An important feature of image analysis is texture, seen in all images, from aerial and satellite images to microscopic images in biomedical research. A chest X-ray is the most common and effective method for diagnosing severe lung diseases such as cancer, pneumonia, and tuberculosis. The lungs are the largest X-ray object. The correct separation of the shapes and sizes of the contours of the lungs is an important reason for diagnosis, because of which an intelligent information environment can be created. Despite the use of X-rays, to identify the diagnosis, there is a chance that the disease will not be detected. In this sense, there is a risk of development, which may be fatal. The article deals with the problems of pneumonia clustering using the autocorrelation function to obtain the most accurate result. This provides a reliable tool for diagnosing lung radiographs. Image pre-processing and data shaping play an important role in revealing a well-functioning basis of the nervous system. Therefore, images from two classes were selected for the task: healthy and with pneumonia. This paper demonstrates the applicability of the autocorrelation function for highlighting interest in lung radiographs based on the fineness of textural features and k-means extraction.

Fire detection is an important task in the field of safety and emergency prevention. In recent years, deep learning methods have shown high efficiency in solving various computer vision problems, including detecting objects in images. In this paper, monitoring wildfires was considered, which allows you to quickly respond to them and prevent their spread using deep learning methods. For the experiment, images from the satellite and images from the FireWatch sensor were taken as initial data. In this work, the deep learning algorithms you only look once (YOLO), convolutional neural network (CNN), and fast recurrent neural network (FastRNN) were considered, which makes it possible to determine the accuracy of a natural fire. As a result of the experiments, an automated fire recognition algorithm using YOLOv4 deep learning methods was created. It is expected that the results of the study will show that deep learning methods can be successfully applied to detect fire in images. This may lead to the development of automated monitoring systems capable of quickly and reliably detecting fire situations, which will help improve safety and reduce the risk of fires.

This paper focuses on aerospace image analysis methods. Aerospace images are considered for the study of agricultural crops of northern Kazakhstan belonging to the A. I. Barayev Research and Production Center for Grain Farming. The main goal of the research is the development and implementation of algorithms that make it possible to detect and highlight on aerospace images the factors that negatively affect the growth of crops over the growing seasons. To resolve the problem, the spectral brightness coefficient (SBC), NDVI, clustering, orthogonal transformations are used. Special attention was paid to the development of software tools for selecting characteristics that describe texture differences to segment texture regions into sub-regions. That is, the issue of the applicability of sets of textural features and orthogonal transformations for the analysis of experimental data to identify characteristic areas on aerospace images that can be associated with weeds, pests, etc. in the future was investigated. The questions of signal image processing remain the focus of attention of different specialists. The images act both as a result and as a research object in physics, astronautics, meteorology, forensic medicine and many other areas of science and technology. Furthermore, image processing systems are currently being used to resolve many applied problems. A program has been implemented in the MATLAB environment that allows performing spectral transformations of six types: 1) cosine; 2) Hadamard of order 2n; 3) Hadamard of order n=p+1, p≡3 (mod4); 4) Haar; 5) slant; 6) Daubechies 4. Analysis of the data obtained revealed the features of changes in the reflectivity of cultivated crops and weeds in certain periods of the growing season. The data obtained are of great importance for the validation of remote space observations using aerospace images

This article discusses a large number of textural features and integral transformations for the analysis of texture-type images. It also discusses the description and analysis of the features of applying existing methods for segmenting texture areas in images and determining the advantages and disadvantages of these methods and the problems that arise in the segmentation of texture areas in images. The purpose of the ongoing research is to use methods and determine the effectiveness of methods for the analysis of aerospace images, which are a combination of textural regions of natural origin and artificial objects. Currently, the automation of the processing of aerospace information, in particular images of the earth’s surface, remains an urgent task. The main goal is to develop models and methods for more efficient use of information technologies for the analysis of multispectral texture-type images in the developed algorithms. The article proposes a comprehensive approach to these issues, that is, the consideration of a large number of textural features by integral transformation to eventually create algorithms and programs applicable to solving a wide class of problems in agriculture.

Image processing systems are currently used to solve many applied problems. The article is devoted to the identification of negative factors affecting the growth of grain in different periods of harvesting, using a program implemented in the MATLAB software environment, based on aerial photographs. The program is based on the Law’s textural mask method and successive clustering. This paper presents the algorithm of the program and shows the results of image processing by highlighting the uniformity of the image. To solve the problem, the spectral luminance coefficient (SBC), normalized difference vegetation index (NDVI), Law’s textural mask method, and clustering are used. This approach is general and has great potential for identifying objects and territories with different boundary properties on controlled aerial photographs using groups of images of the same surface taken at different vegetation periods. That is, the applicability of sets of Laws texture masks with original image enhancement for the analysis of experimental data on the identification of pest outbreaks is being investigated.

In this study, an analysis of the spectral brightness coefficients (SBC) of agricultural crops in the steppe regions of Kazakhstan was carried out using remote field and space measurements during the growing season. The possibility of assessing structural changes in plants using near-infrared data was explored. An electronic database of corrected spectral data of SBC for the studied crops has been created. The results obtained confirm that the dynamics of SBC values reflect morphophysiological changes in crops during their growing season. Analysis of the seasonal dynamics of the spectral brightness of pests and diseases makes it possible to diagnose their species composition and the physiological state of plants. Spectrophotometric information obtained from satellite data of various crops can be used to build simulation models that provide scientifically based forecasts of the dynamics of the spatial distribution of the species composition of vegetation cover. The study highlights the potential of using subtle spectral differences to study the spatial distribution of different vegetation types and their ecological status. The results of the analysis of satellite information from Sentinel confirm the prospects of its use for assessing the morphophysiological state of agricultural crops using ground-based spectrometric calibration, as well as for predicting yields.