United States Government Publishing Office publisher pbl distributor dst United States Commerce Department National Institute of Standards and Technology (NIST) author aut Government Organization Franaszek, Marek. author aut text government publication eng GOVPUB Executive Agency Publications executive 2023-10-27 Commerce Department 2022-03-25 monographic Withdrawal deposited born digital 1 digital object pages C 13. https://www.govinfo.gov/app/details/GOVPUB-C13-0e8a4245994cd420dcff13e94ff3855a P0b002ee1c1bb3fc1 on1389890325 (OCoLC)1389890325 DGPO 2023-10-27 2026-06-27 GOVPUB-C13-0e8a4245994cd420dcff13e94ff3855a machine generated eng fdlp C13 GOVPUB-C13-0e8a4245994cd420dcff13e94ff3855a 0e8a4245994cd420dcff13e94ff3855a GOVPUB NIST Technical Notes NOTE: THE “DATE ISSUED” ABOVE MAY DEFAULT TO JANUARY 1ST OF A GIVEN YEAR. TO THE VIEW THE MOST ACCURATE DATE OF ISSUE, REVIEW THE TITLE PAGE OF THE PUBLICATION. Studies or reports which are complete in themselves but restrictive in their treatment of a subject. Analogous to monographs but not so comprehensive in scope or definitive in treatment of the subject area. Often serve as a vehicle for final reports of work performed at NIST under the sponsorship of other government agencies. National Institute of Standards and Technology Commerce Department. National Institute of Standards and Technology. 2022 2022-03-25 https://www.govinfo.gov/app/details/GOVPUB-C13-0e8a4245994cd420dcff13e94ff3855a https://www.govinfo.gov/content/pkg/GOVPUB-C13-0e8a4245994cd420dcff13e94ff3855a/pdf/GOVPUB-C13-0e8a4245994cd420dcff13e94ff3855a.pdf 2D images Databases Image segmentation Machine learning Object recognition Training machine learning algorithms Franaszek, Marek. creator Franaszek, Marek. National Institute of Standards and Technology (U.S.) Engineering Laboratory mdu U.S. Dept. of Commerce, National Institute of Standards and Technology 2022-03-25. Withdrawal monographic 1 online resource (40 pages) : illustrations (color) text technical report eng Image segmentation is the first step in a complex process of object recognition. This report presents a method to gauge the difficulty of segmentation by calculating a scalar parameter Q for an image. This parameter depends on a distribution of the intensity of the grayscale image and the distribution of the clustering of pixels. It is assumed that images with a smaller number of clusters are easier to segment than images with a large number of clusters. Since segmentation precedes any human perception and categorization, the distribution of parameter Q introduced in this study may be useful in characterizing the variability of images collected in a training database for the development of object recognition algorithms which use Machine Learning (ML) methods. Parameter Q can be especially useful for building a representative dataset of images for training ML algorithms. To demonstrate a link between particular values of Q and different segmentation conditions, a few grayscale images were distorted by some common transformations (like Gaussian noise, median filtering, reduction in grayscale) and the corresponding values of parameter Q were calculated. To demonstrate a possible use of the parameter Q on data other than grayscale images, depth images of flat planar targets taken by two depth cameras were also processed. Marek Franaszek. March 2022. Title from PDF title page (viewed January 4, 2023). Includes bibliographical references. Approved by the NIST Editorial Review Board on 2022-03-03 Mode of access: World Wide Web. Systems requirements: Adobe Acrobat PDF reader. Databases Image segmentation Machine learning Object recognition 2D images Training machine learning algorithms https://doi.org/10.6028/NIST.TN.2207