A Comparative Performance Analysis for Classification of Real-Time Illumination Images Using Histogram Driven Euclidean Distance and Intersection Technique

Illuminance imaging based on lux sensor measurements has emerged as an effective alternative to camera-based methods, particularly in environments where optical imaging is impractical or limited. Converting lux data into illumination images provides a lightweight means of visualizing spatial lighting patterns; however, reliably classifying these images remains challenging due to variations in indoor geometry, sensor motion, and non-uniform lighting conditions. These factors often reduce the accuracy of conventional similarity or distance-based classification approaches. This study investigates 2 histogram-driven techniques for classifying real-time illumination images: the histogram intersection method and the histogram Euclidean distance method. A wireless sensing platform was developed by integrating an illuminance sensor with an infrared transceiver and a microcontroller communicating via the I2 C protocol. As RF-operated mobile unit traversed the indoor test environment, continuous lux measurements were acquired and converted into grayscale illumination images for subsequent analysis. A comparative performance assessment demonstrates that the histogram Euclidean distance method delivers higher classification accuracy and greater consistency than the Histogram Intersection approach. The results highlight the potential of histogram-based lux-to-image classification as an efficient tool for real-time illuminance assessment and support its broader applicability to smart lighting, indoor monitoring, and energy-aware lighting control systems.