An algorithm for object identification on the color images ofintegrated circuit layout is proposed. The layout image is represented as set ofpicture areas that have slightly different conditions ofphotographing. The identification algorithm based on segmentation and twosteps image filtration using mathematical morphology and semantic approach. It can be appliedfor the tasks of integrated circuits redesign and automated visual inspection of integrated circuits and photomask production

No abstract

To control the process parameter settings and to visually inspect the process quality, a monitoring system for the sintering process was designed. The monitoring of the sintering process is based on measurements of the maximum surface temperature and the temperature distribution at the sintering zone by the spectral ratio method. Software and hardware for adaptive process control of powder solids SLS were developed.

To identify and classify objects on images obtained using UAV imaging and orbital-based imaging, a neural network classification model based on the use of an autoencoder and built on the architecture of an ensemble of multilayer perceptrons is proposed. Additionally, at the stage of highlighting informative features, is added a color information, which is based on the per-channel histograms and is invariant to the scale and rotations of the image. The model is implemented using the Keras library. The use of the proposed model for classification into four classes: “Fire”, “Smoke”, “Vegetation” and “Buildings”, allows to achieve a classification accuracy above 99%.