Neural Networks for Image Recognition in Mobile Applications

The image recognition and pattern recognition on a mobile platform are getting more and more popular. Many of libraries and tools were created to make implementing new solutions easier. The goal of the paper was to present the analysis of selected machine learning algorithms for image recognition in mobile applications on the Android platform on the example of application that recognises the chosen images – tree leafs. The MLP (multilayer perceptron) artificial neural network was used as a tool to classify the objects. The program was implemented and trained in Python. The important part of the research was the image pre-processing: many of popular algorithms were tested, for example a mean filter or a Canny’s edges detector. The final result was the mobile solution that uses the learned model of MLP neural network to recognize a leaf on the photo.