scholarly journals Image analysis of real-time classification of cherry fruit from colour features

2021 ◽  
Vol 52 (4) ◽  
Author(s):  
José F. Reyes ◽  
Elías Contreras ◽  
Christian Correa ◽  
Pedro Melin
Keyword(s):  
Image Analysis ◽  
Real Time ◽  
Low Cost ◽  
Image Features ◽  
Colour Pattern ◽  
Image Analysis Algorithm ◽  
Colour Patterns ◽  
Sample Set ◽  
Colour Classes

An image analysis algorithm for the classification of cherries in real time by processing their digitalized colour images was developed, and tested. A set of five digitalized images of colour pattern, corresponding to five colour classes defined for commercial cherries, was characterized. The algorithm performs the segmentation of the cheery image by rejecting the pixels of the background and keeping the image features corresponding to the coloured area of the fruit. A histogram analysis was carried out for the RGB and HSV colour spaces, where the Red and Hue components showed differences between each of the specified colour patterns of the exporting reference system. This information led to the development of a hybrid Bayesian classification algorithm based on the components R and H. Its accuracy was tested with a set of cherry samples within the colour range of interest. The algorithm was implemented by means of a real time C++ code in Microsoft Visual Studio environment. When testing, the algorithm showed a 100% effectiveness in classifying a sample set of cherries into the five standardized cherry classes. The components of the hardware-software system for implementing the methodology are low cost, thus ensuring an affordable commercial deployment.

A low-cost single-board solution for real-time, unsupervised waveform classification of multineuron recordings

1989 ◽  
Vol 30 (1) ◽  
pp. 59-69 ◽  
Author(s):  
Andreas K. Kreiter ◽  
Ad M.H.J. Aertsen ◽  
George L. Gerstein
Keyword(s):  
Real Time ◽  
Low Cost

scholarly journals On the classification of simple and complex biological images using Krawtchouk moments and Generalized pseudo-Zernike moments: a case study with fly wing images and breast cancer mammograms

2021 ◽  
Vol 7 ◽  
pp. e698
Author(s):  
Jia Yin Goh ◽  
Tsung Fei Khang
Keyword(s):  
Image Analysis ◽  
Classification Performance ◽  
Image Features ◽  
Zernike Moments ◽  
Taxonomic Classification ◽  
Learning Context ◽  
Orthogonal Moments ◽  
Krawtchouk Moments

In image analysis, orthogonal moments are useful mathematical transformations for creating new features from digital images. Moreover, orthogonal moment invariants produce image features that are resistant to translation, rotation, and scaling operations. Here, we show the result of a case study in biological image analysis to help researchers judge the potential efficacy of image features derived from orthogonal moments in a machine learning context. In taxonomic classification of forensically important flies from the Sarcophagidae and the Calliphoridae family (n = 74), we found the GUIDE random forests model was able to completely classify samples from 15 different species correctly based on Krawtchouk moment invariant features generated from fly wing images, with zero out-of-bag error probability. For the more challenging problem of classifying breast masses based solely on digital mammograms from the CBIS-DDSM database (n = 1,151), we found that image features generated from the Generalized pseudo-Zernike moments and the Krawtchouk moments only enabled the GUIDE kernel model to achieve modest classification performance. However, using the predicted probability of malignancy from GUIDE as a feature together with five expert features resulted in a reasonably good model that has mean sensitivity of 85%, mean specificity of 61%, and mean accuracy of 70%. We conclude that orthogonal moments have high potential as informative image features in taxonomic classification problems where the patterns of biological variations are not overly complex. For more complicated and heterogeneous patterns of biological variations such as those present in medical images, relying on orthogonal moments alone to reach strong classification performance is unrealistic, but integrating prediction result using them with carefully selected expert features may still produce reasonably good prediction models.

scholarly journals Real-Time Classification of Patients with Balance Disorders vs. Normal Subjects Using a Low-Cost Small Wireless Wearable Gait Sensor

Biosensors ◽  
2016 ◽  
Vol 6 (4) ◽  
pp. 58 ◽  
Author(s):  
Bhargava Nukala ◽  
Taro Nakano ◽  
Amanda Rodriguez ◽  
Jerry Tsay ◽  
Jerry Lopez ◽  
...  
Keyword(s):  
Real Time ◽  
Low Cost ◽  
Normal Subjects ◽  
Balance Disorders ◽  
Real Time Classification

EXACT: an Expert System for Real Time X-Ray Image Analysis and Classification of Weldings

1992 ◽  
pp. 646-650
Author(s):  
Giorgio Montini ◽  
Maria Grazia Bordini ◽  
Flavio Boschetti ◽  
Stefano Ripamonti
Keyword(s):  
Image Analysis ◽  
Expert System ◽  
Real Time ◽  
X Ray

scholarly journals Quantifying colour difference in animals with variable patterning

2019 ◽  
Author(s):  
Tereza Dračková ◽  
Radovan Smolinský ◽  
Zuzana Hiadlovská ◽  
Matej Dolinay ◽  
Natália Martínková
Keyword(s):  
Image Analysis ◽  
Colour Pattern ◽  
Colour Difference ◽  
Spectrophotometric Methods ◽  
Dominant Colour ◽  
Light Reflectance ◽  
Sand Lizard ◽  
Lacerta Agilis ◽  
Colour Patterns ◽  
The Impact

AbstractColour pattern influences behaviour and modifies survival of organisms through perception of light reflectance. Spectrophotometric methods used to study colour navigate between precision and accuracy of reflectance across wavelengths, while photographic methods are generally used to assess the complexity of colour patterns. Here, we compare how colours characterised using point measurements (simulating spectrophotometry) on the skin of a sand lizard (Lacerta agilis) differ from colours estimated by clustering pixels in a photograph of the lizard’s body. We found that point measurements adequately represented the dominant colour of the lizard; however, where colour patterning influenced measurement geometry, image analysis outper-formed point measurement as regards stability between technical replicates on the same animal. The greater colour variation established from point measurements increased further under controlled laboratory illumination. Both methods revealed lateral colour asymmetry in sand lizards. We conclude that studies assessing the impact of colour on animal ecology and behaviour should utilise hyperspectral imaging, followed by image analysis that encompasses the whole colour pattern.

Image analysis of the ventral colour pattern discriminates between Spectacled salamanders, Salamandrina perspicillata and S. terdigitata (Amphibia, Salamandridae)

2010 ◽  
Vol 31 (2) ◽  
pp. 273-282 ◽  
Author(s):  
Claudio Angelini ◽  
Carlo Utzeri ◽  
Corrado Costa ◽  
Paolo Menesatti ◽  
Stefano Raimondi
Keyword(s):  
Image Analysis ◽  
Discriminant Analysis ◽  
Colour Pattern ◽  
Pectoral Girdle ◽  
Correct Classification ◽  
Anova Analysis ◽  
Quantitative Image ◽  
Different Populations ◽  
Colour Patterns ◽  
Two Populations

AbstractIn the present study, we applied statistical methods to quantitative image analysis of the persistent and individual ventral colour pattern of Salamandrina salamanders, in order to discriminate between individuals of the two species belonging to this genus. Pictures of 238 individuals from three populations of S. perspicillata and pictures of 95 S. terdigitata from two populations were analysed. Partial least squares discriminant analysis (PLSDA) classified 98.78% of individuals into the correct species. PLSDA reaches lower percentages of correct classification when applied to discriminate individuals from different populations of the same species (74.14% for S. perspicillata, 78.26% for S. terdigitata). An ANOVA analysis of colour abundances in different body sectors reveals significant differences between species. The results show that colour pattern has a specific basis, the most discriminant areas being the head and the pectoral girdle. We discuss these results in the light of the proposed evolutionary scenarios of the species, and suggest that ventral colour patterns were driven by founder effect.

Sign in / Sign up

Export Citation Format

Share Document