Providing Decision Support in Career Guidance Through the use of Machine Vision
- 1 January 2022
- conference paper
- Published by Keldysh Institute of Applied Mathematics
Abstract
This paper is devoted to the review of the results of the development and implementation of the ColorUnique Pro career guidance software package in the career guidance activities of higher educational institutions. The review begins with the initial formulation of the problem, justification of the use of neural networks as the basis of one of the classifiers, consideration of the results of experiments and then – the introduction of a software package. At the end of the article, prospects for further research are described, such as the creation of a three-dimensional map of types and subtypes and the further identification of new subtypes. The possibility of using additional methods of analysis, detection and classification is also being considered in order to study the influence on the definition of ISA of such features of the images obtained as «demonstrative» and «true» structures, as well as the presence of a «background» that does not contain characteristic elements. In addition to neural networks, the authors also used the «sliding» window image processing method, as a result, the software package includes two classifiers that analyze images separately, however, in the future, the results of the analysis of both classifiers are compared by an expert, since some subtypes can only be determined by joint interpretation.Keywords
This publication has 7 references indexed in Scilit:
- AUTOMATED METHODOLOGY OF CAREER GUIDANCE TESTING AS A DECISION SUPPORT SYSTEMСИСТЕМЫ УПРАВЛЕНИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ, 2022
- Structure-Measure: A New Way to Evaluate Foreground MapsInternational Journal of Computer Vision, 2021
- Algorithms for Automated Differentiation of Subtypes and Improving the Overall Accuracy of Image Classification in Career Guidance2021
- Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural NetworksInternational Journal of Computer Vision, 2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Going deeper with convolutions2015
- What is a Salient Object? A Dataset and a Baseline Model for Salient Object DetectionIEEE Transactions on Image Processing, 2014