Predicting the live weight of cattle helps us monitor the health of animals, conduct genetic selection, and determine the optimal timing of slaughter. On large farms, accurate and expensive industrial scales are used to measure live weight. However, a promising alternative is to estimate live weight using morphometric measurements of livestock and then apply regression equations relating such measurements to live weight. Manual measurements on animals using a tape measure are time-consuming and stressful for the animals. Therefore, computer vision technologies are now increasingly used for non-contact morphometric measurements. The paper proposes a new model for predicting live weight based on augmenting three-dimensional clouds in the form of flat projections and image regression with deep learning. It is shown that on real datasets, the accuracy of weight measurement using the proposed model reaches 91.6%. We also discuss the potential applicability of the proposed approach to animal husbandry.

Optics InfoBase is the Optical Society's online library for flagship journals, partnered and copublished journals, and recent proceedings from OSA conferences.

Fast algorithms for computing various discrete cosine transforms and discrete sine transforms in a sliding window are proposed. The algorithms are based on a recursive relationship between three subsequent local transform spectra. Efficient inverse algorithms for signal processing in a sliding window are also presented. The computational complexity of the algorithms is compared with that of known fast discrete sinusoidal transforms and running recursive algorithms.

Preprocessing of the input scene can be used to improve the performance of an optical correlator. The result of the preprocessing algorithms can be bipolar real-valued images, with positive and negative values, for input to the optical correlator. We present different procedures for the implementation of the bipolar real-valued signal with spatial light modulators that work in either amplitude-only or phase-only regimes. We apply these techniques to the implementation of bipolar real-valued preprocessed input images in color pattern recognition. © 1998 Society of Photo-Optical Instrumentation Engineers.

An accurate algorithm for three-dimensional (3-D) pose recognition of a rigid object is presented. The algorithm is based on adaptive template matched filtering and local search optimization. When a scene image is captured, a bank of correlation filters is constructed to find the best correspondence between the current view of the target in the scene and a target image synthesized by means of computer graphics. The synthetic image is created using a known 3-D model of the target and an iterative procedure based on local search. Computer simulation results obtained with the proposed algorithm in synthetic and real-life scenes are presented and discussed in terms of accuracy of pose recognition in the presence of noise, cluttered background, and occlusion. Experimental results show that our proposal presents high accuracy for 3-D pose estimation using monocular images.