Footprint key point intelligent extraction system based on four-region segmentation method

• Main Authors: ZHU MING, ZHANG YAN, XU CHANGKANG, ZHOU XUDONG, WANG NIAN
• Format: Patent
• Language: Chinese; English
• Published: 17.12.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a footprint key point intellignet extraction system based on a four-region segmentation method, relates to the technical field of image processing, and solves the technical problems of low efficiency and large error caused by field extraction depending on professionals in an existing scheme. According to the method, de-noising processing is carried out on the footprint image collected on site, and the brightness and contrast are adjusted, so that the quality of the image is improved; secondly, the background is unified, footprint contour features are extracted according to research requirements, and meanwhile, centralization and rotation operation is carried out on the image, so that the position and the inclination angle of an effective footprint area of the image are normalized into a unified standard; finally, the footprint image is divided through a region segmentation module, key points are extracted, and footprint biological parameters of the footprint image are calculated; compa