Instant segmentation and feature extraction for recognition of simple objects on mobile phones

Object detection and recognition algorithms are an integral part of the architecture of many modern image processing systems employing Computer Vision (CV) techniques. In this paper we describe our work in the area of segmentation and recognition of simple objects in mobile phone imagery. Given an image of several objects on a structured background, we show how these objects can be segmented efficiently and how features can be extracted efficiently for further object recognition and classification. We prove the algorithms presented are useful given a set of test cases, and we show that the algorithms discussed can be used for instant object segmentation and recognition in a real-world application on ordinary off-the-shelf smartphones.