Abstract
A genetic algorithm has been developed that implements the automatic selection of operations for processing complex structured images at the stage of localization of point objects. The algorithm is distinguished by the representation of a set of operations in the form of a variable-length chromosome, combining the performance of both halftone and binary morphological transformations and filters, a developed fitness function that takes into account the recall and IoU measure together, and a set of genetic operators (crossover and special types of mutation) corresponding to the task. Dilation, erosion, opening, closing, and skeletonization were studied as morphological operations. Clipping by area, eccentricity, and dimensions of the major and minor axes of the equivalent ellipse were used as filters. The genetic algorithm was launched and experimentally tested on scanned topographic maps of the USSR from 1965−1982, as typical representatives of images with a complex structure, together with sets of morphological operations obtained manually to determine objects of the “elevation mark” type. The quality criteria were the proportion of localized pixels, the number of missed images, and the processing time. For training on multiple images, the fitness function was modified in two ways: soft (averaging calculation for all images) and hard (zeroing the value of fitness function with a decrease in recall on at least one training image). The hard calculation of the fitness function turned out to be more effective, the final set of operations consists of 10 operations with a decrease in the number of localized pixels by 2,6 times. The results show that the use of a genetic algorithm for the selection of localization operations makes it possible to reduce the total number of localized pixels with reducing the overall operating time, taking into account the recognition stage, which allows us to conclude that it is consistent for image processing.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Vestnik komp'iuternykh i informatsionnykh tekhnologii
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
