Multispectral Vision for Monitoring Peach Ripeness (original) (raw)
Related papers
Multispectral images of peach related to firmness and maturity at harvest
Journal of Food Engineering, 2009
Two multispectral maturity classifications for red soft-flesh peaches ('Kingcrest', 'Rubyrich' and 'Richlady' n = 260) are proposed and compared based on R (red) and R/IR (red divided by infrared) images obtained with a three CCD camera (800 nm, 675 nm and 450 nm). R/IR histograms were able to correct the effect of 3D shape on light reflectance and thus more Gaussian histograms were produced than R images. As fruits ripened, the R/IR histograms showed increasing levels of intensity. Reference measurements such as firmness and visible spectra also varied significantly as the fruit ripens, firmness decreased while reflectance at 680 nm increased (chlorophyll absorption peak).
Food Analytical Methods
Bananito (Musa acuminata, AA) fruit in three maturity stages (stages 2, 4 and 6) were investigated in this study. Correlation analysis was conducted between fruit firmness, soluble solids content (SSC) and several colour parameters. Point-measured spectroscopy (Vis-point) and spatial-measured hyperspectral imaging (Vis-HSI) were applied to collect visible spectra (400-740 nm) from the fruit peel. Three classification methods, k-nearest neighbour (k-NN), soft independence modelling of class analogy (SIMCA) and partial least square discriminate analysis (PLSDA), were applied for maturity stage classification. Results showed that a strong correlation was found between SSC and peel yellowness index (r = 0.92). Ripeness classification models developed using Vis-HSI data performed better than using Vis-point data. The best model based on PLSDA achieved a total correct classification rate of 93.3%. A simplified PLSDA model established on three wavelengths (650 nm, 705 nm and 740 nm) derived from the regression vector provided an equivalent model performance. This study demonstrated the use of hyperspectral imaging for accurate and non-destructive ripeness classification of bananito fruit based on the visible peel spectra, and the potential of using the three feature wavelengths to develop a multispectral imaging system for industrial application.
Assessing Multiple Quality Attributes of Peaches Using Optical Absorption and Scattering Properties
Transactions of the ASABE, 2012
The objective of this research was to measure the spectral absorption (µ a) and reduced scattering coefficients (µ s ') of peaches, using a hyperspectral imaging-based spatially resolved method, for maturity/quality assessment. A newly developed optical property measuring instrument was used for acquiring hyperspectral reflectance images of 500 'Redstar' peaches. The µ a and µ s ' spectra for 515 to 1,000 nm were extracted from the spatially resolved reflectance profiles using a diffusion model coupled with an inverse algorithm. The absorption spectra of peach fruit were marked with absorption peaks around 525 nm for anthocyanin, 620 nm for chlorophyll-b, 675 nm for chlorophyll-a, and 970 nm for water, while µ s ' decreased monotonically with the increasing wavelength for most of the tested samples. Both µ a and µ s ' were correlated with peach firmness, soluble solids content (SSC), and skin and flesh color parameters. Better correlation results for partial least squares models were obtained using the combined values of µ a and µ s ' (i.e., µ a × µ s ' and µ eff) than using µ a or µ s ', where µ eff is the effective attenuation coefficient: µ eff = [3µ a (µ a + µ s ')] 1/2. The results were further improved using least squares support vector machine models, with values of the best correlation coefficient for firmness, SSC, skin lightness, and flesh lightness being 0.749 (standard error of prediction or SEP = 17.39 N), 0.504 (SEP = 0.92 °Brix), 0.898 (SEP = 3.45), and 0.741 (SEP = 3.27), respectively. These results compared favorably to acoustic and impact firmness measurements, whose correlations with destructive measurements were 0.639 and 0.631, respectively. The hyperspectral imaging-based spatially resolved technique is useful for measuring the optical properties of peach fruit, and it has good potential for assessing fruit maturity/quality attributes.
Journal of Food Science and Technology, 2015
Mechanical injuries to fruits are often caused due to hidden internal damages that results in bruising of fruit. This is a serious cause of concern to the fruit industry, as spoiled or bruised fruits directly impact the producers profit. Hyperspectral imaging method can provide the ability to identify these internal bruises to classify these fruits as normal and injured (bruised), reducing time and increasing efficiency over the sorting line in marketing chain. In this paper, we have used three types of fruits i.e., apple, chikoo & guava for experiments. The mechanical injury is introduced by manual impact on surface of the fruits sample and hyperspectral images were captured over nine narrow band pass filters to produce hyperspectral cubes for a fruit. Three types of methods were used for the data processing. First two are non-invasive in nature i.e., pixel signatures over hyperspectral cubes and second is prediction model for classification of fruits quality into normal and bruised using feed forward back propagation neural network. Finally, invasive method is used to confirm the said prediction model using parameters like firmness, Total Soluble Solid (TSS) and weight with Principal Component Analysis. Results obtained by hyperspectral imaging method indicate scope for non-invasive quality control over spectral wavelength range of 400-1000 nm.
Classification of Peach Fruits in Ripe , Unripe and Damaged Towards Automated Harvest
2021
Using computer vision technology, specifically convolutional neural networks, a solution was proposed to perform the recognition of ripe peach fruits, as well as the identification of damaged fruits. The purpose is to obtain fruits with the appropriate level of quality for their commercialization. To achieve this purpose, images of peaches were obtained in an uncontrolled environment. Digital images were cropped until the area of interest was obtained. Three data sets were configured: the first, for ripe and unripe peaches; the second, also of ripe and unripe peaches but only focused on a textural area, and the third, of healthy and damaged peaches. A convolutional neural network was applied, which was programmed in the Python language, the Keras and TensorFlow libraries. During the tests, a precision of 95.31 % was obtained when choosing between mature and immature. While when classifying healthy and damaged peaches, 92.18 % accuracy was obtained. Finally, when classifying the thre...
Computer Vision System Applied to Classification of “Manila” Mangoes During Ripening Process
Food and Bioprocess Technology, 2013
This work develops automated systems based on computer vision to improve the quality control and sorting of dried figs of Cosenza (protected denomination of origin) focusing on two research issues. The first one was based on qualitative discrimination of figs through colour assessment comparing the analysis of colour images obtained using a digital camera, with those obtained according to conventional instrumental methods, i.e. colourimetry currently done in laboratories. Data were expressed in terms of CIE XYZ, CIELAB and HunterLab colour spaces, as well as the browning index measurement of each fruit, that were analyzed using PCA and PLS-DA based methods. The results showed that both chroma meter and image analysis allowed a complete distinction between high quality and deteriorated figs, according to colour attributes. The second issue had the purpose to develop image processing algorithms to achieve real-time sorting of figs using an experimental prototype based on 2 machine vision, advancing an industrial application. An extremely high 99.5% of deteriorated figs were classified correctly as well as 89.0% of light good quality figs. Lower percentage was obtained for dark good quality figs but results were acceptable since the most of the confusion was among the two classes of good product.
A Survey of Computer Vision and Soft Computing Techniques for Ripeness Grading of Fruits
Now a 'days agriculture is one field where automated systems for classification and grading of fruits can be very useful not only for farmers but at experts in taking fast and accurate decisions. Over some recent year’s customers and buyers lifestyles and needs have increased and there have been many changes. Such lifestyle and changes have proved to be a challenge for the farmers and experts in the field of agriculture. Because of this with the help of technology a well-defined automated system need to be present in the market which would grade and analyze the agricultural products with minimum error. Thus giving the farmers best product to sell and make the customers feel happy for the money they have spent. This survey paper presents the literature review of various related systems and earlier studies done in the field grading of fruits on the basis of their ripeness. Then the comparative study of different computational techniques for ripeness grading has been done.
Optical Techniques for Assessing the Fruit Maturity Stage
2002 Chicago, IL July 28-31, 2002, 2002
During fruit ripening, chlorophyll degradation is responsible for the degreening of the ground color, which is a well−established ripeness indicator for several species. In completely red−pigmented cultivars of fruits such as apples and peaches, this process is not visible, being masked by anthocyanins in the skin. Two different optical systems were developed to non−destructively assess the chlorophyll content in these fruits, to estimate ripeness, and to optimize harvesting and postharvest management. A fluorescence imaging system equipped with a UV−blue actinic light was used to obtain fluorescence images of fruit in which the gray level of pixels correlated (R 2 = 0.81) with the firmness of fresh apples (Malus domestica cv. Red Delicious). With this technique it was possible to estimate changes in the firmness and soluble solids sugar content of stored Red Delicious apples undergoing no detectable hue change in the skin. Using the same system with a red actinic light, fluorescence correlated fairly well with firmness for fresh peaches and nectarines (Prunus persica cv. Elegant Lady, Summer Rich, and Morsiani 90), even though the detected fluorescence signal was low in intensity. A laser−diode based, dual−band reflectance probe was developed and tested on fresh peaches (cv. Summer Rich) and stored apples (cv. Royal Gala). The R/IR index, defined as the ratio of the signal measured in red and near−infrared bands, was found to correlate with the chlorophyll content of the fruits (R 2 = 0.66), regardless of fruit species and anthocyanin presence. The R/IR index was used to track the postharvest ripening process for fresh peaches harvested at different maturity stages.