Anti-reflective coating on ophthalmic lenses is an essential process for glare reduction. After coating, lenses must be individually inspected to obtain the highest quality control. The ISO 8980-4 method recommends that the spectral reflectance measurement of the sample’s top surface require the sample’s back surface to be frosted or painted matte black, a destructive process. Lens manufacturers often employ a manual inspection technique, observing color appearance and brightness reflected from a lens sample compared to a reference sample by the naked eye of well-trained technicians. With many lenses to be inspected daily, human errors are unavoidable. In this work, we have developed a new non-destructive optical technique that can be used to measure the spectral reflectance of the lenses based on a modified spectral confocal microscopy. The critical procedure of this technique is that the confocal probe must be placed at the confocal peak of the reference standard and the confocal peak of the lens sample. Compared to a spectrophotometric method, a mean relative reflectance error of 0.042 %R in the 400-780 nm spectral range can be archived using the proposed confocal technique, provided that the confocal probe is placed within ± 5 μm from the peaks of the confocal signal. The proposed confocal technique could be utilized non-destructively and routinely for spectral reflectance measurement of the coating quality of ophthalmic lenses and other transparent optical elements.
In this work, we utilized deep learning models for depth image regression to predict chicken weights. The dataset consists of annotated 99,427 depth images obtained from 18,706 chickens standing on the weighing scale during the rearing days 21-84. Pretrained models performed regression on the depth image data, including Mobilenet V2, ResNet50 V2, ResNet101 V2, ResNet152 V2, InceptionV3, and Xception. All models performed comparable results regarding mean absolute error (MAE) and mean relative error (MRE); however, Xception performed best with an MAE of 17.2 g and an MRE of 2.52% on the test dataset compared to the reference weight. Based on these results, chicken weight estimation using depth images and deep learning is a promising technique for daily growth rate monitoring for the poultry industry.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.