PKU-Market-Phone

手机屏幕表面缺陷分割数据集此数据集包含3种类型的表面缺陷: 油污，划痕和斑点。每种类型的缺陷400个图像，总共1200个图像。缺陷是由我们模拟的工业环境制造的。图像由分辨率1920年 × 1080的工业相机收集。数据集分为train:validation:test = 6:2:2。数据集格式采用PASCAL VOC。

Mobile Phone Screen Surface Defect Segmentation Dataset
This dataset includes three types of surface defects: oil stains, scratches, and spots. There are 400 images for each defect type, totaling 1200 images in the entire dataset. The defects were generated in our simulated industrial environment. The images were captured by industrial cameras with a resolution of 1920 × 1080. The dataset is split into training, validation and test sets at a ratio of 6:2:2. The dataset follows the PASCAL VOC format.

AI搜集汇总

背景与挑战

背景概述

PKU-Market-Phone是一个手机屏幕表面缺陷分割数据集，专注于油污、划痕和斑点三种缺陷类型，共包含1200张高分辨率工业图像。数据集采用PASCAL VOC格式，并已按6:2:2的比例划分为训练集、验证集和测试集，适用于计算机视觉任务如缺陷检测和分割。