Hazardous signs and fire exit signs classification using appropriate shape coding algorithm and BPN

This paper presents the hazardous signs and fire exit signs classification in vision-based fire protection and fire evacuation paths control system. The algorithm described here take an advantage of image sign features that their colors and shapes are very different from natural environments. The system is divided into three parts, first for image detection by CCD camera that is installed with user's cover head set. The camera is connected to user with their PDA and then sent this image data via on Wi-Fi Channel to fire protection control system center. The preprocessing process is used to reduce the noise effect and shape coding analysis with a continuous thinning algorithms are used in second part for reduced the sized of data and can be representatives for suitable features of image data to classify by an image binary data encoding algorithm. Finally, the Back Propagation Neural Network (BPN) techniques are used in image recognition and classification process and display the correct sign that meaning for suitable fire extinguishers and fire evacuation paths. By applying the present method, performance has been improved which more than 96% correctly in laboratory room. Some results from natural scenes are shown that system performance may be improved the capability to detect the image signs in longer range and more efficiency adjust in classification algorithms that can be support for real time capture image as VDO streaming.