Eye image segmentation method based on sclera region supervision

Abstract

The invention discloses an eye image segmentation method based on sclera region supervision, and mainly solves the problem of low segmentation precision of a traditional method. According to the scheme, the method includes the following steps: extracting high-dimensional features of a sclera area through a residual network; performing attention adjustment on the high-dimensional features of the original eye image by using the high-dimensional features; encoding the high-dimensional features of the adjusted original eye image to obtain encoded semantic features; improving the coding semantic features through cross-connection excitation, and inputting the coding semantic features into a decoder for decoding to obtain decoding semantic features; performing channel adjustment on the decoded semantic features, and outputting a preliminary segmentation result; and calculating the total loss of the initial segmentation result and the segmentation label, comparing the total loss with a set threshold value, judging whether all filters, encoders and decoders need to be optimized, and outputting a final segmentation result of the pupil, the iris and the sclera. The method improves the segmentation precision, and can be used for human eye positioning, blink detection, sight line estimation improvement and pupil change monitoring.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an eye image segmentation method, which can be used for human eye positioning, eye blink detection, improved line of sight estimation and fixation point estimation, and pupil change monitoring. Background technique [0002] The main task of eye image segmentation is to associate each pixel of the eye image with specific pupil, iris, sclera and other category labels, and finally output a semantic segmentation map with specific position information of each part of the eye. One of the most popular methods of existing semantic segmentation is to use the network structure of encoding and decoding. The encoding is realized by multi-layer convolution and pooling, that is, downsampling. Sampling, and finally get a full-resolution segmentation map with the same size as the original image. [0003] Tencent Healthcare (Shenzhen) Co., Ltd. discloses a patented technology "eye...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that the process of calculating the prior information is very time-consuming, and the specific interpretability of the above prior information is not strong, and there will be different prior information for eye images in real scenes. information, it is very difficult to calculate the prior information

However, there are two problems: one is that the adaptive threshold method it uses may require different settings for different samples, which affects the fine segmentation results of ellipse fitting, resulting in limited segmentation accuracy; the other is that this method does not make good use of the eye The characteristics of the iris and sclera in the external image except the pupil and the relationship between them reduce the segmentation efficiency

Images