In this investigation, an automated vision system "AVS" for non-destructive quality inspection of potato tubers "PT" was developed. Color, size, mass, firmness, and the texture homogeneity of the "PT" surface, various sensitive features were studied, and extracted from the digital image by using the R program. Otsu threshold method, RGB, Lu*v*, CIE LCh uv color models, and texture analysis by using the package Gray-Level Co-Occurrence Matrices (GLCMs) were applied. The results showed a great correlation between the tuber pixel area percentages (DIM=dimension as a percentage of total pixels), and both mass and geometric mean diameter (GMD) of all "PT" varieties. The color results demonstrated that the hue angle (h uv ) ranged from 68.92 to 96.61 °, and the "PT" color was classified into deep and light color intensity. The "AVS" could predict the mass and size, and gave statistical data at the mass production level, in terms of the inspecting samples No., mass, and grades based on size, color, and free from injuries through the texture homogeneity of tuber surface. A predictive model hypothesized based on the tuber's surface texture characteristics for predicting the tubers firmness was statistically significant. This "AVS" can be applied as a non-destructive, precise, and symmetric technique in-line inspection, the quality of "PT", also helping decision-makers in the agricultural field and stakeholders to improve the horticulture sector through the statistical data issued by this system.
by equalization with no need to transfer the already computed parts of the list from the slaves to the master processor.Both histogram list calculation and equalization algorithms have been implemented on a TELMAT T-NODE machine with 4, 8, or 16 transputers T800. In the case of 16 transputers, the speedup obtained over the serial computation ranges from 4.01 (L = 64) to 14.87 (L = 256). As expected, the speedup is best for 256 levels/component because the computational load is much larger than the communication load between processors. The same observations hold for parallel equalization using the color histogram list, where a speedup of 10.15 has been obtained for L = 256 and a farm of 16 transputers.
A Fast Learning Algorithm for Gabor TransformationAyman Ibrahim and Mahmood R. Azimi-SadjadiAbstract-An adaptive learning approach for the computation of the coefficients of the generalized nonorthogonal 2·D Gabor transform representation is introduced in this correspondence. The algorithm uses a recursive least squares (RLS) type algorithm. The aim is to achieve minimum mean squared error for the reconstructed image from the set of the Gabor coefficients. The proposed RLS learning offers better accuracy and faster convergence behavior when compared with the least mean squares (LMS)·based algorithms. Applications of this scheme in image data reduction are also demonstrated.
Solar energy is one of the most important solutions to reduce the concerns of the severe climate change phenomenon. Granted, the main manner to harness solar energy to generate power electricity is implemented through arrays made up of PV solar panels. However, the accumulation of dust on PV surfaces nevertheless remains a serious issue that considerably reduces the efficient conversion of PV panels. Therefore, this research is aimed at automating both monitoring and cleaning of the PV panel’s surfaces through the design, manufacture, and operation and evaluating a dry-cleaning robot based on a color monitoring system. The preliminary results demonstrate that the color analysis of the PV panels can distinguish between the density of dust accumulated, where the total color differences between the clean PV panels and both the PV panels with simple, moderate, and intense dust were 43.69, 61.19, and 75.23. This raised the efficiency of the power produced for simple dust panels from 88.03 to 98.91% (one cleaning round), moderate dust panels from 70.72 to 92.96%, and intense dust panels from 39.05 to 62.11% (two cleaning rounds). These preliminary finds illustrate the possibility of using this approach to automatic monitoring the PV panel color and operate the cleaning robot.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.