Computer implemented method for training a software infrastructure based on machine learning techniques and intended for analysis of data obtained from a three-dimensional tomographic inspection of objects of a predetermined type, such as logs, with the aim of determining information about internal characteristics of interest of the self-same objects, wherein, once a training set comprising a plurality of objects of the same predetermined type has been selected, for each object the software infrastructure is supplied with training input data and corresponding training output data, which are processed by the software infrastructure for setting internal processing parameters of the software infrastructure which correlate the training input data with the training output data; where the training input data comprise data obtained from a three-dimensional tomographic inspection of the object, and the training output data comprise information about internal characteristics of interest assessed at internal points of the object, and where the information about the internal characteristics of interest is at least partly assessed at real internal points of the object, previously made accessible by cutting or breaking the object.

A method of wood shingle classification and sawing using machine vision comprises the steps of taking an image of a wood slab in a wood block and identifying a defect in that slab; comparing an image of this defect to images of confirmed defects in a database of confirmed defects to find a match of the defect in these images. If a match is not found, sawing a shingle from the slab and classifying the shingle while making abstraction of the defect. In a second aspect, when images of two consecutive shingles are identical, a third and subsequent shingles can be sawn from a block without taking images thereof. In another aspect, the comparing of images is done by an artificial intelligence system that is trained on a database of images that are associable to the subjectivity of experienced shingle sawyers.

An evaluation value of a sense of temperature that is closer to human perception is estimated. An image feature amount extraction unit (11) extracts an image feature amount from an input image. A temperature sense estimation unit (12) estimates a temperature sense score from the image feature amount with use of a temperature sense estimation model in which a correlation between the image feature amount and the temperature sense score has been learned in advance. The temperature sense score may be weighted with use of a material weight previously set with respect to the material information corresponding to the input image. As the image feature amount, representative values of coordinates a*, b* in a Lab three-dimensional space or a color histogram in which the Lab three-dimensional space is divided into the predetermined number may be used.

Image feature alignment is provided. In some implementations, a computer-readable tangible medium includes instructions that direct a processor to access a reference feature point associated with a high contrast region in a first sub-image that is associated with a first section of a borehole. Instructions are also present that direct the processor to identify several candidate feature points in a second sub-image associated with a second section of the borehole adjacent to the first section of the borehole, with each of the candidate feature points being believed to possibly be associated with the high contrast region. Additional instructions are present that direct the processor to prune the candidate feature points using global solution pruning to arrive at a matching candidate feature point in the second sub-image.

Stock management for wood and lumber products requires measuring and counting items individually on a continuous basis; considering a single lumber package alone can contain hundreds of pieces, it is a tedious task that is error prone when done manually. The invention provides a technology solution that involves taking a picture of products using a smart-phone, or a tablet's built-in camera, processing said picture data to detect individual items using Artificial Intelligence Object Detection methods, and utilizing special algorithms to measure and compute unit volume to present the user a detailed description, measure, count, and a summary. This process helps identify and take stock counts faster and with higher accuracy.

A light 2 for reflected light that emits visible light for reflected light onto a front side of a veneer 6, a light 32 for invisible light that emits near-infrared light for transmitted light onto a back side of the veneer 6, and an image processing device 1 that detects defects of the veneer 6 by analyzing a captured image generated by a line sensor camera 4 are provided. Defects of the veneer 6 are discriminated on the basis of a set of shading and shapes in an infrared-transmitted-light image based on the transmitted light, and colors in a visible-light image based on the reflected light. Consequently, even if a defect has a small color difference from a normal part in the visible-light image, difference of shading between the defective part and the normal part appears in the infrared-transmitted-light image, and a defect that is difficult to detect by seeing only a color difference in a visible-light image can be relatively easily detected.

A log scanning system and method for scanning a log load. Each individual log in the log load may have an ID element with a unique log ID data on at least one log end face. The system has a handheld scanner unit for free-form scanning by an operator over a load end face of the log load. The scanner unit has a depth sensor configured to capture a series of depth images of the load end face and a texture sensor configured to capture a series of texture images of the load end face during the load end face scan. The system also has a data processor(s) that receives and processes the depth and texture images captured from the scan. The processor(s) are configured to fuse the depth images or depth and texture images into a data model of the load end face, determine log end boundaries of the individual logs visible in the load end face by processing the data model, process the texture images to identify and decode any ID elements visible in the scan to extract individual log ID data, and generate output data representing the log load based on the determined log end boundaries and extracted log ID data.

The wood tracking system for a production line generally has a wood product optimizer; a wood product trimmer downstream from the optimizer in the production line; a conveyor for moving wood products from the optimizer to the trimmer and across a handling area therebetween, the optimizer being configured to scan each of the wood products in a given order and to generate optimization data for each wood product; and a computer vision system positioned proximate the handling area along the production line, the computer vision system having a camera, a processor in communication with the optimizer and with the trimmer and a computer-readable memory for storing the optimization data, the processor being configured to acquire images of the handling area from the camera, the processor being configured to associate the optimization data of a given wood product across each of the images until it arrives at the trimmer.

Near InfraRed NIR technology, including NIR cameras and detectors, is used to accurately identify moisture content, the specific locations of the moisture on an entire surface of a dry veneer sheet or other wood product, and the strength of the dry veneer sheet or other wood product. Based on the identified moisture content and/or predicted strength for a dry veneer sheet or other wood product, one or more actions are taken with respect to dry veneer sheet or other wood product to ensure the dry veneer sheet or other wood product is put the most efficient, effective, and valuable use.

Disclosed is a method of identifying an object using at least one imaging. The method comprises acquiring calibration information for each of the imaging device arranged substantially perpendicular to a planar surface of the object, capturing an image of the planar surface using each of the imaging device, generating a transformed image corresponding to each image of the planar surface, using the calibration information of the imaging device used for capturing each image, generating a security map for each transformed image, wherein the security map comprises a weightage factor for each pixel of the transformed image, and wherein the weightage factor is based on image resolution of the transformed image, and constructing a resultant image of the planar surface using each transformed image and the security map for the transformed image, to identify the object.