The invention discloses a face super-resolution reconstruction method based on deep learning, and aims to utilize the deep learning technology to train low resolution face data, thus obtaining a mapping function from the low resolution face to the high resolution face; the technical keys comprise the following steps: 1, extracting key points of a training face data set; 2, calculating a face angleaccording to the extracted key points, and selecting a relatively right face image; 3, correcting the relatively right face image; 4, segmenting the corrected face image into the left eyebrow, the left eye, the right eyebrow, the right eye, the nose and the mouth, and respectively training said parts; 5, super-resolution processing the eyebrow, eye, nose and mouth images, super-resolution processing the face image, and combining said images so as to obtain the final super-resolution face image. The face super-resolution reconstruction method based on deep learning can effectively improve theobtained face image quality without changing the imaging system hardware equipment.