employee
Nizhniy Novgorod, Nizhny Novgorod, Russian Federation
Nizhny Novgorod, Russian Federation
Nizhny Novgorod, Russian Federation
BISAC COM012000 Computer Graphics
Career guidance testing assumes the presence of several types of individuals, and in the case when the output data of testing are images that characterize certain qualities of the subjects – several types (classes) of images. The image classes includes of selected searchable elements that determine whether an image belongs to a particular selected type (class). There is a ColourUnique M software module that allows you to automate the process of testing and saving test forms. The functions of the classifier are still performed by an expert (teacher or psychologist), which implies errors in evaluating the result due to individual characteristics of human perception, which can negatively affect the reliability of the classification. The paper considers two algorithms for evaluating images (the made test forms), one of which is a neural network, and the second is a filtering algorithm with hard – defined areas for determining the desired elements. During the implementing of these algorithms, a number of problems arose. The classifier is created in order to improve the accuracy of classification, both in comparison with expert assessment and with the first experimental data obtained. For achieve of the most reliable classification results, the authors consider the possibility of implementing a hybrid classifier for career guidance tasks.
neural network, algorithm, classification, element recognition, filter
1. Tsvetkov A. A. Algorithms for object recognition / A. A. Tsvetkov, D. K. Shorokh, M. G. Zubareva [et al.] / / Technical Sciences: problems and prospects: materials of the IV international conference. nauch. konf. - Saint Petersburg: Its publishing house, 2016. - P. 20-28. - URL: https://moluch.ru/conf/tech/archive/166/10825/ (accessed: 08.05.2020).
2. Proforientator.ru Career guidance tests [Electronic resource]: Website - https://proforientator.ru/tests/ (accessed 26.05.2020).
3. Tarasova, I.S. Implementation of algorithms of image analysis in the software package ColourUniquePRO with the aim of increasing the accuracy of classification types individuals / I.S. Tarasova, A.V. Chechin, V.V. Andreev // Computer Graphics and Vision. Proceedings of the 29th International Conference on Computer Graphics and Vision. Bryansk, Russia, September 23-26, 2019. – pp.189-193.
4. Utrobin, V. A. Computer image processing. Information models of the understanding stage: studies.manual / V. A. Utrobin. - N. Novgorod: NSTU, 2006. - 247 p.
5. Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam. MobileNets: Efficient Convolutional Neural Networks for Mobile VisionApplications. arXiv:1704.04861v1, 2017. – https://arxiv.org/pdf/1704.04861.pdf.
6. Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich. Going deeper with convolutions. arXiv:1409.4842v1, 2014. – https://arxiv.org/pdf/1409.4842.pdf.
7. Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:1505.04597v1, 2015. – https://arxiv.org/pdf/1505.04597.pdf.
8. Wikipedia. Stochastic gradient descent. [Electronic resource]: Website - wikipedia.org.
9. Keras-Open neural network library – https://keras.io/. (accessed: 08.05.2020).
10. Open CV-computer vision Library – https://opencv.org/.(date accessed: 08.05.2020).
11. Topunov, V.L. Combinatorics. Workshop on solving problems: textbook / V.L.Topunov; edited by V.I. Nechaev, V.G. Chirsky. - 2nd ed. - Moscow: MPSU, 2016. - 88 p.
12. Andreev V.V. Problems and prospects of implementation of the algorithm of classification of test forms of the color Unique Pro software complex / V.V. Andreev, I.S. Tarasova, A.V. Chechin / / Information systems and technologies-2020: [Electronic resource]: collection of materials of the XXVI International scientific and technical conference-Electron. Dan - N. Novgorod: NSTU, 2020. - P. 913-918. - URL: https://www.nntu.ru/frontend/web/ngtu/files/news/2020/05/12/ist2020/sbornik_ist2020.pdf
