Abstract

The foundation of detection relies on the surface micro-defect images of KDP, and the effectiveness of the detection model depends on the quality of these images. Higher quality images can pinpoint the shape details and boundary features of defects, thereby enhancing the overall detection capability.

Surface micro-defect images of KDP crystals were captured using an industrial camera with a resolution of 2592×1944 pixels in the laboratory. To address the transparency of KDP crystals, a pure black pad was placed beneath them. Illumination was provided by a ring light source positioned between the crystals and the optics, maintaining a fixed distance of 8mm from the crystals and 65mm from the optics.

A total of 338 micro-defect images were obtained under conditions free from external light interference. Analysis revealed 240 micro-craters and 200 micro-cracks in these images.

Instructions:

Firstly, annotate each photo in the dataset using LabelImg. After annotation, an XML file will be obtained for each photo in the dataset. Then, use Python to convert these XML files into TXT files. Finally, select 80% of the photos and corresponding TXT files as the training set, and the remaining 20% as the validation set.

Comments

Thanks for the dataset!

Submitted by Seymur Hasanov on Sat, 04/13/2024 - 22:19

need datset for my project

Submitted by Mimansa Sinha on Sat, 06/15/2024 - 06:30

Dataset Files

Files have not been uploaded for this dataset

Datasets

Standard Dataset

Images of micro-craters and micro-cracks on the surface of KDP crystals

Abstract

Comments

Dataset Files

QUESTIONS?