Artificial intelligence

Abstract: This article describes the elements of information technology for analysis of facial expressions to apply in interactive study of sign language. The main elements of information technology, its structure and experimental implementation has been discussed. Analysis was carried out in order to identify how the classifier error rate depends on type of classifier, number of feature and teach set. Optimal constructs of classifiers were proposed, giving drastic improvement of existing algorithms.

Keywords: information technology, algorithm for identification, facial expressions, sign language.

References:

1. Zaytseva H.L. Zhestovaya rech'. Daktylolohyya: Ucheb. dlya stud. vsissh. ucheb. zavedenyy / Zaytseva H.L. – M: Humanyt. yzd. tsentr VLADOS, 2000. – 192 s.
2. Tkacheva T. Zhestovy yazik hlukhykh kak osobaya znakovaya kommunykatyvnaya systema (na materyale russkoho y frantsuzskoho zhestovykh yazykov) / Tkacheva T., Akhmedysheva N. // Materyali Mezhdunarodnoy nauchno-praktycheskoy konferentsyy «Pryoryteti y ynteresi sovremennoho obshchestva». – Astrakhan': AHU, 2010. – S. 361–365.
3. Kul'bida S.V. Ukrayins'ka zhestova mova yak pryrodna znakova systema / S.V. Kul'bida // zbirnyk naukovykh prats' «Zhestova mova y suchasnist'»: K: Pedahohichna dumka, 2009. – S. 218-239.
4. Krak Iu.V. Rozrobka osnovnykh instrumentiv komp"yuternoyi animatsiyi dlya pobudovy systemy syntezu zhestovoyi movy / Iu.V. Krak, M.P. Lisnyak, A.S. Ternov // Materialy mizhnarodnoyi naukovoyi konferentsiyi „Intelektual'ni systemy pryynyattya rishen' ta problemy obchyslyuval'noho intelektu”, 27–31 travnya 2012. – Kherson: KhNTU, 2012. – S. 104-105.
5. Krak Iu.V Modelyrovanye emotsyonal'nikh proyavlenyy s pomoshch'yu parametrycheskykh modeley holovi cheloveka / Iu.V. Krak, A.S. Ternov, V.O. Kuznetsov // Naukovo-teoretychnyy zhurnal «Shtuchnyy intelekt». – 2013. – № 3. – Donets'k.: IPShI, 2013. – S. 154-170.
6. Krak Iu.V. Facial expressions analysis based on computer vision algorithms / Iu.V. Krak, A.S. Ternov, V.A. Kuznyetsov // International Journal "Information Content and Processing". – 2014. – # 4. – Sofia.: ITHEA, 2014. – pp. 326-338.
7. Krak Iu.V Analyz mymycheskykh proyavlenyy na lytse cheloveka / Iu.V. Krak, A.S. Ternov, V.O. Kuznetsov // Naukovo-teoretychnyy zhurnal «Shtuchnyy intelekt». – 2015. – № 3-4. – Kyiv.: IPShI, 2015. – S. 37-50.
8. Honglak L. Unsupervised Feature Learning for Audio Classification Using Convolutional Deep Belief Networks // L. Honglak, Y. Largman, P. Pham, Y.Ng. Andrew // Proceedings of conference on Neural Information Processing Systems (NIPS 2009) – Red Hook, NY: Curran Associates, Inc., 2009, - pp. 1096-1104.
9. Al-Naymat G. Sparse DTW: A novel approach to speed up Dynamic Time Warping / G. Al-Naymat, S. Chawla, J. Taheri // The 2009 Australasian Data Mining, vol. 101 – Melbourne, Australia, ACM Digital Library. – pp. 117-127.
10. Chumakov A.G., Kurashov V.N. Karhunen-Loeve Basis Synthesis for Grate Capacity Signal Performance in Optical Processors // SPIE Proc. – 1993. – Vol.21-08. – P. 338- 342.
11. Loeffler C., Ligtenberg A., Moschytz G. Practical Fast 1-D DCT Algorithms with 11 Multiplications // Proc. Int. Conf. on Acoustics, Speech, and Signal Processing 1989 (ICASSP '89). – 1989. – P. 988-991.
12. Elektronnyy resurs intehrovanoho seredovyshcha rozrobky Java/Scala IntelliJ IDEA. Rezhym dostupu: https://www.jetbrains.com/idea/
13. Elektronnyy resurs movy Scala. Rezhym dostupu: http://www.scala-lang.org
14. Elektronnyy resurs bazy danykh PostgreSQL. Rezhym dostupu: https://www.postgresql.org/
15. Elektronnyy resurs Oracle Java Virtual Machine. Rezhym dostupu: http://www.oracle.com/technetwork/java/javase/overview/index.html