In order to solve the problem that it is difficult to detect the early bruises of apple surface, an early bruises detection method of apple surface based on near infrared camera imaging technology and image threshold segmentation method was proposed. The near infrared image of apple samples was collected by T2SL near infrared camera, which had absolute advantages in the near infrared band imaging compared with other types of camera. The background of the near infrared image was segmented by Otsu method. The threshold of sound and bruise region segmentation was set based on the gray histogram of the image, and the bruise region of apple samples was extracted by morphological processing. The accuracy of the method was 88% for the sound samples, 90% for the samples after bruise, and 96% for the samples after 30 minutes of bruise. The early bruises detection of apple surface based on near infrared camera imaging and threshold segmentation did not need modeling learning, which was similar to an unsupervised discriminant analysis method. The results showed that the method was feasible for early bruises detection of apple surface, it can not only detect the early bruises of apple surface, but also can directly outline the location of the surface bruises, which can provide a fast and efficient method for real-time online detection of apple surface bruises.