Background: Nowadays, the latent power of technology, which can offer innovative resolutions to disease diagnosis, has awakened high-level anticipation in the community of patients as well as professionals. An easy-touse mobile app is developed by us, which is purposefully intended for those patients with glaucoma. Methods: A mobile App has been invented for smartphones for the convenient use wherever and whenever. The corresponding experiments carried out by public retinal image database and real captured clinical data reveal the ideal classification accuracy of the App. Also, user feedback evaluation is also carried out in terms of performance test as well as and users' experience. Results: For clinical test using Yanbao App, we found 274 patients for the identification with 648 retinal images to be evaluated by glaucoma classification. Of the 243 glaucoma patients, 191 were screened out with an accuracy of 0.7860 (sensitivity); the number of non-glaucoma patients was 310 of 405, and the accuracy reached 0.7654 (specificity).`The total Accuracy amounted to 0.7731, and the result is close to the test performance obtained on public dataset ORIGA and DRISHTI-GS1. Conclusions: Yanbao App can be applied as an innovative approach exploiting mobile technology to enhance the clinicians' efficiency and a balanced medical resources as well as a provided better tiered medical service system.

A new image dehazing algorithm based on adaptive sky region is proposed in this paper, which shows good fidelity in sky region and satisfying visual effect in non‐sky region. For robust sky segmentation, we propose a rough‐to‐fine method that can make a balance between efficiency and accuracy. Considering distribution of haze is inconsistent, we divide the input image into three parts and calculate their atmospheric lights respectively. To solve the problem of invalid dark channel prior, we make an improvement for the transmission estimation. Finally, image fusion is taken as a post processing that can solve the problem of partial darkness and ensure a visual pleasing result. The experimental results for both synthetic and natural hazy images demonstrate that our algorithm performs comparable or even better results than the state‐of‐the‐art methods in terms of various measurement indexes, such as the PSNR, SSIM, and so forth. Besides, the proposed algorithm can be also applied in FPGA platform due to the optimized performance. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.