An Improved Wood Identification Accuracy Using Gaussian Pyramid and Laplacian Edge Detection Based on Android Smartphone

The position identification of SMD electronic components mainly uses Canny edge detection algorithm to detect the edges of specific elements, benefited from its computational simplicity. The traditional Canny algorithm lacks the adaptability in gradient calculation and double thresholds selection, which may affect the location and identification accuracy of specific elements in electronic components. In this paper, an improved canny edge detection algorithm is proposed. The gradient magnitude is calculated in four directions, i.e., horizontal, vertical, and diagonal. Both the high and low thresholds can be adaptively determined based on the grayscale distribution information, to increase the adaptability of edge identification. The experimental results show that the proposed method can better locate the true edges of specific elements in electronic components with a reasonable processing speed, compared with the traditional Canny algorithm, and has been successfully applied on practical real-time vision inspection on SMD electronic components.

Download Full-text

Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features

Forests ◽

10.3390/f12111527 ◽

2021 ◽

Vol 12 (11) ◽

pp. 1527

Author(s):

Xi Pan ◽

Kang Li ◽

Zhangjing Chen ◽

Zhong Yang

Keyword(s):

Near Infrared ◽

Spatial Clustering ◽

Texture Feature ◽

Principal Component ◽

Texture Features ◽

Image Features ◽

Identification Accuracy ◽

Support Vector ◽

Gray Level ◽

Wood Identification

Identifying wood accurately and rapidly is one of the best ways to prevent wood product fakes and adulterants in forestry products. Wood identification traditionally relies heavily on special experts that spend extensive time in the laboratory. A new method is proposed that uses near-infrared (NIR) spectra at a wavelength of 780–2300 nm incorporated with the gray-level co-occurrence (GLCM) texture feature to accurately and rapidly identify timbers. The NIR spectral features were determined by principal component analysis (PCA), and the digital image features extracted with the GLCM were used to create a support vector machine (SVM) model to identify the timbers. The results from fusion features of raw spectra and four GLCM features of 25 timbers showed that identification accuracy by the model was 99.43%. A sample anisotropy and heterogeneity comparative analysis revealed that the wood identification information from the transverse surface had more characteristics than that from the tangential and radial surfaces. Furthermore, short-wavelength pre-processed NIR bands of 780–1100 nm and 1100–2300 nm realized high identification accuracy of 99.43% and 100%, respectively. The four GLCM features were effective for improving identification accuracy by improving the data spatial clustering features.

Download Full-text

Wood microscopic image identification method based on convolution neural network

BioResources ◽

10.15376/biores.16.3.4986-4999 ◽

2021 ◽

Vol 16 (3) ◽

pp. 4986-4999

Author(s):

Ziyu Zhao ◽

Xiaoxia Yang ◽

Zhedong Ge ◽

Hui Guo ◽

Yucheng Zhou

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Recognition Accuracy ◽

Network Models ◽

Identification Accuracy ◽

Technical Solution ◽

Wood Identification ◽

Neural Network Models ◽

Identification Method

To prevent the illegal trade of precious wood in circulation, a wood species identification method based on convolutional neural network (CNN), namely PWoodIDNet (Precise Wood Specifications Identification) model, is proposed. In this paper, the PWoodIDNet model for the identification of rare tree species is constructed to reduce network parameters by decomposing convolutional kernel, prevent overfitting, enrich the diversity of features, and improve the performance of the model. The results showed that the PWoodIDNet model can effectively improve the generalization ability, the characterization ability of detail features, and the recognition accuracy, and effectively improve the classification of wood identification. PWoodIDNet was used to analyze the identification accuracy of microscopic images of 16 kinds of wood, and the identification accuracy reached 99%, which was higher than the identification accuracy of several existing classical convolutional neural network models. In addition, the PWoodIDNet model was analyzed to verify the feasibility and effectiveness of the PWoodIDNet model as a wood identification method, which can provide a new direction and technical solution for the field of wood identification.

Download Full-text

Difference mode EXELFS with parallel-detection EELS

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100130948 ◽

1992 ◽

Vol 50 (2) ◽

pp. 1262-1263

Author(s):

Michael K. Kundmann ◽

Ondrej L. Krivanek

Keyword(s):

Edge Detection ◽

Important Distinction ◽

Edge Structure ◽

Parallel Detection ◽

Gain Variation ◽

Ideal Solutions ◽

Detector Cell ◽

The Difference ◽

Elemental Detection ◽

Partial Correction

Parallel detection has greatly improved the elemental detection sensitivities attainable with EELS. An important element of this advance has been the development of differencing techniques which circumvent limitations imposed by the channel-to-channel gain variation of parallel detectors. The gain variation problem is particularly severe for detection of the subtle post-threshold structure comprising the EXELFS signal. Although correction techniques such as gain averaging or normalization can yield useful EXELFS signals, these are not ideal solutions. The former is a partial throwback to serial detection and the latter can only achieve partial correction because of detector cell inhomogeneities. We consider here the feasibility of using the difference method to efficiently and accurately measure the EXELFS signal.An important distinction between the edge-detection and EXELFS cases lies in the energy-space periodicities which comprise the two signals. Edge detection involves the near-edge structure and its well-defined, shortperiod (5-10 eV) oscillations. On the other hand, EXELFS has continuously changing long-period oscillations (∼10-100 eV).

Download Full-text

Perceptual Evaluation of Speech Naturalness in Speakers of Varying Gender Identities

Journal of Speech Language and Hearing Research ◽

10.1044/2020_jslhr-19-00337 ◽

2020 ◽

Vol 63 (7) ◽

pp. 2054-2069

Author(s):

Brandon Merritt ◽

Tessa Bent

Keyword(s):

Spontaneous Speech ◽

Identification Accuracy ◽

Rating Task ◽

Gender Identification ◽

Identification Task ◽

Male And Female ◽

Perceptual Evaluation ◽

Speech Training ◽

And Gender ◽

Speech Naturalness

Purpose The purpose of this study was to investigate how speech naturalness relates to masculinity–femininity and gender identification (accuracy and reaction time) for cisgender male and female speakers as well as transmasculine and transfeminine speakers. Method Stimuli included spontaneous speech samples from 20 speakers who are transgender (10 transmasculine and 10 transfeminine) and 20 speakers who are cisgender (10 male and 10 female). Fifty-two listeners completed three tasks: a two-alternative forced-choice gender identification task, a speech naturalness rating task, and a masculinity/femininity rating task. Results Transfeminine and transmasculine speakers were rated as significantly less natural sounding than cisgender speakers. Speakers rated as less natural took longer to identify and were identified less accurately in the gender identification task; furthermore, they were rated as less prototypically masculine/feminine. Conclusions Perceptual speech naturalness for both transfeminine and transmasculine speakers is strongly associated with gender cues in spontaneous speech. Training to align a speaker's voice with their gender identity may concurrently improve perceptual speech naturalness. Supplemental Material https://doi.org/10.23641/asha.12543158

Download Full-text