2025 Hoarding and INDoor cluttER (HINDER) Dataset

Motivation

Collecting and rating images of hoarding-related indoor clutter is difficult and labor-intensive. First, finding such images is very challenging. Although quite a few videos can be found on-line, one has to select frames that are sufficiently different from one another, field of view is sufficiently wide, no people are recognizable (privacy), logos are not obtrusive, etc. Furthermore, each image must be rated by a health professional to assign a CIR (Clutter Image Rating) value [R.O. Frost, G. Steketee. D.F. Tolin and S. Renaud]. This can be problematic since even professionals have sometimes challenges with precise assignment of a CIR value (e.g., the rating may be between a 4 and 5).

We have have expanded the HINDER-2018  dataset [Tezcan et al., 2018], which consists of 1,323 images of indoor clutter with highly unbalanced CIR class membership. The new dataset HINDER-2025 is balanced, with 200 images of indoor clutter per CIR class, for the total of 1,800 images, a 36% increase over the 2018 dataset.

Description

HINDER-2025 includes 1,800 images of different sizes, aspect ratios and visual appearance (lighting, contrast, compression artifacts). All images are in JPEG format, grouped into 9 folders (separate folder for each CIR class). The filename of each image includes the CIR class and a random hash string. The downloadable file is a single ZIP file containing all folders and images.

Dataset Download

You may use this dataset for non-commercial purposes. If you publish any work reporting results using this dataset, please cite the following paper:

Z. Sun, J. Muroff, and J. Konrad, “Classification of indoor clutter from images: Application to hoarding assessment,” in 33rd European Signal Processing Conference (EUSIPCO-2025), Palermo, Italy, Sept. 2025.

To access the download page, please complete the form below (tested only in Chrome).

Contact

Please contact [jkonrad] at [bu] dot [edu] if you have any questions.

Acknowledgements

We would also like to thank Boston University students for their help in collecting and rating images in this dataset.