Design Of The Digital Ophthalmoscope And Research On The Diagnosis Of Lesion Fundus Images

Eye are closely related with body organs,symptoms of fundus diseases can reflect the health of some important organs,so ophthalmic examination is very necessary for each person.The fundus examination equipment and the diagnosis of lesion fundus images are two important contents in ophthalmic examination,with the development of digital technology,the traditional direct ophthalmoscope and manual analysis of fundus image can not meet the requirements,this paper focuses on the two aspects,a digital direct ophthalmoscope is designed and an automatic detection algorithm for the diabetes retinopathy exudate is presented.The digital direct ophthalmoscope is based on the traditional direct ophthalmoscope which is added with light splitting module and MT9D111 image sensor,it uses CC3200 as the microcontroller which can send fundus images to the remote QT client to display and store by WiFi.It realized the visual observation and digital display.Furthermore,the digtial direct ophthalmoscope has the advantages of simple structure,convenient operation,low cost and high practicabilityAiming to reduce the residual error caused by ineffective image enhancement and the false detection caused by incomplete removal of interference regions existing in common morphology-based exudates detection methods,this paper proposes an automated method based on mathematical morphology,which mainly improves the preprocessing of fundus images and the detection of interference regions like otpic disc.From the testing results on the new public dataset of e-ophtha EX,the proposed method achieves sensitivity of 91.7%,specificity of 94.6% on the exudate level and sensitivity of 100%,specificity of 88.6% and accuracy of 95.1% on the image level.