The Use of Image Analysis to Detect Seed Contamination—A Case Study of Triticale

Abstract

Samples of triticale seeds of various qualities were assessed in the study. The seeds were obtained during experiments, reflecting the actual sowing conditions. The experiments were conducted on an original test facility designed by the authors of this study. The speed of the air (15, 20, 25 m/s) transporting seeds in the pneumatic conduit was adjusted to sowing. The resulting graphic database enabled the distinction of six classes of seeds according to their quality and sowing speed. The database was prepared to build training, validation and test sets. The neural model generation process was based on multi-layer perceptron networks (MLPN) and statistical (machine training). When the MLPN was used to identify contaminants in seeds sown at a speed of 15 m/s, the lowest RMS error of 0.052 was noted, whereas the classification correctness coefficient amounted to 0.99.

Deep and Machine Learning Using SEM, FTIR, and Texture Analysis to Detect Polysaccharide in Raspberry Powders

“…While discussing entropy variables [ 15 ], which in the literature determine the amount of energy lost during physical reaction [ 47 ], one can observe similarity between research classes. It turns out that the highest similarity for the entropy variables occurred between research classes with a 30% content of sugar between IN and MD.…”

“…In the end, 430 microscopic images were obtained (230 scanning images for 0° and for 90°). In the next stage, the analysis of texture was carried out with a gray-level co-occurrence matrix (GLCM) [ 7 , 25 , 31 ], which—in a three-dimensional graphic—allowed presenting details regarding surface with mathematical function (procedural textures) [ 15 ]. In order to do it, digital image—from 24 to 8-bit color depth—processing was carried out with a “PID system”.…”

“…TIFF format. The prepared base of monochromatic images (8 bit) was imported to the tool called ImageJ (Available online: https://imagej.nih.gov/, accessed on 20 August 2021) [32], with the help of which texture descriptors were properly extracted: Angular Second Moment (ASM), Entropy, Correlation, Contrast, and Inverse Different Moment (IDM) [15,33] (Figure 1).…”

“…Artificial neural networks are most commonly used in terms of data, which do not have simple and organized structure calculations. ANN are used above all in stochastic issues, and the ones related to information processing, among other things, with images (bitmap) [ 10 ], acoustic emission [ 13 ], and numerical data [ 14 , 15 ]. The networks were also used in the process of deep learning, which includes extended methods of image processing.…”

Autofluorescence-spectral imaging as an innovative method for rapid, non-destructive and reliable assessing of soybean seed quality

“…The ANN method was implemented with the multilayer perceptron (MLP) algorithm that trains using Backpropagation. Neural networks have been successfully applied to identify contaminants in seeds through image analysis and the topology of the multilayer perceptron (MLP) also proved to be the best in recognizing classes of triticale seeds 33 . The SVM- l algorithm showed to be efficient in discriminating high-and low-vigor soybean seeds compared to LDA models 34 .…”