计算机科学
分割
异常检测
人工智能
模式识别(心理学)
管道(软件)
卷积神经网络
比例(比率)
任务(项目管理)
特征(语言学)
图像分割
异常(物理)
尺度空间分割
编码
特征提取
产品(数学)
聚类分析
缩放比例
计算机视觉
深度学习
基于分割的对象分类
人工神经网络
图像(数学)
目标检测
质量(理念)
噪音(视频)
机器学习
公制(单位)
数据挖掘
作者
Stefano Samele,Francesco Attorreb,Matteo Matteuccib
标识
DOI:10.1016/j.dsp.2025.105613
摘要
Detecting anomalies in product images is a critical task in industrial quality control, where even subtle defects can have operational and financial impact. However, deploying anomaly detection algorithms in real-world industrial scenarios remains challenging, particularly when products are large, complex, or captured at high resolution. Many existing methods struggle to scale effectively while maintaining precision. This work aims to develop an algorithm that can effectively scale to larger, more complex objects. The method, SADSeM (Scaling Anomaly Detection with Segmentation Models), is based on classic convolutional neural networks for segmentation, such as Mask-RCNN. Thanks to these models’ ability to learn and encode an object’s structure, we can design a pipeline that uses both their segmentation maps and feature embeddings to carry out unsupervised anomaly detection. As the segmentation task is effectively solved by these models independently of image size, we scale to higher-resolution images with more effectiveness than competitors, while maintaining competitive results in simpler scenarios.
科研通智能强力驱动
Strongly Powered by AbleSci AI