Using “Just Noticeable Difference” to Automate Visual Inspection of Displays According to Human Visual Perception
Visual display testing is rapidly being automated using systems that are capable of objectively quantifying visual qualities like brightness, color, and contrast of displays.
Human perception is the ultimate standard for determining the visual quality of a device. However, the use of human inspection as a quality control method for development or production of devices is problematic because of the statistical variation between observers. Human vision is subjective, unquantifiable, and difficult to replicate. This variability may increase the risk of accepting defective devices or failing good devices—both of which add cost to the manufacturing process. Human inspection also lacks detailed quantitative information about defect types and occurrences, especially since human observers tend to only classify the most obvious defects. This has implications when evaluating devices that have a predominantly visual impact—like displays. What’s more, displays have become the pivotal user interface in consumer devices, from televisions to smartphones to automotive interiors, so quality control measures that take human visual experience into account are particularly important in display manufacturing.