Papers › CID: Cow Images Dataset for Regression and Classification
CID: Cow Images Dataset for Regression and Classification
Mobasshir Bhuiya Shagor, Md Zahidul Haque Alvi, Khandaker Tabin Hasan
Cattle livestock trading is scaling with exponential growth and managing this scaled production and procurement has become a huge challenge for the industry. With a vision to solve these challenges with emerging technologies and state-of-the-art techniques from computer vision, we tried to develop a large possible dataset that is labeled and accurate so that our research community can build their novel models or finetune existing ones without the hassle of data collection. We developed our cow images dataset of 17,899 images with vitals (sex, color, breed, feed, age, teeth, height, weight, price, size) which can be used for both classification and regression. We are also contributing baseline models demonstrating how this dataset can be used for regression and classification. These baseline models consist of multi input-output network (1 input - 2 outputs; 3 outputs; 4 outputs) to classify and regress cattle livestock vitals among them (1 input - 2 outputs) have the best accuracy of 75% and 67% respectively for age and breed with the minimum loss. Estimating or predicting cattle livestock vitals is an open research area and our cow images dataset and baseline models are going to play a vital role towards further research opportunities. The repository link for this paper is attached here https://github.com/bhuiyanmobasshir94/CID
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections