Detection of mechanical defects in fruits is very important for quality inspection systems.Bruising is defined as damage of fruits tissue as a result of external forces which cause physical changes of texture and chemical changes of color, smell and taste.However, the fruits with early mechanical damage which has no apparent changes of color, smell and taste cant been identified by the human eye.So it will lead to big economic losses result from infection of microbes and pulp rottenness.At present, defect detection in fruits in our country has been predominantly performed manually or by visible spectrum imaging systems, which are not capable of effectively distinguishing fruit with mechanical damage which occur a short time before inspection.Aiming at above problems, the infrared thermography nondestructive technique was introduced in this paper for addressing it.According to the specific situation of China, Kuerle pear which is thinly peeled and rich in juice was chosen.In order to obtain the different damage degree of the early mechanical damage, the process of the mechanical damage was simulated in the laboratory.The well-preserved sample was been dropped vertically from 0.7m high and scratched by the tools with edges and comers to acquire the early mechanical damage.The sample was stored for 12 h at 16℃.Ten minutes before the experiment, the sample was taken out and placed at the 20℃ and at 50% relative humidity for the uniform and stable experimental conditions of the sample.In the experiment, we applied the thermal wave excitation to enhance the temperature difference between the sample and background.So two 250W infrared lamps were placed on both left and right sides of the sample.And the distance from the thermography to the sample was 0.15m and the position of thermal imager was adjusted for the moderate sample image.Using the infrared thermography system, the non-destructive detection mechanism of infrared thermography of fruit was researched and a heat transfer model of one-dimension unsteady state heat conduction equation for evaluating the cooling properties of spherical fruits was applied to analyze the temperature behavior within different regions of pears in thermal images and the temperature behavior within different regions of pears in thermal images.The experiments results revealed that the features of level temperature profile of apples in thermal images could be as an effective method to identify different mechanical damages.According to the curve of the time and temperature, it showed that the temperature of lesions had a 0.4-1.3℃ higher than the normal area, especially when the bruise cant be observed by naked eyes, but it can be detected by thermography.Next a non-uniformity correction method based on histogram matching and Single-Scale-Retinex algorithm under low scale was applied to highlight the contrast of raw thermal images and the edges of fruits in raw thermal images for the purpose of image correction.Then the method of threshold segmentation was adopted and extracting contour was used for image segmented.The result indicates the accurate detection rate of sound pears can reach to 82%, and the accurate detection rate of defective pears is still over 79% after thresholding, which can be well used in fruit early mechanical damages detection.