An Encoder-Decoder Architecture within a Classical Signal-Processing Framework for Real-Time Barcode Segmentation.

In this work, two methods are proposed for solving the problem of one-dimensional barcode segmentation in images, with an emphasis on augmented reality (AR) applications. These methods take the partial discrete Radon transform as a building block. The first proposed method uses overlapping tiles for obtaining good angle precision while maintaining good spatial precision. The second one uses an encoder-decoder structure inspired by state-of-the-art convolutional neural networks for segmentation while maintaining a classical processing framework, thus not requiring training. It is shown that the second method's processing time is lower than the video acquisition time with a 1024 × 1024 input on a CPU, which had not been previously achieved. The accuracy it obtained on datasets widely used by the scientific community was almost on par with that obtained using the most-recent state-of-the-art methods using deep learning. Beyond the challenges of those datasets, the method proposed is particularly well suited to image sequences taken with short exposure and exhibiting motion blur and lens blur, which are expected in a real-world AR scenario. Two implementations of the proposed methods are made available to the scientific community: one for easy prototyping and one optimised for parallel implementation, which can be run on desktop and mobile phone CPUs.

Wavefront Characteristics of a Digital Holographic Optical Element.

In this study, a 50 × 50 mm holographic optical element (HOE) with the property of a spherical mirror was recorded digitally on a silver halide photoplate using a wavefront printing method. It consisted of 51 × 96 hologram spots with each spot measuring 0.98 × 0.52 mm. The wavefronts and optical performance of the HOE were compared with those of reconstructed images from a point hologram displayed on DMDs of different pixel structures. The same comparison was also performed with an analog-type HOE for a heads-up display and with a spherical mirror. A Shack-Hartmann wavefront sensor was used to measure the wavefronts of the diffracted beams from the digital HOE and the holograms as well as the reflected beam from the analog HOE and the mirror when a collimated beam was incident on them. These comparisons revealed that the digital HOE could perform as a spherical mirror, but they also revealed astigmatism-as in the reconstructed images from the holograms on DMDs-and that its focusability was worse than that of the analog HOE and the spherical mirror. A phase map, i.e., the polar coordinate-type presentation of the wavefront, could visualize the wavefront distortions more clearly than the reconstructed wavefronts obtained using Zernike polynomials. The phase map revealed that the wavefront of the digital HOE was more distorted than those of the analog HOE and the spherical mirror.