RESUMEN
The machine-driven products processed by CNC machine tools are divided into multiple parts, which are often transmitted to unqualified processing crystals due to the error of the part's posture, thus affecting the projection effect. Aiming at handling this problem, we, in this work, propose a method for locating and correcting machine capabilities based on bicycle visual recognition. The robot obtains coordinates and offset points through the vision system. In order to satisfy the requirement of fast sorting of the robot parts, a robot species method (BAS-GA) that supports machine vision and improved genetic algorithm rules is proposed. The rank method first preprocesses the part copies, then uses the Sift feature twin similarity notification algorithm to filter the part idols, and finally uses in-law deformation to place the target parts. Afterward, an particular model is built for the maintenance of the nurtural skill, and the mathematical mold is solved using the BAS-GA algorithmic program authority. The close trail of the robot is maintained to manifest the marijuana of the robot. Experimental inference have shown that the BAS-GA algorithm rule achieves the optimal conclusion similar to the pseudo-annealing algorithmic program plant. Meanwhile, the genetic algorithm rule is modified ant settlement algorithm program. Knife sharpening was also reduced by 7%, inferring that this process can effectively improve the robot's action success rate.
RESUMEN
Generative adversarial network (GAN)-guided visual quality evaluation means scoring GAN-propagated portraits to quantify the degree of visual distortions. In general, there are very few image- and character-evaluation algorithms generated by GAN, and the algorithm's athletic ability is not capable. In this article, we proposed a novel image ranking algorithm based on the nearest neighbor algorithm. It can obtain automatic and extrinsic evaluation of GAN procreate images using an efficient evaluation technique. First, with the support of the artificial neural network, the boundaries of the variety images are extracted to form a homogeneous portrait candidate pool, based on which the comparison of product copies is restricted. Subsequently, with the support of the K-nearest neighbors algorithm, from the unified similarity candidate pool, we extract the most similar concept of K-Emperor to the generated portrait and calculate the portrait quality score accordingly. Finally, the property of generative similarity that produced by the GAN models are trained on a variety of classical datasets. Comprehensive experimental results have shown that our algorithm substantially improves the efficiency and accuracy of the natural evaluation of pictures generated by GAN. The calculated metric is only 1/9-1/28 compared to the other methods. Meanwhile, the objective evaluation of the GAN and human consistency has increased by more than 80% in line with human visual perception.