Wood cutting properties for the chains of chainsaw is measured in the lab by analyzing the force, torque, consumed power and other aspects of the chain as it cuts through the wood log. One of the essential properties of the chains is the cutting efficiency which is the measured cutting surface per the power used for cutting per the time unit. These data are not available beforehand and therefore, cutting efficiency cannot be measured before performing the cut. Cutting efficiency is related to the relativehardness of the wood which means that it is affected by the existence of knots (hardstructure areas) and cracks (no material areas). The actual situation is that all the cuts with knots and cracks are eliminated and just the clean cuts are used, therefore estimating the relative wood hardness by identifying the knots and cracks beforehand can significantly help to automate the process of testing the chain properties, saving time and material and give a better understanding of cutting wood logs to improve chains quality.Many studies have been done to develop methods to analyze and measure different features of an end face. This thesis work is carried out to evaluate a machinelearning model to detect knots and cracks on end faces and to understand their impact on the average cutting efficiency. Mask R-CNN is widely used for instance segmentation and in this thesis work, Mask R-CNN is evaluated to detect and segment knots and cracks on an end face. Methods are also developed to estimatepith’s vertical position from the wood image and generate average cutting efficiency graph based on knot’s and crack’s percentage at each vertical position of wood image.

Tracking of tree logs from a harvesting site to its processing site is a legal requirement for timber-based industries. Wood log identification is an important task in the forestry industry and has traditionally relied on manual inspection by trained experts. However, with the increasing demand for wood products and the need for efficient and accurate identification, there has been a growing interest in developing automated wood log identification systems. In this study, we explored approaches to wood log identification with three objectives: automated log identification, damaged log identification (detection of damaged log), and pith detection (estimation of the pith location). We propose a novel approach for wood log identification using computer vision techniques. Our approach involves capturing images of wood logs using a digital camera, detection of pith location using machine learning model, then applying image processing algorithms to extract relevant features, such as the bark pattern, rings, and use information provided by radial line that extends from the bark to the pith to identify the wood log. In our experiments, we used different image processing techniques to build computer vision models for log identification, trained machine learning and deep learning models to classify the wood log into damaged or not, and deep learning models for estimation of the pith location. The findings of this study indicate that the proposed approach for wood log identification work best with Canny Edge Detection technique, and we can further extend this approach.