In recent times, machine learning algorithms have shown great performance in solving problems in different fields of study, including the analysis of remote sensing images, computer vision, natural language processing, medical issues, etc. A well-prepared input dataset can have a huge impact on the result metrics. However, a correctly selected hyperparameter combined with neural network architecture could highly increase the final metrics. Therefore, the hyperparameters optimization problem becomes a key issue in a deep learning algorithm. The process of finding a suitable hyperparameter combination could be performed manually or automatically. Manual search is based on previous research and requires enormous human efforts. However, there are many automated hyperparameter optimization methods have been successfully applied in practice. The automated hyperparameter tuning techniques are divided into two groups: black-box optimization techniques (such as Grid Search, Random Search) and multi-fidelity optimization techniques (HyperBand, BOHB). The most recent and promising among all approaches is BOHB which, which combines both Bayesian optimization and bandit-based methods, outperforms classical approaches, and can run asynchronously with given GPU resources and time budget that plays a vital role in the hyperparameter optimization process. The previous study proposed a convolutional deep learning neural network for solving land cover classification problems in the EuroSAT dataset. It was found that adding spectral indexes NDVI, NDWI, and GNDVI with RGB channels increased the result accuracy (from 64.72% to 84.19%) and F1 (from 63.89 % to 84.05%) score. However, the convolutional neural network architecture and hyperparameter combination were selected manually. The research optimizes convolutional neural network architecture and finds suitable hyperparameter combinations applied to land cover classification problems using multispectral images. The obtained results must increase result performance compared with the previous study and given budget constraints.

No abstract

The system of automatic license plate recognition (ALPR) is a combination of software and hardware technologies implementing ALPR algorithms. It seems to be easy to achieve the goal but recognition of license plate requires many difficult solutions to some non-trivial tasks. If the license plate is oriented horizontally, uniformly lighted, has a clean surface, clearly distinguishable characters, then it’ll be not too difficult to recognize such a license plate. However, the reality is much worse. The lighting of each part of the plate isn’t equal; the picture from the camera is noisy. Besides, the license plate can have a big angle relative to the camera and be dirty. These obstacles make it difficult to recognize the license plate characters and determine their location on the image. For instance, the accuracy of recognition is much worse on large camera angles. To solve these problems, the developers of automatic license plate recognition systems use a different approach to processing and analysis of images. The work shows an automatic license plate recognition system, which increases the recognition accuracy at large camera angles. The system is based on the technology of recognition of images with the use of highly accurate convolutional neural networks. The proposed system improves stages of normalization and segmentation of an image of the license plate, taking on large camera angles. The goal of improvements is to increase of accuracy of recognition. On the stage of normalization, before histogram equalization, the affine transformation of the image is performed. For the process of segmentation and recognition, Mask R-CNN is used. As the main segment-search algorithm, selective search is chosen. The combined loss function is used to fasten the process of training and classification of the network. The additional module to the convolutional neural network is added for solving the interclass segmentation. The input for this module is generated feature tensor. The output is segmented data for semantic processing. The developed system was compared to well-known systems (SeeAuto.USA and Nomeroff.Net). The invented system got better results on large camera shooting angles.

The subject matter of the article is the method of automating the identification of vehicle plate numbers based on the processing of one-aspect images obtained using video recording means. The goal is to provide automation of the process of identifying vehicle plate numbers within a wide range of changing the viewing angles and the levels of illumination. The task is formulation of the method of automated identification of vehicle plate numbers on one-aspect images, which are obtained by means of video fixation within wide limits of changing both the viewing angles and the levels of illumination. Analysis of the problems of methods and algorithms of automated detection and recognition of vehicle plate numbers has shown that it is most promising to use flexible algorithms that adapt to the changing conditions of observation of traffic control devices. One of the promising technologies for implementing such algorithms is the application of artificial neural networks. The solution of the problem of recognition of vehicle plate numbers can be represented as a complex of image processing and analysis of algorithms, which includes the initial preparation of the image, the discovery of the area of the vehicle plate on the image, the segmentation of symbols and the recognition of symbols. Conclusions: an algorithmically implemented method of identifying vehicle plate numbers, which makes possible searching the text areas under an arbitrary angle in different lighting conditions, is proposed. This method allows automating the process of identification of vehicle plate numbers within a wide range of distances to the car, as well as viewing the angles and levels of illumination. The purpose of further research is to improve the proposed method for its implementation, using modern software and hardware. K e ywor d s : vehicle plate number identification; image processing; character recognition; neural network; convolutional neural network.

No abstract