Image Processing

As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed.

219 views
  • Artificial Intelligence
  • Last Updated On: 
    Sun, 10/13/2019 - 17:08

    This dataset includes all letters from Turkish Alphabet in two parts. In the first part, the dataset was categorized by letters, and the second part dataset was categorized by fonts. Both parts of dataset includes the features mentioned below.

    • 72, 20 AND 8 POINT LETTERS
    • UPPER AND LOWER CASES

    The all characters in Turkish Alphabet are included (a, b, c, ç, d, e, f, g, ğ, h, ı, i, j, k, l, m, n, o, ö, p, r, s, ş, t, u, ü, v, y, z).

    222 views
  • Artificial Intelligence
  • Last Updated On: 
    Thu, 10/10/2019 - 02:45

    The Dataset

    The Onera Satellite Change Detection dataset addresses the issue of detecting changes between satellite images from different dates.

    1286 views
  • Computer Vision
  • Last Updated On: 
    Wed, 10/09/2019 - 08:34

    基于波动算法的快速视网膜分割

    -------------------------------------------------- -------------------------------------------------- -----------

    光电成像与测量技术实验室

    地址:中国天津市卫经路92号

    邮政编码:300072

    电话:+ 86-22-27404535传真:+ 86-22-27404535

    团队网站:http : //jyxy.tju.edu.cn/Precision/PEIT_1/index.html

    67 views
  • Image Processing
  • Last Updated On: 
    Sun, 01/12/2020 - 07:53

    Pedestrian detection and lane guidance 

    102 views
  • Computer Vision
  • Last Updated On: 
    Sat, 10/05/2019 - 16:56

    This dataset contains sheets of handwritten Telugu characters separated in boxes. It contains vowel, consonant, vowel-consonant and consonant-consonant pairs of Telugu characters. The purpose of this dataset is to act as a benchmark for Telugu handwritting related tasks like character recognition. There are 11 sheet layouts that produce 937 unique Telugu characters. Eighty three writers participated in generating the dataset and contributed 913 sheets in all. Each sheet layout contains 90 characters except the last which contains 83 characters where the last 10 are english numerals 0-9.

    156 views
  • Computer Vision
  • Last Updated On: 
    Fri, 10/04/2019 - 12:58

    Table1 present the peak-level activation point of 8 brain regions for all 1080 subjects.

    Table2 present the peak-level activation point of 8 brain regions for selected 893 subjects. 

     

    Supplementary data -RotL.rar present the SPM{T}map and extracted masks calculated with 2nd-level modeling analysis from RtoL fMRI data of subjects 1 to 50.

    Supplementary data -LtoR.rar present the SPM{T}map and extracted masks calculated with 2nd-level modeling analysis from LtoR fMRI data of subjects 1 to 50.

     

    14 views
  • Image Processing
  • Last Updated On: 
    Wed, 10/02/2019 - 02:08

    A paradigm dataset is constantly required for any characterization framework. As far as we could possibly know, no paradigmdataset exists for manually written characters of Telugu Aksharaalu content in open space until now. Telugu content (Telugu: తెలుగు లిపి, romanized: Telugu lipi), an abugida from the Brahmic group of contents, is utilized to compose the Telugu language, a Dravidian language spoken in the India of Andhra Pradesh and Telangana just a few other neighboring states. The Telugu content is generally utilized for composing Sanskrit writings.

    137 views
  • Computer Vision
  • Last Updated On: 
    Wed, 11/27/2019 - 07:22

    A benchmark dataset is always required for any classification or recognition system. To the best of our knowledge, no benchmark dataset exists for handwritten character recognition of Manipuri Meetei-Mayek script in public domain so far. Manipuri, also referred to as Meeteilon or sometimes Meiteilon, is a Sino-Tibetan language and also one of the Eight Scheduled languages of Indian Constitution. It is the official language and lingua franca of the southeastern Himalayan state of Manipur, in northeastern India.

    514 views
  • Computer Vision
  • Last Updated On: 
    Fri, 09/27/2019 - 08:25

    Multi-modal Exercises Dataset is a multi- sensor, multi-modal dataset, implemented to benchmark Human Activity Recognition(HAR) and Multi-modal Fusion algorithms. Collection of this dataset was inspired by the need for recognising and evaluating quality of exercise performance to support patients with Musculoskeletal Disorders(MSD).The MEx Dataset contains data from 25 people recorded with four sensors, 2 accelerometers, a pressure mat and a depth camera.

    324 views
  • Computer Vision
  • Last Updated On: 
    Tue, 10/01/2019 - 10:57

    Pages