A new enhancement method is proposed based on the characteristics of fundus images in this paper. Firstly, top-hat transform is utilized to weaken the background. Secondly, contrast limited adaptive histogram equalization (CLAHE) is performed to improve the uneven illumination. Finally, two-dimensional matched filters are designed to further enhance the contrast between blood vessels and background. The algorithm was tested in DIARETDB0 databases and showed good applicability for both normal and pathological fundus images. A new no-reference image quality assessment method was used to evaluate the enhancement methods objectively. The results demonstrated that the proposed method could effectively weaken the background, increase contrast, enhance details in the fundus images and improve the image quality greatly.
A new urine analysis core module based on high performance 32-bit microprocessor and high precision color sensor was presented. A novel optical structure and a specific circuit were applied to improve measurement precision and temperature was used to compensate for results in this core module. The information of urine test peice, such as all original data and color RGB value, reflectivity, semi-quantitative level, etc. can be output. The results showed that the measuring precision was about 95% or above with ideal stability and reliability using this presented core module, which can be conveniently applied in various urine analyzers, and can greatly decrease the cost of urine analyzers in development and production.