Neural network application for thermal image recognition of low-resolution objects

作者：Fang Yi Chin^*; Wu Bo Wen

来源：Journal of Optics A: Pure and Applied Optics , 2007, 9(2): 134-144.

DOI：10.1088/1464-4258/9/2/003

• thermal image
• low resolution
• recognition
• neural network
• invariant moments

In the ever-changing situation on a battle field, accurate recognition of a distant object is critical to a commander's decision-making and the general public's safety. Efficiently distinguishing between an enemy's armoured vehicles and ordinary civilian houses under all weather conditions has become an important research topic. This study presents a system for recognizing an armoured vehicle by distinguishing marks and contours. The characteristics of 12 different shapes and 12 characters are used to explore thermal image recognition under the circumstance of long distance and low resolution. Although the recognition capability of human eyes is superior to that of artificial intelligence under normal conditions, it tends to deteriorate substantially under long-distance and low-resolution scenarios. This study presents an effective method for choosing features and processing images. The artificial neural network technique is applied to further improve the probability of accurate recognition well beyond the limit of the recognition capability of human eyes.

• 出版日期2007-2