The research of image segmentation methods for interested area extraction in image matching guidance

摘要

The extraction of Region of Interest (ROI) is an important information guarantee in the application of imaging matchingguidance, which directly affects the acquisition probability and matching accuracy of the target. Image segmentation is animportant method to extract the Region of Interest of the target. Based on image segmentation algorithm, histogramequalization and morphological filtering, this paper proposes an effective image processing method to extract the Regionof Interest of the target. A variety of image threshold segmentation methods are applied to the actual processing flow,and their segmentation performance is compared and analyzed. Some image segmentation methods are obtained, whichare suitable for target region extraction in template image preparation and target potential region location in matchingrecognition. Preliminary localization of visible remote sensing images is carried, using color information, to obtainlocal regions, then enhance the image using histogram equalization method, finally morphological filtering is used toremove the edge noise. The Otsu method and Kittler minimum error method are processed in parallel, then thesegmentation results are fused, and the evaluation indexes such as area constraint, similarity and contrast are filtered toobtain the target region .Tests have been done with visible image and infrared image in this paper. The result indicates thatthe effectiveness of the morphological filter is more obvious after histogram equalization for the original image. Besides,the Otsu method and Kittler minimum error method are processed in parallel, then the segmentation results are fused toget preciser Region of Interest, thus ensuring the accuracy and timeliness of imaging matching guidance.