Research on Thermal Image Enhancement for Detecting Early Mechanical Damage in Apple
According to the characteristics of poor contrast and heterogeneous brightness of thermal image during the fruits evaluation by active infrared thermography technology, an image enhancement method was presented based on a hypothesis that the edge and central parts of fruits belong to different areas of interest. Red Fuji apple with mechanical damage was tested in this research. Sensed by a middle infrared (MIR) camera, the fruit thermal image was firstly converted into gray image. Through a transformation that yields an output image with a pre-specified histogram, the defect regions located in central parts were boosted. Meanwhile, an edge enhancement model produced by Multi-Scale Retinex (MSR) algorithm was created to restore edge information. With combination of contrast adjustment image and edge enhancement model, a gray correction image can be obtained. Test results reveal that the thermal images after being processed by this method show rich details and good contrast. The methodology can be also applied for other spherical objects.
Apple Defect Detection Mechanical Damage Thermal Image Image Enhancement
Jianmin Zhou Qixian Zhou Lili Shu Dongdong Xu
Institute of Optics-Mechatronics Technology and Application, East China Jiaotong University, Nanchang 330013, P. R. China
国际会议
南昌
英文
1031-1036
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）