Maryam Soltani Kazemi; Saman Abdanan; Mokhtar Heidari; Seyed Mojtaba Faregh
Abstract
Introduction: Blackberry is a perennial woody plant native to warm, temperate, and subtropical regions of Asia, Africa, North America, and southern Europe. Blackberry fruit (Morus Alba Varnigra L.) is a rich source of anthocyanins. Furthermore, it has great many medicinal properties such as an antidiabetic ...
Read More
Introduction: Blackberry is a perennial woody plant native to warm, temperate, and subtropical regions of Asia, Africa, North America, and southern Europe. Blackberry fruit (Morus Alba Varnigra L.) is a rich source of anthocyanins. Furthermore, it has great many medicinal properties such as an antidiabetic (Asano et al., 2001), antihyperglycemic (Andallu &Varadacharyulu, 2003), antiviral (Du et al., 2003), antioxidative (Kim et al., 1998), hypolipidemic (El-Beshbishy et al., 2006), and neuroprotective (Kang et al., 2006). However, measuring some qualitative and nutrient parameters in this fruit such as anthocyanins, vitamin C and phenol directly has become a major issue (Pace et al, 2013). Therefore, researchers try to predict aforementioned parameters by mathematical models. One of these models is the fractal model which is widely used to study the properties of the images/objects (Welstead, 1999; Zhang, 2007). Recently, many researchers try to develop different methods to classify or predict the agricultural products quality (Langner, 2001). In a research Seng and Mirisaee (2009) designed a machine vision algorithm for classification of fruits (apple, lemon, strawberry and banana) based on color, shape and size. Li and He investigated the application of visible/near infrared spectroscopy (Vis/NIRS) for measuring the acidity of Chinese bayberry. The model for prediction the acidity (r=0.963), standard error of prediction (SEP) 0.21 with a bias of 0.138 showed an excellent prediction performance. Therefore, the aim of this study was to predict biochemical parameters (TSS, anthocyanins, browning compounds, total phenols, Ascorbic Acid, pH) of blackberry juice, nondestructively, during maturity process using machine vision and fractal analysis. To develop predictive models and data classification, artificial neural networks (ANN) and k-nearest neighbor (k-NN) were used.
Materials and methods: Eighty blackberry fruits from four maturity stages were selected. The fruit samples were placed in airtight polyethylene bags, stored in an ice-filled cooler and transported to the laboratory to keep at cold temperature (4±1◦C).
Fresh fruits were squeezed by a household juicer, and immediately transported to the laboratory. Then, juice images were taken with a digital camera CASIO (Model Exilim EX-ZR700; 16 megapixels, Japan) and stored to the computer.
There are several ways to measure the fractal dimension. In this study, the proposed method by Addison (2005) was used to calculate the fractal dimension.
Feature selection is one of the issues that have been raised in the context of machine learning. In this study, floating search method feature selection was used (Pudil et al., 1994).
k-Nearest Neighbor (k-NN) is one of the simplest methods for information classification. In this study, the Euclidean distance between two points was used to determine the distance between the input data with the training patterns (Mucherino et al., 2009).
To train the neural network, Levenberg–Marquardt training algorithm was used. In this regard, the data were divided randomly into two parts (two-thirds for training (60) and one-third (20) for testing the network). Input parameters were Xa, Xb, X, Y and S and output parameters were TSS, ascorbic acide, acidity, polyphenols, anthocyanins, brown-causing substances and pH. Moreover, in this study, the number of neurons in the hidden layer was selected by trial and error method.
After selecting the best features extracted from the image processing with the highest correlation with chemical parameters (TSS, anthocyanins, total phenols, ascorbic acid, and pH), a machine vision system was designed and built to be able to determine the internal properties of black mulberry juice.
Total soluble solids (TSS) were determined by a hand refractometer device (model: MT03 Japan). The anthocyanin content was estimated following the procedure of Holecraft et al., (1998). Ascorbic acid of the juice was measured by titration with copper sulfate and potassium iodide based on the Barakat et al., (1973) procedure. Titratable acidity was measured according to the Eksi and Turkman, (2011) method. Waterhouse (2002) method was used for measuring the total phenol of juice.
Results and discussion: Artificial neural network (ANN) and (k-NN) models were used to predict the changes of anthocyanin (AC), browning compounds, ascorbic acid (AA), total phenols (TP), acidity, TSS and pH in mulberry juice during ripening based on fractal analysis. Two features namely: maximum fractal and fractal curve area were selected from five extracted features and used for training neural network and k-NN classifier
Saman Abdanan; Mehran Nouri; Maryam Soltani Kazemi; Somaye Amraei
Abstract
Introduction: Nutritional quality of food during storage has become increasingly an important problem. The loss of some nutrients such as ascorbic acid (vitamin C) might be a critical factor for the shelf life of some products as citrus juice concentrates, since vitamin C content of citrus juices undergoes ...
Read More
Introduction: Nutritional quality of food during storage has become increasingly an important problem. The loss of some nutrients such as ascorbic acid (vitamin C) might be a critical factor for the shelf life of some products as citrus juice concentrates, since vitamin C content of citrus juices undergoes destruction during storage (Plaza et al., 2011a). Ascorbic acid is an important component of our nutrition and used as additive in many foods because of its antioxidant capacity. Thus, it increases quality and technological properties of food as well as nutritional value (Larisch et al., 1998). However, ascorbic acid is an unstable compound and even under minor desirable conditions it decomposes easily. Degradation of ascorbic acid proceeds both aerobic and anaerobic pathways and depends upon many factors such as oxygen, heat, light, storage temperature and storage time. Oxidation of ascorbic acid occurs mainly during the processing of citrus juices, whereas, anaerobic degradation of ascorbic acid mainly appears during storage which is especially observed in thermally preserved citrus juices (Lee & Coates, 1999). It was reported that several decomposition reactive products occur via the degradation of vitamin C and these compounds may combine with amino acids, thus result in formation of brown pigments (Wibowo et al., 2015). In recent years, several nondestructive methods such as computer vision, spectroscopy, ultrasonic have been developed to objectively evaluate different agricultural materials (Abdanan Mehdizadeh et al., 2014; Wang and Paliwal, 2007). However, due to the physical properties of fruit, machine vision has not been discussed much in the literature (Fernanzed-Vazquez et al., 2011). One disadvantage of using spectroscopic methods is that these methods require expensive equipment and also carrying these instruments are difficult. On the contrary, the combining of a digital camera and its image processing software that replaces the traditional measuring instruments have been widely used to provide a cheaper and versatile form to measure some internal quality of many foods. Therefore, the goal of this research is to determine the best features of surface texture (entropy, homogeneity, contrast, correlation and prominence) in order to predict quality factors (pH, acidity, soluble solids and ascorbic acid) of citrus juice.
Materials and methods: Orange, sour lemon, sour orange and tangerine fruit were obtained from one of local marker in Ahvaz, Iran. All samples were washed and the juice was extracted using a Pars-Khazar rotary extractor. The citrus juice, (sour orange, orange, lemon and tangerine) immediately after pasteurization process, were kept at a temperature of refrigerators (4º C) for 60 days in darkness. After taking images of the citrus juice, pH, acidity, ascorbic acid and soluble solids were measured on days 0, 20, 40 and 60.
Physicochemical analysis:
The pH of samples was determined with a pH meter (Methrohm, 827 pH lab, Switzerland). The soluble solids content of concentrates was determined as o Bx using a refractometer (Atago Co, Ltd. Carnation, WA). Total titrable acidity was assessed by titration with sodium hydroxide (0.1 N) and expressed as % citric acid (Kimball, 1999). Ascorbic acid was determined using 2,6-dichlorophenolindophenol by visual titration (Kabasakalis, 2000).
Imaging and color analysis:
Samples were placed under the camera (Canon PowerShot SX60 HS, Japan) of a computer vision system at the distance of 300 mm inside a black box with the size of 100 ×100 ×100 cm3. The samples were illuminated using four fluorescent lamps at the angle of 45o in relation with the sample.
After taking images, color images were transformed to L*a*b* color space. The L* parameter (luminosity) is an attribute by which a surface emits more or less light and can take values between 0 (absolute black) to 100 (absolute white). The parameters a* and b* represent the chromaticity, where a* defines the red-green component (red for positive values and green for negative values) and the b* parameter defines the yellow-blue component (yellow for positive values and blue for negative values) (Quevedo et al., 2009a). Following color transformation, the well-known textural parameter called the Gray-Level Co-Occurrence Matrix (GLCM function) was applied to the images and six features through Eq. 1-6 were extracted (Table 1).
Results and discussion: Color changes during storage in three color channels L*,a*,b* showed that the variation of channel L* could illustrate deterioration of citrus juice better than other channels. In the Figure 1, a gallery of four selected images (taken at different times in the experiment) corresponding to one sour orange sample and their corresponding surface intensity (based on L* value) are showed.
The results of statistical analysis depicted that acidity and ascorbic acid, in four citrus juices, significantly (P