Abstract: A method of board lumber grading is performed in an industrial environment on a machine learning framework configured as an interface to a machine learning-based deep convolutional network that is trained end-to-end, pixels-to-pixels on semantic segmentation. The method uses deep learning techniques that are applied to semantic segmentation to delineate board lumber characteristics, including their sizes and boundaries.

Abstract: A method of board lumber grading is performed in an industrial environment on a machine learning framework configured as an interface to a machine learning-based deep convolutional network that is trained end-to-end, pixels-to-pixels on semantic segmentation. The method uses deep learning techniques that are applied to semantic segmentation to delineate board lumber characteristics, including their sizes and boundaries.

Abstract: A method of improving board feature quality grading facilitates human check grader reaction to grading output. The method entails specifying, for application by an automatic grading system to the faces of boards passing through a scanning zone, a virtual grade expressed by a range of values that overlap values in two of successive standard rule-based grades representing higher and lower board feature qualities; producing a signal in response to detection of a board feature quality representing a virtual grade value of a board analyzed by the automatic grading system; indicating, in response to the signal, a virtual grading designation onto the board to alert a check grader to assess whether the board exhibits board feature quality that exceeds the lower board feature quality; and assigning to the board the standard rule-based grade representing the higher board feature quality whenever the check grader's assessment concurs with the virtual grade designation.

Abstract: A lumber check grader-actuatable interface enables a check grader to interact with grade-quality measured boards of lumber conveyed along a flow path and passing in front of the check grader. The interface accurately and continuously tracks the location of each board in front of a check grader and tracks the location of the check grader's hands relative to the boards. Gestures can, therefore, be used for a selected board to perform additional actions, such as changing the grade or changing the trims. The interface enables a check grader to walk alongside and keep pace with a board of interest as it is transported and to provide feedback to the interface about a needed change for the board of interest. By knowing which board is of interest to a check grader, the interface can display additional information for only that board without overwhelming the check grader with non-stop information overload.

Abstract: A grain angle sensor system for measuring grain angle direction of surface fibers of a wood object with respect to at least one of a surface plane direction or a transverse direction, such as a dive angle, or with respect to both the surface plane and transverse direction. The system includes multiple laser diodes and photosensor detectors integrated into an electro-optical assembly that can sequence the firing of the lasers to minimize crosstalk. An exemplary assembly includes an enclosure housing an electronic control board connected to circuit cards containing multiple laser diodes and multiple photosensor detectors.

Abstract: A “Woodprint™” characterization and identification technique employs cameras (16), lighting (14), camera interface hardware (18), a computer (20), and/or image processing software to collect and analyze surface characteristics of pieces of wood (8) to track them through an automated production process in real-time with information that is specific to each wood piece (8), such as what machining is required, its value, and/or its destination. When a wood piece (8) reaches a point in the production process where a decision is required, its unique identity is used to retrieve appropriate information previously determined and assigned to the wood piece (8).

Abstract: A “Woodprint™” characterization and identification technique employs cameras (16), lighting (14), camera interface hardware (18), a computer (20), and/or image processing software to collect and analyze surface characteristics of pieces of wood (8) to track them through an automated production process in real-time with information that is specific to each wood piece (8), such as what machining is required, its value, and/or its destination. When a wood piece (8) reaches a point in the production process where a decision is required, its unique identity is used to retrieve appropriate information previously determined and assigned to the wood piece (8).

Abstract: A grain angle sensor system for measuring grain angle direction of surface fibers of a wood object with respect to at least one of a surface plane direction or a transverse direction, such as a dive angle, or with respect to both the surface plane and transverse direction. The system includes multiple laser diodes and photosensor detectors integrated into an electro-optical assembly that can sequence the firing of the lasers to minimize crosstalk. An exemplary assembly includes an enclosure housing an electronic control board connected to circuit cards containing multiple laser diodes and multiple photosensor detectors.

Abstract: A “woodprint™” characterization and identification technique unique employs cameras (16), lighting (14), camera interface hardware (18), a computer (20), and/or image processing software to collect and analyze surface characteristics of pieces of wood (8) to track them through an automated production process in real-time with information that is specific to each wood piece (8), such as what machining is required, its value, and/or its destination. When a wood piece (8) reaches a point in the production process where a decision is required, its unique identity is used to retrieve appropriate information previously determined and assigned to the wood piece (8).

Abstract: The present invention employs a blinded fiber-optic light illumination system (12) to illuminate a wood board (24) with a sharp projected light edge to detect the tracheid, color, and geometric characteristics of the lumber during an automated grading process. The light line (70) employs thousands of fibers (46) of desired length (58) and thickness (52). The fibers (46) are randomized such that fibers (46) neighboring each other in the cable (48) do not necessarily neighbor each other in the light line subunit (42) so that the emitted light has substantially uniform intensity over its spatial range. Multiple light line subunits (42) are positioned adjacent to one an other to achieve a desired light line length (60). A set of image sensors (22) in predetermined positions obtain three types of data from the light incident to the board (24). A computer analyzes the data to interpret the physical characteristics of the board (24) and determine how to grade or cut it.