Enhancing Shape Perception and Segmentation Consistency for Industrial Image Inspection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Mao, Guoxuan, Cao, Ting, Li, Ziyang, Dong, Yuan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910958701510656
author Mao, Guoxuan
Cao, Ting
Li, Ziyang
Dong, Yuan
author_facet Mao, Guoxuan
Cao, Ting
Li, Ziyang
Dong, Yuan
contents Semantic segmentation stands as a pivotal research focus in computer vision. In the context of industrial image inspection, conventional semantic segmentation models fail to maintain the segmentation consistency of fixed components across varying contextual environments due to a lack of perception of object contours. Given the real-time constraints and limited computing capability of industrial image detection machines, it is also necessary to create efficient models to reduce computational complexity. In this work, a Shape-Aware Efficient Network (SPENet) is proposed, which focuses on the shapes of objects to achieve excellent segmentation consistency by separately supervising the extraction of boundary and body information from images. In SPENet, a novel method is introduced for describing fuzzy boundaries to better adapt to real-world scenarios named Variable Boundary Domain (VBD). Additionally, a new metric, Consistency Mean Square Error(CMSE), is proposed to measure segmentation consistency for fixed components. Our approach attains the best segmentation accuracy and competitive speed on our dataset, showcasing significant advantages in CMSE among numerous state-of-the-art real-time segmentation networks, achieving a reduction of over 50% compared to the previously top-performing models.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14718
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Shape Perception and Segmentation Consistency for Industrial Image Inspection
Mao, Guoxuan
Cao, Ting
Li, Ziyang
Dong, Yuan
Computer Vision and Pattern Recognition
Artificial Intelligence
Semantic segmentation stands as a pivotal research focus in computer vision. In the context of industrial image inspection, conventional semantic segmentation models fail to maintain the segmentation consistency of fixed components across varying contextual environments due to a lack of perception of object contours. Given the real-time constraints and limited computing capability of industrial image detection machines, it is also necessary to create efficient models to reduce computational complexity. In this work, a Shape-Aware Efficient Network (SPENet) is proposed, which focuses on the shapes of objects to achieve excellent segmentation consistency by separately supervising the extraction of boundary and body information from images. In SPENet, a novel method is introduced for describing fuzzy boundaries to better adapt to real-world scenarios named Variable Boundary Domain (VBD). Additionally, a new metric, Consistency Mean Square Error(CMSE), is proposed to measure segmentation consistency for fixed components. Our approach attains the best segmentation accuracy and competitive speed on our dataset, showcasing significant advantages in CMSE among numerous state-of-the-art real-time segmentation networks, achieving a reduction of over 50% compared to the previously top-performing models.
title Enhancing Shape Perception and Segmentation Consistency for Industrial Image Inspection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.14718