Design and prototype development of a computer vision-based lumber production planning system

Automated Planning and Optimization of Lumber Production Using Machine Vision and Computed Tomography

“…Techniques for internal defect identification and classification in cross-sectional CT images of logs include gray-level thresholding and binarization [13], [34], neural network-based classification [29], integration of shape and texture features [1], [2], [5] and DempsterSchafer theory-based evidential reasoning on the 3-D geometric features of the defects [36]. Bhandarkar et al [1], [2] and Samson [26] present geometrical modeling algorithms to describe the structure of internal defects within the logs and their appearance on the surfaces of the lumber beams sawn from those logs, and to compute the effect of the presence of knots in the conversion of logs into structural lumber [2], [27].…”

“…Bhandarkar et al [1], [2] and Samson [26] present geometrical modeling algorithms to describe the structure of internal defects within the logs and their appearance on the surfaces of the lumber beams sawn from those logs, and to compute the effect of the presence of knots in the conversion of logs into structural lumber [2], [27]. The results of internal defect identification and localization can be used to reconstruct a 3-D model of the log along with its internal defects [1], [2]. Software programs that simulate various machining operations such as sawing and veneering on the virtual 3-D log reconstruction have been described in the literature [1], [2], [8], [15], [23], [28].…”

“…The results of internal defect identification and localization can be used to reconstruct a 3-D model of the log along with its internal defects [1], [2]. Software programs that simulate various machining operations such as sawing and veneering on the virtual 3-D log reconstruction have been described in the literature [1], [2], [8], [15], [23], [28]. Likewise, programs for automated grading of virtually produced lumber (using the aforementioned simulators) and physical lumber produced by sawmills have also been reported in the literature [20], [21].…”

“…Likewise, programs for automated grading of virtually produced lumber (using the aforementioned simulators) and physical lumber produced by sawmills have also been reported in the literature [20], [21]. These programs have been used to estimate the improvements in lumber value yield recovery resulting from internal log scanning which are reported to be in the range of 40%-60% [2], [7], [15]. The above review covers the most relevant developments in the use of CT and MRI technologies for internal defect detection and identification in hardwood logs.…”

“…Studies of computed axial tomography (CAT or CT) and magnetic resonance imaging (MRI) (also known as nuclear magnetic resonance (NMR) imaging) for internal log defects [1], [2], [6], [13], [34] have demonstrated that the CT and MRI technologies available today can be used successfully to image the internal features of logs. On account of their inherent sensitivity to the water content of the imaged sample, MRI techniques are particularly well suited for detecting internal features of logs, such as knots, reaction wood, wetwood, and gum spots, that are characterized by varying moisture content in the underlying wood [6].…”