Wood is widely used in construction, the home, and art applications all over the world because of its good mechanical properties and aesthetic value. However, because the growth and preservation of wood are greatly affected by the environment, it often contains different types of defects that affect its performance and ornamental value. To solve the issues of high labor costs and low efficiency in the detection of wood defects, we used machine vision and deep learning methods in this work. A color charge-coupled device camera was used to collect the surface images of two types of wood from Akagi and Pinus sylvestris trees. A total of 500 images with a size of 200 × 200 pixels containing wood knots, dead knots, and checking defects were obtained. The transfer learning method was used to apply the single-shot multibox detector (SSD), a target detection algorithm and the DenseNet network was introduced to improve the algorithm. The mean average precision for detecting the three types of defects, live knots, dead knots and checking was 96.1%.

The deep learning feature extraction method and extreme learning machine (ELM) classification method are combined to establish a depth extreme learning machine model for wood image defect detection. The convolution neural network (CNN) algorithm alone tends to provide inaccurate defect locations, incomplete defect contour and boundary information, and inaccurate recognition of defect types. The nonsubsampled shearlet transform (NSST) is used here to preprocess the wood images, which reduces the complexity and computation of the image processing. CNN is then applied to manage the deep algorithm design of the wood images. The simple linear iterative clustering algorithm is used to improve the initial model; the obtained image features are used as ELM classification inputs. ELM has faster training speed and stronger generalization ability than other similar neural networks, but the random selection of input weights and thresholds degrades the classification accuracy. A genetic algorithm is used here to optimize the initial parameters of the ELM to stabilize the network classification performance. The depth extreme learning machine can extract high-level abstract information from the data, does not require iterative adjustment of the network weights, has high calculation efficiency, and allows CNN to effectively extract the wood defect contour. The distributed input data feature is automatically expressed in layer form by deep learning pre-training. The wood defect recognition accuracy reached 96.72% in a test time of only 187 ms.

The green plum is rich in amino acids, lipids, inorganic salts, vitamins, and trace elements. It has high nutritional value and medicinal value and is very popular among Chinese people. However, green plums are susceptible to collisions and pests during growth, picking, storage, and transportation, causing surface defects, affecting the quality of green plums and their products and reducing their economic value. In China, defect detection and grading of green plum products are still performed manually. Traditional manual classification has low accuracy and high cost, which is far from meeting the production needs of green plum products. In order to improve the economic value of green plums and their products and improve the automation and intelligence level of the product production process, this study adopted deep learning methods based on a convolutional neural network and cost-effective computer vision technology to achieve efficient classification of green plum defects. First, a camera and LEDs were used to collect 1240 green plum images of RGB, and the green plum experimental classification standard was formulated and divided into five categories, namely, rot, spot, scar, crack, and normal. Images were randomly divided into a training set and test set, and the number of images of the training set was expanded. Then, the stochastic weight averaging (SWA) optimizer and w-softmax loss function were used to improve the VGG network, which was trained and tested to generate a green plum defect detection network model. The average recognition accuracy of green plum defects was 93.8%, the test time for each picture was 84.69 ms, the recognition rate of decay defect was 99.25%, and the recognition rate of normal green plum was 95.65%. The results were compared with the source VGG network, resnet18 network, and green lemon network. The results show that for the classification of green plum defects, the recognition accuracy of the green plum defect detection network increased by 9.8% and 16.6%, and the test speed is increased by 1.87 and 6.21 ms, respectively, which has certain advantages.

Variational mode decomposition (VMD) with a non-recursive and narrow-band filtering nature is a promising time-frequency analysis tool, which can deal effectively with a non-stationary and complicated compound signal. Nevertheless, the factitious parameter setting in VMD is closely related to its decomposability. Moreover, VMD has a certain endpoint effect phenomenon. Hence, to overcome these drawbacks, this paper presents a novel time-frequency analysis algorithm termed as improved adaptive variational mode decomposition (IAVMD) for rotor fault diagnosis. First, a waveform matching extension is employed to preprocess the left and right boundaries of the raw compound signal instead of mirroring the extreme extension. Then, a grey wolf optimization (GWO) algorithm is employed to determine the inside parameters ( $\widehat{\alpha }$ , K) of VMD, where the minimization of the mean of weighted sparseness kurtosis (WSK) is regarded as the optimized target. Meanwhile, VMD with the optimized parameters is used to decompose the preprocessed signal into several mono-component signals. Finally, a Teager energy operator (TEO) with a favorable demodulation performance is conducted to efficiently estimate the instantaneous characteristics of each mono-component signal, which is aimed at obtaining the ultimate time-frequency representation (TFR). The efficacy of the presented approach is verified by applying the simulated data and experimental rotor vibration data. The results indicate that our approach can provide a precise diagnosis result, and it exhibits the patterns of time-varying frequency more explicitly than some existing congeneric methods do (e.g., local mean decomposition (LMD), empirical mode decomposition (EMD) and wavelet transform (WT) ).

Blueberries, which are rich in nutrition, are susceptible to fungal infection during postharvest or storage. However, early detection of diseases in blueberry is challenging because of their opaque appearance and the inconspicuousness of spots in the early stage of disease. The goal of this study was to investigate the potential of hyperspectral imaging over the spectral range of 400–1000 nm to discriminate early disease in blueberries. Scanning electron microscope observation verified that fungal damage to the cellular structure takes place during the early stages. A total of 400 hyperspectral images, 200 samples each of healthy and early disease groups, were collected to obtain mean spectra of each blueberry samples. Spectral correlation analysis was performed to select an effective spectral range. Partial least square discrimination analysis (PLSDA) models were developed using two types of spectral range (i.e., full wavelength range of 400–1000 nm and effective spectral range of 685–1000 nm). The results showed that the effective spectral range made it possible to provide better classification results due to the elimination of the influence of irrelevant variables. Moreover, the effective spectral range combined with an autoscale preprocessing method was able to obtain optimal classification accuracies, with recognition rates of 100% and 99% for healthy and early disease blueberries. This study demonstrated that it is feasible to use hyperspectral imaging to measure early disease blueberries.

Solid wood panels are widely used in the wood flooring and furniture industries, and paneling is an excellent material for indoor decoration. The classification of colors helps to improve the appearance of wood products assembled from multiple panels due to the differences in surface colors of solid wood panels. Traditional wood surface color classification mainly depends on workers’ visual observations, and manual color classification is prone to visual fatigue and quality instability. In order to reduce labor costs of sorting and to improve production efficiency, in this study, we introduced machine vision technology and an unsupervised learning technique. First-order color moments, second-order color moments, and color histogram peaks were selected to extract feature vectors and to realize data dimension reduction. The feature vector set was divided into different clusters by the K-means algorithm to achieve color classification and, thus, the solid wood panels with similar surface color were classified into one category. Furthermore, during twice clustering based on second-order color moment, texture recognition was realized on the basis of color classification. A sample of beech wood was selected as the research object, not only was color classification completed, but texture recognition was also realized. The experimental results verified the effectiveness of the technical proposal.