A Method for Assessing the Sharpness of Stitched Images

Abstract

The invention discloses a method for evaluating the clarity of spliced ​​images, which belongs to the technical field of image splicing and image quality evaluation, and relates to the field of computer vision, comprising the following steps: S1: generating a training data set and a testing data set. S2: Generate a convolutional neural network model. S3: Test dataset based on trained convolutional neural network. According to the output label of each block output by the convolutional neural network, the present invention calculates the average value of the output labels of all blocks of each spliced ​​composite image to be evaluated, and then calculates the average value of the output labels of all spliced ​​composite images under the same splicing algorithm as the The evaluation level of the quality of the splicing algorithm. The use of convolutional neural network can replace the cumbersome, a large number of artificial statistical scoring, and can accurately judge the clarity of the fusion area in image stitching, overcome the limitations brought by the single factor evaluation index, and is conducive to fully automatic Adapting to the realization of the image mosaic system has very important application value.

Description

technical field [0001] The invention belongs to the technical field of image splicing and image quality evaluation, relates to the field of computer vision, and in particular relates to a method for evaluating the clarity of spliced ​​images. Background technique [0002] With the development of the electronic information industry and technological progress, equipment that can acquire and record video information is becoming more and more popular. However, compared with the field of view of the human eye, the field of view of ordinary cameras is much smaller. How to effectively use computer technology to expand The range of the field of view of the camera to capture images and videos has attracted extensive attention from researchers. Image stitching technology can solve the problem that wide-field images cannot be generated due to the limitation of the viewing angle and size of imaging instruments such as cameras. There are two main solutions for existing image stitching te...

AI Technical Summary

Problems solved by technology

The existing evaluation methods all evaluate the splicing quality by observing the splicing seam with human eyes, but the method of human eye observation has large errors and cannot accurately evaluate the splicing quality of the image stitching algorithm

Images