An image automatic semantic segmentation method and system

By calculating the peak and valley values ​​of the image grayscale histogram, image semantic segmentation is automatically performed, which solves the problem of time-consuming and expensive manual labeling and achieves efficient image segmentation and recognition.

CN119579890BActive Publication Date: 2025-10-10SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202411623662.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-11-14
Publication Date
2025-10-10
Estimated Expiration
2044-11-14

AI Technical Summary

Technical Problem

In existing technologies, the annotation process of image semantic segmentation is time-consuming and costly, especially for large-scale datasets, where relying solely on manual annotation is inefficient.

Method used

Automated semantic segmentation is achieved by converting the image into a grayscale image, calculating the histogram, determining the maximum peak and valley values ​​as reference points and thresholds, and creating a mask layer to highlight the segmentation results.

Benefits of technology

Automatically calculates image grayscale peaks and valleys, simplifies the image segmentation process, is suitable for large-scale image data processing, and improves the accuracy of analysis and recognition.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application relates to the technical field of digital image processing, and particularly provides an image automatic semantic segmentation method and system, which has the following steps: S1, first, an image is converted into a gray image, and then a histogram of the obtained gray image is calculated; S2, a gray value corresponding to a maximum peak value in the histogram is determined as an initial reference point G1; S3, a square difference of each gray value and G1 is multiplied by a histogram value of the gray value, so that a distance weighted histogram M(g) is obtained; S4, a gray value corresponding to a valley value between two peak values is determined as a threshold T; and S5, a mask layer is created to highlight a segmentation result. Compared with the prior art, the application can significantly improve the accuracy of image analysis and recognition.
Need to check novelty before this filing date? Find Prior Art