Currently, the means of semantic segmentation of images, which are based on the use of neural networks, are increasingly being used in computer systems for various purposes. Despite significant progress in this industry, one of the most important unsolved problems is the task of adapting a neural network model to the conditions for selecting an object mask in an image. The features of such a task necessitate determining the type and parameters of convolutional neural networks underlying the encoder and decoder. As a result of the research, an appropriate method has been developed that allows adapting the neural network encoder and decoder to the following conditions of the segmentation problem: image size, number of color channels, acceptable minimum segmentation accuracy, acceptable maximum computational complexity of segmentation, the need to label segments, the need to select several segments, the need to select deformed , displaced and rotated objects, allowable maximum computational complexity of training a neural network model, allowable training time for a neural network model. The main stages of the method are related to the following procedures: determination of the list of image parameters to be registered; formation of training example parameters for the neural network model used for object selection; determination of the type of CNN encoder and decoder that are most effective under the conditions of the given task; formation of a representative educational sample; substantiation of the parameters that should be used to assess the accuracy of selection; calculation of the values of the design parameters of the CNN of the specified type for the encoder and decoder; assessment of the accuracy of selection and, if necessary, refinement of the architecture of the neural network model. The developed method was verified experimentally on examples of semantic segmentation of images containing objects such as a car. The obtained experimental results show that the application of the proposed method allows, avoiding complex long-term experiments,

The widespread implementation of neural network tools for biometric authentication based on facial and iris images at critical infrastructure facilities has significantly increased the level of security. However, modern requirements dictate the need to modernize these tools to increase resistance to spoofing attacks, as well as to provide a base for assessing the compliance of the psycho-emotional state of personnel with job responsibilities, which is difficult to ensure using traditional monolithic neural network models. Therefore, this article is devoted to the development of a modular neural network model that provides effective biometric authentication for critical infrastructure personnel based on facial images, taking into account the listed requirements. When developing the model, an approach was used in which the functionality of each module was defined in such a way as to correspond to a task traditionally solved by a separate neural network model. This made it possible to use in each individual module a tested and accessible toolkit that has proven its effectiveness in solving the corresponding problem, which, in turn, compared to traditional approaches, allows for a 30–40% increase in the efficiency of the development and adaptation of authentication tools for the conditions of their application. Innovative features of the developed modular model include the ability to recognize spoofing attacks based on environmental artifacts and the naturalness of emotions, as well as an increase in the accuracy of person recognition due to the use of a U-Net neural network to highlight natural facial contours in occlusions. The experimental results show that the proposed model allows for a 5–10% decrease in person recognition error, recognition of spoofing attacks based on the naturalness of emotions and images of background objects, and recognition of the emotional state of personnel, which increases the efficiency of biometric authentication tools.