Download Page

This page lists technical reports, code and research data that are available to the public. To download, please complete the Release Agreement and email it to phung@uow.edu.au.

• MATLAB Library for Convolutional Neural Network
  
  This MATLAB library, developed by us, can be used to create, simulate and train convolutional neural networks. Convolutional neural network, initially proposed by LeCun, is widely used in image pattern recognition. It is based on three key architectural ideas of local receptive fields, weight sharing, and sub-sampling in the spatial domain.
  
  Technical report | Download

• Face and Skin Detection Database
  The Face and Skin Detection (FSD) Database is created to support research on skin segmentation and face detection. It contains 4,000 colour images that are diverse in terms of the background scenes, lighting conditions, and face and skin types. The lighting conditions include indoor lighting and outdoor lighting; the skin types include whitish, brownish, yellowish, and darkish skins. To provide the ground-truth, all images are meticulously segmented for face regions and skin regions. The skin segmented images consist of all exposed skin regions such as facial skin, neck, arms, and hands.
  
  Description | Download

• UOW 3-D Range Dataset
  The UOW 3-D Range Dataset is created to support research on scene segmentation and pedestrian classification. It contains 220 images for scene segmentation and 2000 images for pedestrian classification. The data set was acquired using a time-of-flight (TOF) range camera SwissRanger SR4000, produced by MESA Imaging.
  
  Description | Download