Experiment Design Sketch Image Classification Dataset

In the field of industrial manufacturing, the design process often relies on a large number of design sketches that need to be quickly converted into actual engineering designs during the subsequent manufacturing stages. However, manually processing these sketches is often time-consuming and prone to errors, currently relying mainly on manual labeling and conversion by designers, which is inefficient and unstable. Existing automation solutions are mostly limited to simple graphic recognition and difficult to accurately handle complex design sketches. The Experiment Design Sketch Image Classification Dataset aims to improve automated recognition techniques by using high-quality, large-scale annotated sketch images to help solve key challenges in sketch recognition and classification. Data collection involves scanning design sketches using high-resolution scanners to ensure image quality under conditions of no reflection and uniform light source. Quality control measures include multiple rounds of annotation verification and consistency checks, and expert review to ensure the precision and consistency of annotations. The annotation team consists of 30 professionals with design backgrounds. Data preprocessing includes image denoising, contour enhancement, and size normalization, stored in JPG format, organized into categories using a directory structure. The annotation accuracy of this dataset exceeds 98%, maintaining a high degree of consistency and integrity. By introducing semi-automated annotation tools and data augmentation algorithms, the accuracy and robustness in classification tasks are enhanced. Experiments show that the recognition system applying this dataset can reduce sketch processing time by more than 30%, improving the efficiency of design and manufacturing. Compared to similar datasets, this dataset offers higher annotation accuracy and a more diverse range of sketch types, covering multiple design scenarios with strong scalability and generality.