Methods for enhancing poultry growth and performance

    公开(公告)号:US11497197B2

    公开(公告)日:2022-11-15

    申请号:US16515856

    申请日:2019-07-18

    Abstract: Methods for enhancing embryonic and post-hatch growth and performance of poultry by administration of a probiotic composition, such as a composition containing a mixture of one or more bacterial cultures, to the surface of the shells of fertilized eggs prior to setting. Optionally, the method further includes administration of the same probiotic composition at the same concentration to chicks hatched from the eggs that had received the topical in ovo administration to the shell. The probiotic composition is administered to the chicks orally, such as in feed.

    Imaging via diffuser modulation by translating a sample

    公开(公告)号:US11487099B2

    公开(公告)日:2022-11-01

    申请号:US16819041

    申请日:2020-03-14

    Inventor: Guoan Zheng

    Abstract: An imaging system includes a sample mount for holding a sample to be imaged, a light source configured to emit a light beam to be incident on the sample, a translation mechanism coupled to the sample mount and configured to scan the sample to a plurality of sample positions in a plane substantially perpendicular to an optical axis of the imaging system, a mask positioned downstream from the sample along the optical axis, and an image sensor positioned downstream from the mask along the optical axis. The image sensor is configured to acquire a plurality of images as the sample is translated to the plurality of sample positions. Each respective image corresponds to a respective sample position. The imaging system further includes a processor configured to process the plurality of images to recover a complex profile of the sample based on positional shifts extracted from the plurality of images.

    Methods and systems for object recognition in low illumination conditions

    公开(公告)号:US11461592B2

    公开(公告)日:2022-10-04

    申请号:US17251327

    申请日:2019-08-07

    Abstract: Described herein is an object recognition system in low illumination conditions. A 3D InIm system can be trained in the low illumination levels to classify 3D objects obtained under low illumination conditions. Regions of interest obtained from 3D reconstructed images are obtained by de-noising the 3D reconstructed image using total-variation regularization using an augmented Lagrange approach followed by face detection. The regions of interest are then inputted into a trained CNN. The CNN can be trained using 3D InIm reconstructed under low illumination after TV-denoising. The elemental images were obtained under various low illumination conditions having different SNRs. The CNN can effectively recognize the 3D reconstructed faces after TV-denoising.

Patent Agency Ranking