An Assistive Object Recognition System for Enhancing Seniors Quality of Life

This paper presents an indoor object recognition system based on the histogram of oriented gradient and Machine Learning (ML) algorithms; such as Support Vector Machines (SVMs), Random Forests (RF) and Linear Discriminant Analysis (LDA) algorithms, for classifying different indoor objects to improve quality of elderly people's life. The proposed approach consists of three phases; namely segmentation, feature extraction, and classification phases. Datasets used for these experiments, are totally consisted of 347 images with different eight indoor objects used for both training and testing datasets. Training dataset is divided into eight classes representing the different eight indoor objects. Experimental results showed that RF classification algorithm outperformed both SVMs and LDA algorithms, where RF achieved 80.12%, SVMs and LDA achieved 77.81% and 78.76% respectively.