| Abstrakt: |
The technique of modifying an image to make it better suited for a certain use than the original image is known as image enhancement. Digitalized picture enhancement systems provide numerous choices for improving image visual quality. Imaging modalities, observation settings, and other factors all have a substantial impact on the appropriate choosing of various methodologies. The Fractional Pelican Crow Search Algorithm improved SQA (FPCSO_ enhanced SQA) is a novel image enhancement technique for histopathology imaging of uterine tissue that is provided here. The database is initially generated, and the image is forwarded to the pre-processing phase. In order to reduce noise and enhance image quality, the median filter is employed in image pre-processing. Additionally, image enhancement is done utilizing the Pelican Crow Search Algorithm-trained Multiple Identities Representation Network. After the image enhancement, the tissue segmentation is performed using proposed segmentation quality assessment network, where parameter selection is based on Deep Convolutional Neural Network (DCNN). Here, DCNN is trained using proposed FPCSO algorithm. Accordingly, proposed FPCSO approach is newly integrated by the combination of Pelican Optimization Algorithm, Crow Search Optimization and Fractional calculus. Furthermore, FPCSO-enhanced SQAreached best consequences with maximal Peak signal-to-noise ratio (PSNR) of 49.574 dB, minimum Mean Square Error of 0.975, and minimum degree of distortion of 0.061 dB, correspondingly. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink