Scattered object recognition using Hu Moment invariant and backpropagation neural network
Nelly Indriani Widiastuti, Restu Suhendar · 2015
Scattered objects in a digital image have shape and different positions. It also allows some differences in translation, rotation, and scaling. Backpropagation neural network is one of machine learning algorithms that can recognize patterns and identify an object image based on the training provided. Implementation of neural network on image that has a variety of translation, scaling and rotation without prior manipulated require considerable number of samples. Even in terms of accuracy allows the occurrence of a failure in the decision to recognize the object. Solution algorithm that allows improvement of the problem is Hu Moment invariant. The result values of Hu moment invariant consists seven values that identify characteristics of a digital image. These values are independent of the translation, rotation and scaling. These values can be used as samples for each information object for input of neural network to recognize an object. Ming-Kuei Hu proposed this methode to identified twenty six characters in seperated manipulation. In this study, the unique value of the object produced by Hu moment invariant can be used for neural network input. This is proved by learning process and testing, learning parameter values and corresponding architecture, neural network can learn and produce fairly good.