Abstract
Image target recognition is realized by lossless compression of multi-scale fusion saliency color image features. A lossless compression algorithm of multi-scale fusion saliency color image features based on improved particle swarm optimization algorithm is proposed. Firstly, the collected multi-scale fusion saliency color images are preprocessed by wavelet denoising, and then RGB-D saliency detection is carried out on the noise-reduced and purified multi-scale fusion saliency color images. Laplacian contrast is used as pheromone for information combination optimization and fusion, adaptive weight balanced segmentation method is used to extract the visual characteristics of salient objects of multi-scale fused salient color images, and improved particle swarm optimization algorithm is used to realize feature lossless compression through global contrast information fusion, particle swarm evolution and information fusion. Finally, the performance test is carried out through simulation experiments. The results show that the output peak signal-to-noise ratio of the feature lossless compression of multi-scale fusion saliency color images with this method is higher, and the root mean square error is smaller, which improves the feature point detection and recognition ability of feature lossless compression.
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 callDisclaimer: 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.
