a sign representation, the
image is set in the form of an oriented graph corresponding to the binary relation of the increase
in brightness on a set of pixels. Thus, the sign representation determines not a single image, but a
set of images, the brightness functions of which are connected by strictly monotonic brightness
transformations. It is this property of the sign representation that determines its effectiveness for
solving the problems caused by the goal set above. A feature of the method under consideration is
a special approach to the interpretation of the characteristic points of the image. This concept in
image processing theory is not strictly defined; we can say that the characteristic point is characterized
by increased "complexity" of the image structure in its vicinity. Since the sign representation
of the image can be represented in the form of a directed graph, in this paper, to evaluate the
complexity measure of the local neighborhood of its vertices, it is proposed to use the ranking
method known in the spectral theory of graphs based on the Perron-Frobenius theorem. Its essence
lies in the fact that the value of the component of the so-called Perron eigenvector of the
adjacency matrix of this graph acts as a measure of the complexity of the vertex. To conduct experimental
studies of the proposed approach, a set of programs was developed, the results of
which confirm the efficiency of the method and demonstrate that with its help it is possible to obtain
results close to the expected ones on model examples. The paper also offers a number of recommendations
on the use of this method.
References
human faces, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, Vol. 12,
pp. 23-35.
2. Sirovich L., Kirby M. Low-dimensional procedure for characterization of human face, Journal
of the Optical Society of America, 1987, Vol. 4, pp. 519-524.
3. Turk M., Pentland A. Eigenfaces for recognition, Journal of Cognitive Neuroscience, 1991,
Vol. 3, pp. 72-86.
4. Liu C., Wechsler H. A shape- and texture-based enhanced fisher classifier for face recognition,
IEEE Transactions Image Processing, 2001, Vol. 10, pp. 598-608.
5. Swets D.L., Weng J. Using discriminant eigenfeatures for image retrieval, IEEE Transactions
on Pattern Analysis and Machine Intelligence, 1996, Vol. 18, pp. 831-836.
6. Moghaddam B., Pentland A. Probabilistic visual learning for object representation, IEEE
Transactions on Pattern Analysis and Machine Intelligence, 1997, Vol. 19, pp. 696-710.
7. Lin S.H., Kung S.Y., Lin L.J. Face recognition/detection by probabilistic decision-based neural
network, Transactions on Neural Network, 1997, Vol. 8, pp. 114-132.
8. Liu C., Wechsler H. Evolutionary pursuit and its application to face recognition, IEEE Transactions
on Pattern Analysis and Machine Intelligence, 2000, Vol. 22, pp. 570-582.
9. Cox I.J., Ghosn J., Yianilos P.N. Feature-based face recognition using mixture distance, Computer
Vision and Pattern Recognition, 1996, pp. 209-216.
10. Nefian A.V., Hayes M.H. Hidden Markov models for face recognition, Acoustics, Speech and
Signal Processing, 1998, Vol. 5, pp. 2721-2724.
11. Samaria F., Young S. HMM-based architecture for face identification, Image and Vision
Computting, 1994, Vol. 12, pp. 537-543.
12. Pentland A., Moghaddam B., Starner T. View-based and modular eigenspaces for face recognition,
Computer Vision and Pattern Recognition, 1994, pp. 84-91.
13. Penev P., Atick J. Local feature analysis: A general statistical theory for object representation,
Computation in Neural Systems, 1996, No. 7, pp. 477-500.
14. Lanitis A., Taylor C.J., Cootes T.F. Automatic face identification system using flexible appearance
models, Image and Vision Computing, 1995, Vol. 13, pp. 393-401.
15. Weyrauch B., Heisele B., Huang J., Blanz V. Component-Based Face Recognition with 3D
Morphable Models, Computer Vision and Pattern Recognition Workshop, 2004, pp. 85-93.
16. Goncharov A.V., Karkishchenko A.N. Vliyanie osveshchennosti na kachestvo
raspoznavaniya frontal'nykh lits [Effects of illumination and quality of frontal faces recognition],
Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2008,
No. 4 (81), pp. 82-92.
17. Goncharov A., Gubarev V. Comparison of high-level and low-level face recognition methods,
Proc. Pattern recognition and image analysis: new information technologies (PRIA-9-2008),
2008, pp. 178-181.
18. Goncharov A.V. Issledovanie svoystv znakovogo predstavleniya izobrazheniy v zadachakh
raspoznavaniya obrazov [Investigation of properties of images sign representation in the pattern
recognition problems], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering
Sciences], 2009, No. 8 (97), pp. 178-188.
19. Bronevich A.G., Goncharov A.V. Znakovoe predstavlenie izobrazheniy i ego informativnost'
[Sign representations of images and its informativity], 14-ya Vserossiyskaya konf.
Matematicheskie metody raspoznavaniya obrazov [Proceedings of 14th All-Russia scientific
conference of mathematical methods for images recognition]. Moscow: MAKS Press, 2009,
pp. 309-312.
20. Goncharov A.V. Raspoznavanie lits na osnove mnogomasshtabnogo znakovogo prestavleniya
izobrazheniy [On face recognition based on multiscale sign representations of images],
Tsifrovaya obrabotka signalov [Digital signal processing], 2010, Vol. 1, pp. 10-13.
21. Grechukhin I.A., Karkishchenko A.N. O metode postroeniya kharakternykh tochek na osnove
variatsii yarkostnogo profilya [On a method for key points construction based on brightness
cross-section variations], Tr. OAO «NIIAS». Sb. nauchnykh trudov [Proceedings of JSC
NIIAS]. Issue 9. Moscow: Izd-vo OOO «Gruppa IDT», 2011, pp. 203-220.
22. Karkishchenko A.N., Goncharov A.B. Geometriya znakovogo predstavleniya izobrazheniy i ee
prilozhenie k issledovaniyu ustoychivosti k shumam [Sign reprsentations geometry applied for
noise stability investigations], Mezhdunarodnaya konferentsiya Intellektualizatsiya obrabotki
informatsii (IOI-8): Sb. dokladov [Proceedings of International conference on intellectualization
of images processing (IIP-8)]. Moscow: MAKS Press, 2010, pp. 335-339.
23. Karkishchenko A.N., Goncharov A.V. Issledovanie ustoychivosti znakovogo predstavleniya
izobrazheniy [Stability investigation of the sign representation of images], Avtomatika i
telemekhanika [Automation and Remote Control], 2010, Vol. 9, pp. 57-69.
24. Myasnikov V.V. Opisanie izobrazheniy s ispol'zovaniem konfiguratsionnogo otnosheniya
ekvivalentnosti [Description of images based on configurational equivalence relation],
Komp'yuternaya optika [Computer Optics], 2018, Vol. 42, No. 6, pp. 998-1007.
25. Pyt'ev Yu.P., Chulichkov A.I. Metody morfologicheskogo analiza izobrazheniy [Methods for
Morphological Analysis of Images]. Moscow: Fizmatlit, 2010, 336 p.
26. Bronevich A.G., Karkishchenko A.N., Lepskiy A.E. Analiz neopredelennosti vydeleniya
informativnykh priznakov i predstavleniy izobrazheniy [Uncertainty analysis of informational
features selection and images representations]. Moscow: Fizmatlit, 2013, 308 p.
27. Cvetković D.M., Doob M., Sachs H. Spectra of Graphs – Theory and Application. Berlin,
1980, 368 p.
28. Gantmakher F.R. Teoriya matrits [Theory of Matrices]. Moscow: Nauka, 1988, 552 p.
29. Khorn R., Dzhonson Ch. Matrichnyy analiz [Matrix Analysis]. Moscow: Mir, 1989, 655 p.
