Object recognition in images by human vision and computer vision

Object recognition plays a major role in human behaviour research in the built environment. Computer based object recognition techniques using images as input are challenging, but not an adequate representation of human vision. This paper reports on the differences in object shape recognition between human vision and computer vision. To this end, we explore an image-based recognition algorithm and a model-based recognition algorithm. Experiments were conducted using these two algorithms given images generated by Radiance lighting simulation software. The results reveal significant differences between human vision and computer vision given various conditions in the testing images and in the testing room