Fastener recognition using combination of colour features with shape-based features and Zernike moments
Nur Diyanah Mustaffa Kamal, Nor'aini Abdul Jalil · 2016
This paper presents feature extraction techniques using shape-based features and Zernike moments combined with colour attributes. Features are extracted to classify 30 different fasteners which differ in term of size and colour. Red, green and blue channels of the images are used to extract the features for the colour based technique. For Zernike moments' technique, various orders and repetitions are used as descriptors. In term of shape-based technique, various pixel-based measurements are used such as major axis length, perimeter and solidity. Single hidden layer feed forward artificial neural network is used as the classifier. The experimental result shows shape-based technique combined with colour features yields a good result of 99.89% correct classification accuracy.