Image Processing

This is the dataset for the paper 'SMPL-GPTexture: Scalable, Training-Free SMPL Texture Synthesis with World Knowledge Transfer from GPT via Geometry-Aware Projection'

Forest change detection

This dataset contains 9,548 high-quality annotated images for recognizing agricultural UAV spraying behaviors under diverse field conditions. It is constructed to address the lack of domain-specific datasets for operational state recognition in precision agriculture, where existing UAV datasets mainly focus on target localization in urban security or airspace management scenarios. Images were collected from 71 online videos covering real agricultural spraying operations and retain heterogeneous resolutions and shooting conditions to reflect real-world monitoring environments.

DataSet I includes images of Lymphocyte, Monocyte and Neutrophil. The numbers of these three groups of images are 3209, 15058 and 6203 respectively.

DataSet II comprises 300 precisely annotated semantic segmentation images of leukocytes. 

  
 

Ample multi-institutional routine clinically-acquired pre-operative multimodal MRI scans of glioblastoma (GBM/HGG) and lower grade glioma (LGG)

This dataset, titled HazeVideo-13, provides a compact collection of 13 short haze-affected video sequences designed for benchmarking and evaluating video dehazing algorithms. Each video clip is 5 seconds in duration and stored in standard AVI format, making it suitable for both academic research and model development. The dataset captures varying levels of haze intensity and visibility degradation, enabling researchers to test algorithm performance under diverse atmospheric scattering conditions.

Modern leather industries are focused on producing high quality leather products for sustaining the market competitiveness. However, various leather defects are introduced during various stages of manufacturing process such as material handling, tanning and dyeing. Manual inspection of leather surfaces is subjective and inconsistent in nature; hence machine vision systems have been widely adopted for the automated inspection of leather defects.

The Breast Cancer Histopathological Image Classification (BreakHis) is  composed of 9,109 microscopic images of breast tumor tissue collected from 82 patients using different magnifying factors (40X, 100X, 200X, and 400X).  To date, it contains 2,480  benign and 5,429 malignant samples (700X460 pixels, 3-channel RGB, 8-bit depth in each channel, PNG format). This database has been built in collaboration with the P&D Laboratory  – Pathological Anatomy and Cytopathology, Parana, Brazil (http://www.prevencaoediagnose.com.br).

This dataset contains high-resolution images of almond (Prunus dulcis) varieties collected for research on machine learning-based classification and varietal identification. The images were captured under controlled lighting conditions using a consistent setup to ensure uniform quality and minimal variability caused by external factors. Each image corresponds to a specific almond variety, and annotations include class labels representing the respective types.

This is the pcba dataset we have collected in actual industrial scenarios.