Accurate Segmentation Method of 3D Printed Image With Weak Edge Based on Window Optimization.

Saved in:

Bibliographic Details
Title:	Accurate Segmentation Method of 3D Printed Image With Weak Edge Based on Window Optimization.
Authors:	Zhong, Si¹ 13597320667@163.com, He, Shuxian² hsxqaq99@163.com, Bai, Yanli³ bayaly@guet.edu.cn, Li, Zhen² 18307852912@163.com, Li, Jinpeng² prclijinpeng@163.com, Liu, Yuxuan⁴ elowenwiththavery@163.com
Source:	Engineering Letters. Jul2026, Vol. 34 Issue 7, p2740-2746. 7p.
Subjects:	Edge detection (Image processing), Image processing, Three-dimensional printing, Signal denoising, Image quality analysis
Abstract:	Weak-edge 3D printed images commonly suffer from severe distortion and excessive noise points, making it difficult to enhance image quality through precise edge segmentation. To address this, an accurate segmentation method based on window optimization is proposed. First, a piecewise function is established to divide the image into distinct regions. The real-time state values of pixels within each region are calculated and input into the target window at weak-edge pixels and the noise-filtering window, thereby enabling precise and effective noise filtering. A random robust feature-based approach is employed to statistically analyze image characteristics. Global and local grayscale value features are extracted from the image, and the segmentation threshold with the highest fitness is set to achieve precise segmentation. Simulation experiments demonstrate that the proposed method effectively enhances image quality. During edge segmentation, the distribution of graphic elements across regions remains balanced. Under this segmentation approach, target points of image features exhibit relatively uniform arrangement, with no noticeable dispersion. [ABSTRACT FROM AUTHOR]
	Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Weak-edge 3D printed images commonly suffer from severe distortion and excessive noise points, making it difficult to enhance image quality through precise edge segmentation. To address this, an accurate segmentation method based on window optimization is proposed. First, a piecewise function is established to divide the image into distinct regions. The real-time state values of pixels within each region are calculated and input into the target window at weak-edge pixels and the noise-filtering window, thereby enabling precise and effective noise filtering. A random robust feature-based approach is employed to statistically analyze image characteristics. Global and local grayscale value features are extracted from the image, and the segmentation threshold with the highest fitness is set to achieve precise segmentation. Simulation experiments demonstrate that the proposed method effectively enhances image quality. During edge segmentation, the distribution of graphic elements across regions remains balanced. Under this segmentation approach, target points of image features exhibit relatively uniform arrangement, with no noticeable dispersion. [ABSTRACT FROM AUTHOR]
ISSN:	1816093X