PNG

The "Dynamic Scenes" Dataset is provided for testing visual loop closure detection algorithms in highly dynamic scenes. It has a strong background in some crucial applications such as autonomous driving systems.

  • Transportation
  • Last Updated On: 
    Fri, 05/03/2019 - 15:06

    This dataset is a companion to a paper, "Segmentation Convolutional Neural Networks for Automatic Crater Detection on Mars" by DeLatte et al. These are the segmentation target files for the three targets described in the paper: solid filled, thicker edge, and thinner edge. 

  • Geoscience and Remote Sensing
  • Astronomy
  • Last Updated On: 
    Sun, 02/03/2019 - 10:54

    A sample of synthetic noise-free reference image created by combining multiple instances of structurally preserved cilia cross-sections. 

  • Medical Imaging
  • Digital signal processing
  • Last Updated On: 
    Thu, 11/08/2018 - 10:34
    Citation Author(s): 
    Amit Suveer, Hrushikesh Garud, Anca Dragomir, Ida-Maria Sintorn

    We collected real crack image data to test and analyze the image-based crack detection results. We used 18 images with 1920×1080 resolution sequentially numbered from 1 to 18. And we performed labeling operation to classify the crack image into crack and background regions. online for free use. For the selection of a crack region, we applied a simple rule of extracting a crack edge and selecting the segment matching the true value. The inner region of the selected crack edge (i.e.

  • Image Fusion
  • Last Updated On: 
    Thu, 11/08/2018 - 10:34
    Citation Author(s): 
    Cho Hyunwoo, Yoon Hyuk-Jin

    Datasets of confocal microscopy images of cardiomyocytes aimed at development of image recognition systems. Images of live and healthy cardiomyocytes with fluorescently stained sarcolemma were assigned into 5 classes according to their development stages. The least developed cardiomyocytes were considered to be at stage 1 (class 1) while the most developed ones were assigned stage 5 (class 5). All other images belong to a class 0.

  • Biomedical and Health Sciences
  • Digital signal processing
  • Last Updated On: 
    Thu, 11/08/2018 - 10:34
    Citation Author(s): 
    A. Zahradnikova jr., P. Skrabanek

    We make our dataset publicly avaiable. It consists of 50 H&E stained histopathology annotated images at the nuclei level. This dataset is ideal for those who want an exhaustive annotation of H&E breast cancer patient from a Tripple Negative Breast Cancer cohort.

  • Medical Imaging
  • Cancer Data
  • Last Updated On: 
    Thu, 11/08/2018 - 10:34
    Citation Author(s): 
    Naylor Peter; Laé Marick; Reyal Fabien; Walter Thomas;

    Machine learning is becoming increasingly important for companies and the scientific community. It allows us to generate solutions for several problems faced by society. In this study, we perform a science mapping analysis on the machine learning research, in order to provide an overview of the scientific work during the last decade in this area and to show trends that could be the basis for future developments in the field of computer science. This study was carried out using the CiteSpace and SciMAT tools based on results from Scopus and Clarivate Web of Science.

  • Computational Intelligence
  • Other
  • Last Updated On: 
    Thu, 11/08/2018 - 10:34
    Citation Author(s): 
    Juan Rincon-Patino, Gustavo Ramirez-Gonzalez, Juan Carlos Corrales