An Image Positioning Method for Book Frame

Abstract

The invention discloses an image positioning method for a book frame, comprising steps: 1) book image preprocessing; 2) searching for the upper edge of the book frame; 3) rough positioning of the left and right end points of the upper edge of the book frame; 4) the left and right end points of the upper edge of the book frame Fine positioning; 5) Search for the lower edge of the book frame. The invention has the advantages of making full use of the color information of the color image, and having a good detection effect on low-intensity edges; using the straight line scanning method to complete the rapid positioning of the book edge and the rough positioning of the book edge endpoint; using the straight line fitting method to complete the book The precise positioning of the edge endpoints can also complete the precise positioning of the book border when the book edge outline is not fully extracted; it has the advantages of fast speed, high precision, good robustness and strong environmental adaptability, suitable for various colors, desktop backgrounds and Accurate positioning of book borders in lighting environments.

Description

technical field [0001] The invention relates to a book frame positioning method, in particular to a book frame image positioning method. Background technique [0002] With the development and popularization of computer technology, image processing technology is widely used in various fields of human production and life. Book recognition is one of the applications of image processing technology, which has been widely used in the field of early childhood education in recent years. Book border positioning technology is the most basic core technology in book recognition technology. Its positioning accuracy affects the book recognition accuracy, which is of great significance to the improvement of the performance of children's educational products based on book recognition technology. [0003] There are three main types of existing book frame location methods: (1) frame location methods based on Hough transform, according to the prior knowledge of books, use the principle of Hou...

AI Technical Summary

Problems solved by technology

[0003] There are three main types of existing book frame location methods: (1) frame location methods based on Hough transform, according to the prior knowledge of books, use the principle of Hough transform to detect straight lines to find out the straight line in a specific direction, and complete the book frame location. The method takes up a lot of memory during calculation, and is easily disturbed by the content and background of the book, and the positioning accuracy of the book border is low

(2) The frame positioning method based on the maximum connected domain, through the detection of the maximum connected domain of the image, obtains the book area, and then uses the straight line fitting method combined with the prior knowledge of the book to screen the edge straight line to realize the positioning of the book frame. The real-time performance of the method is not good, and it is easily affected by the interference connected domain, and the positioning accuracy of the book frame is easily affected by the background

(3) Edge-based border positioning method, using edge extraction algorithm to extract the edge contour of the book, and then using the line fitting method combined with the prior knowledge of the book to screen the edge straight line to realize the positioning of the book border. This kind of method is more real-time Good, but for books with low light intensity or unevenness, the frame positioning effect is poor, and it is easily disturbed by the background

Images