Supervised classification of bruised apples with respect to the time after bruising on the basis of hyperspectral imaging data

Visual detection of apple bruises using AdaBoost algorithm and hyperspectral imaging

“…The result demonstrated that the hyperspectral imaging technique with the best threshold waveband ratio algorithm could detect pear bruises accurately. Piotr et al [9] examined the applicability of hyperspectral imaging in the visible and near-infrared (400-1000 nm) and short wavelength infrared (1000-2500 nm) ranges for classification of apple bruising. They found hyperspectral imaging with supervised classification models could distinguish time after bruising respect to five varieties of apples.…”

Non‐destructive classification of apple bruising time based on visible and near‐infrared hyperspectral imaging

“…Bruised apples are not only prone to being infected by bacteria but may also potentially infect other healthy fruit, thus reducing storability . The detection of time after apple bruising can help to assess the quality and safety and determine the storage method of apples . From a practical point of view, the precise prediction of time elapsed from the occurrence of bruising can help to find and solve the problems that cause apple bruising from harvesting to sale, in order to reduce the number of bruised apples.…”

“…Recently, several techniques based on hyperspectral imaging have been applied to detect bruising and classify the bruising time of apples . A new dimension reduction method known as hyperspectroscopy was proposed in which the three dimensions of hyperspectral images were reduced to one dimension while retaining spatial and spectral information .…”

Semi-supervised learning of hyperspectral image segmentation applied to vine tomatoes and table grapes

“…These methods can be divided into four groups, namely a) agglomerativehierarchicalclusteringinaone-step(1) and a two-step procedure (2), b) k-means clustering in a one-step (3) and a two-step (4) procedure, c) multivariateGaussianmixturemodelsinaone-step (5) and a two-step (6) procedure and d) a combination of two of the preceding methods, namelycombinationof(b)and(a) (7),and(b)and(c) (8).…”

“…Segmentation in the spectral domain ignores the spatial position of the pixel spectra in the image and onlylooksatthesimilarityofthepixelspectra.Forthis purpose,theinformationfrommultiplewavelengthsis combinedtoobtainagoodclassification.Forexample, ElMasry et al 6 subtracted images at different wavelengths to classify meat, fat and background. Baranowski et al 7 useddifferentsupervisedclassificationmethods, suchassupportvectormachines(SVM),functionaltrees, nearest-neighbourclassifiersandregressionmethods,to distinguishbruisedappletissuefromsoundtissueand found that logistic regression gave the best classification resultswith a correct classification rate of 98.8%. Lü et al 8 applied SVM on hyperspectral data from kiwifruit to detect bruiseswith a misclassification rate of 12.5%.…”