Figure 1 - uploaded by Manuel Castillo
Content may be subject to copyright.
Schematic of computer vision system coupled to the cheese vat with twin corotating stirrers. CCD = charge-coupled device.
Source publication
Optical characteristics of stirred curd were simultaneously monitored during syneresis in a 10-L cheese vat using computer vision and colorimetric measurements. Curd syneresis kinetic conditions were varied using 2 levels of milk pH (6.0 and 6.5) and 2 agitation speeds (12.1 and 27.2 rpm). Measured optical parameters were compared with gravimetric...
Contexts in source publication
Context 1
... in expulsion of whey from the curd grains (Walstra et al., 1985; Dejmek and Walstra, 2004; Castillo et al., 2006). Syneresis follows the cutting of milk coagulum into cubes and is generally promoted by thermal or mechanical treatments, or both. Moisture is removed from cheese curd in a number of stages in cheese making. Most of the moisture and lactose are removed during syneresis in the cheese vat. Further moisture is removed during “complementary syneresis” [i.e., during postvat curd-handling (draining, salting, molding, pressing), and evaporation, which is a function of the ripening environment]. Moisture control of all these stages has implications for final cheese quality and yield (Weber, 1989; Castillo, 2001). In par- ticular, control of curd moisture in the vat is essential for control of lactose and curd pH and also affects the removal of moisture in subsequent steps, and in turn, enables the cheese manufacturer to improve control of the biochemical processes during ripening. Syneresis also influences protein and fat losses in whey, which in turn affects cheese yield. At present, in the cheese industry worldwide, syneresis is empirically controlled, and there are no technologies available for online monitoring of curd syneresis to assist the cheesemaker. Various empirical techniques have been developed to study the kinetics of syneresis as reviewed by Walstra, van Dijk and Geurts (1985), and Walstra (1993). First order kinetics has been reported by many authors to describe the rate of syneresis (Marshall, 1982; Peri et al., 1985; Castillo et al., 2006). Previous techniques developed to monitor syneresis include determination of the moisture content of curd, estimation of volume of shrunken curd by liquid displacement, and measuring the volume of whey drained from the curd directly (Lawrence, 1959a; Marshall, 1982; Daviau et al., 2000) or by determining the degree of dilution of added tracers (Beeby, 1959; Grundelius et al., 2000). Renault et al. (1997) developed an original off-line method to monitor curd shrinkage based on image analysis. The method did not submerse the curd in whey nor did it use stirring during syneresis and thus deviates from standard in- dustrial conditions. In general, the instantaneous measurement of curd moisture during syneresis is challeng- ing, which limits precision and accuracy of all reported methods (Zviedrans and Graham, 1981). Indeed, the experimental conditions are often too distant from in- dustrial practice to extrapolate results. Factors affecting syneresis rate and extent, including milk composition and pretreatment, coagulation factors, rheological properties of the gel at cutting, curd surface area, external pressure, and curd temperature and pH, have been widely reviewed (Marshall, 1982; Walstra et al., 1985; Pearse and Mackinlay, 1989; Weber, 1989; van Vliet et al., 1991; Lucey, 2001; Walstra et al., 2001). In this study the kinetics of syneresis were changed by altering milk pH and stirring speed during syneresis. It is clear from observation during cheese manufac- turing that the color of milk proceeds from a continuous white mass before cutting to a mixture of white particles in a mostly clear yellowish whey. Direct observation also reveals that light scattered by whey becomes increasingly yellow in hue as syneresis progresses. Based on those 2 empirical observations, it was hypothesized that a) a ratio of the white and yellow areas calculated by processing the images obtained after gel cutting would provide valuable information about syneresis kinetics; and b) the overall color of the curd/whey mixture would also change during syneresis and would carry useful syneresis kinetic information. The objectives of this study were 1) to propose and test 2 original methods for syneresis monitoring in a cheese vat based on color measurement, 2) to evaluate the color parameters obtained from these methods to predict important indices of curd production, and 3) to assess the capability of these methods to respond to the effects of milk pH and stirring speed on syneresis. The 2 approaches being evaluated here are 1) the use of computer vision to distinguish curd from whey and 2) the monitoring of color changes in a cheese vat during syneresis. A randomized factorial experimental design with 2 factors, 2 levels per factor, and 3 replicates was used in this study to evaluate the use of computer vision and a colorimeter for monitoring curd syneresis in a 10-L double-O cheese vat (Pierre Guerin Technologies, Mauze, France). Milk was coagulated using a fixed concentration of calcium chloride and rennet. A broad range of syneresis reaction rates was ensured by coagu- lating the milk at 2 different levels of pH (i.e., 6.0 and 6.5) and by stirring the curd/whey mixture at 2 different speeds (i.e., 12.1 and 27.2 rpm) after cutting the gels. A total of 12 trials ( nab = 3 ؒ 2 2 ) were performed using this design. The double-O cheese vat had twin corotating stirrers (Figure 1). The stirring blades (80 × 50 mm) were set at an angle of 30 ° , with a clearance of 8 to 10 mm from the bottom, which resulted in a 3-dimensional flow of curd/whey mixture during stirring. Commercial pasteurized low-fat milk (Avonmore Slimline Milk, Glanbia, Ireland) was used in this study. The low-fat milk had protein and fat concentrations of 38 and 3 g/L, respectively, and contained 1.36 g/L of calcium. Calcium chloride (CaCl 2 ؒ 2H 2 O) was added (0.156 g/kg of milk), and milk was left to equilibrate for 1 h at 4 ° C before initial pH adjustment. Initial pH adjustment was carried out on the milk at 4 ° C using HCl (1.0 M ) 1 or 2 d before analysis, and the milk was stored at 4 ° C until day of analysis. On the day of analysis, 10 kg of milk was added to the cheese vat for each trial, and the milk was heated to 32 ° C via the vat’s heating jacket while being stirred at 27.2 rpm. The milk was held at this temperature and final pH adjustments were carried out using HCl (1.0 M ) and NaOH (1.0 M ) at 32 ° C. The milk coagulant used was 100% recombinant chymosin (CHY-MAX extra, EC 3.4.23.4, isozyme B, 600 IMCU/mL; Chr Hansen Ireland Ltd., Cork, Ireland). The rennet was added to the milk (0.18 g of chymosin/kg of milk) in the vat while being stirred constantly at 55 rpm. Stirring was stopped after 3 min, and the stirrers were replaced with twin cutting blades. Small amplitude oscillatory rheometry was used to determine the gel cutting time ( t cut ). At 3 min after rennet addition, ∼ 3.5 mL aliquot of milk was removed from the vat and inserted in a controlled stress rheometer (Carri-med CSL 2 -100, TA Instruments, Crawley, UK). The instrument was operated at 32 ° C in oscilla- tion mode at a shear strain of 0.02 and a frequency of 1 Hz using double-gap concentric cylinder geometry. Cutting time was determined by the rheometer as the time at which milk gel reached storage modulus ( G ′ ) = 43 Pa. At t cut the twin cutting blades were activated and the gel was cut at a constant speed of 6 rpm for 15 s, then allowed to heal for 1 min, cut a second time at a speed of 16 rpm for 15 s, allowed to heal for 1 min, and cut a third time at speed 16 rpm for 10 s and allowed to heal for 1 min (Johnston et al., 1998). The moment of initiating gel cutting was taken as the refer- ence time ( t = 0) for all subsequent measurements. Samples of curd/whey mixture ( ∼ 180 mL) were removed from the vat using a ladle at t = 5 min and at 10-min intervals thereafter up to t = 85 min. Curd and whey were immediately separated using a 75- m nu- merical aperture stainless-steel sieve (AGB, Dublin, Ireland), and the 2 phases were weighed without delay using a precision balance for curd and whey yield calcu- lation. The sieve characteristics were selected to ensure that whey fat globules were not retained. Approxi- mately 3 g of curd and 5 g of whey were then accurately weighed into preweighed aluminum dishes for determination of total solids of curd and whey, respectively, by drying in triplicate in a convection oven at 102 ° C for 16 h (Fagan et al., 2007). The yield of whey was ex- pressed as a percentage of the initial weight of milk used in each trial. A computer vision system was coupled to a 10-L cheese vat, as shown in Figure 1, to measure color changes in the curd/whey mixture during syneresis (Figure 2). The computer vision system used in this study con- sisted of a high-quality 3-CCD Sony XC-003P camera (Sony Corporation, Tokyo, Japan) connected to a computer for image analysis with an IC-RGB frame grabber (Imaging Technology, Billerica, MA). Images were captured under 2 fluorescent lamps (Imaging Technology) with plastic light diffusers. The camera captured images ( ∼ 100 mm 2 ) of the surface of the curd/whey mixture during syneresis while the mixture was being stirred. Images were captured at t = 5 or 6 min and at 1-min intervals thereafter up to t = 85 min. Care was taken to capture each image at the same stirrer position. Each image was subdivided into areas of curd or whey, respectively, according to a color threshold. This was achieved by converting each image into a greyscale image, de-noising it using a 2-dimensional adaptive noise- removal filter (Lim, 1990), enhancing the image con- trast-limited adaptive histogram equalization (MathWorks, 1998), and defining a threshold value between curd and whey based on human perception to ensure clear separation of the curd and whey, using Matlab V 6.5.1 (The Mathworks Inc., Natick, MA). The areas of white ( A w ) and yellow ( A y ) in each image were determined mathematically, and their ratio ( a wy = A w / A y ) was calculated and used as a parameter to follow syneresis. Red, green, and blue ( RGB ) values averaged across the images were also recorded using Matlab V 6.5.1 and used to follow syneresis. These RGB values were used to calculate ∆ E RGB using the Euclidean formula Eq. [1], to give a computer vision metric as a function of time with respect to the ...
Context 2
... scattered by whey becomes increasingly yellow in hue as syneresis progresses. Based on those 2 empirical observations, it was hypothesized that a) a ratio of the white and yellow areas calculated by processing the images obtained after gel cutting would provide valuable information about syneresis kinetics; and b) the overall color of the curd/whey mixture would also change during syneresis and would carry useful syneresis kinetic information. The objectives of this study were 1) to propose and test 2 original methods for syneresis monitoring in a cheese vat based on color measurement, 2) to evaluate the color parameters obtained from these methods to predict important indices of curd production, and 3) to assess the capability of these methods to respond to the effects of milk pH and stirring speed on syneresis. The 2 approaches being evaluated here are 1) the use of computer vision to distinguish curd from whey and 2) the monitoring of color changes in a cheese vat during syneresis. A randomized factorial experimental design with 2 factors, 2 levels per factor, and 3 replicates was used in this study to evaluate the use of computer vision and a colorimeter for monitoring curd syneresis in a 10-L double-O cheese vat (Pierre Guerin Technologies, Mauze, France). Milk was coagulated using a fixed concentration of calcium chloride and rennet. A broad range of syneresis reaction rates was ensured by coagu- lating the milk at 2 different levels of pH (i.e., 6.0 and 6.5) and by stirring the curd/whey mixture at 2 different speeds (i.e., 12.1 and 27.2 rpm) after cutting the gels. A total of 12 trials ( nab = 3 ؒ 2 2 ) were performed using this design. The double-O cheese vat had twin corotating stirrers (Figure 1). The stirring blades (80 × 50 mm) were set at an angle of 30 ° , with a clearance of 8 to 10 mm from the bottom, which resulted in a 3-dimensional flow of curd/whey mixture during stirring. Commercial pasteurized low-fat milk (Avonmore Slimline Milk, Glanbia, Ireland) was used in this study. The low-fat milk had protein and fat concentrations of 38 and 3 g/L, respectively, and contained 1.36 g/L of calcium. Calcium chloride (CaCl 2 ؒ 2H 2 O) was added (0.156 g/kg of milk), and milk was left to equilibrate for 1 h at 4 ° C before initial pH adjustment. Initial pH adjustment was carried out on the milk at 4 ° C using HCl (1.0 M ) 1 or 2 d before analysis, and the milk was stored at 4 ° C until day of analysis. On the day of analysis, 10 kg of milk was added to the cheese vat for each trial, and the milk was heated to 32 ° C via the vat’s heating jacket while being stirred at 27.2 rpm. The milk was held at this temperature and final pH adjustments were carried out using HCl (1.0 M ) and NaOH (1.0 M ) at 32 ° C. The milk coagulant used was 100% recombinant chymosin (CHY-MAX extra, EC 3.4.23.4, isozyme B, 600 IMCU/mL; Chr Hansen Ireland Ltd., Cork, Ireland). The rennet was added to the milk (0.18 g of chymosin/kg of milk) in the vat while being stirred constantly at 55 rpm. Stirring was stopped after 3 min, and the stirrers were replaced with twin cutting blades. Small amplitude oscillatory rheometry was used to determine the gel cutting time ( t cut ). At 3 min after rennet addition, ∼ 3.5 mL aliquot of milk was removed from the vat and inserted in a controlled stress rheometer (Carri-med CSL 2 -100, TA Instruments, Crawley, UK). The instrument was operated at 32 ° C in oscilla- tion mode at a shear strain of 0.02 and a frequency of 1 Hz using double-gap concentric cylinder geometry. Cutting time was determined by the rheometer as the time at which milk gel reached storage modulus ( G ′ ) = 43 Pa. At t cut the twin cutting blades were activated and the gel was cut at a constant speed of 6 rpm for 15 s, then allowed to heal for 1 min, cut a second time at a speed of 16 rpm for 15 s, allowed to heal for 1 min, and cut a third time at speed 16 rpm for 10 s and allowed to heal for 1 min (Johnston et al., 1998). The moment of initiating gel cutting was taken as the refer- ence time ( t = 0) for all subsequent measurements. Samples of curd/whey mixture ( ∼ 180 mL) were removed from the vat using a ladle at t = 5 min and at 10-min intervals thereafter up to t = 85 min. Curd and whey were immediately separated using a 75- m nu- merical aperture stainless-steel sieve (AGB, Dublin, Ireland), and the 2 phases were weighed without delay using a precision balance for curd and whey yield calcu- lation. The sieve characteristics were selected to ensure that whey fat globules were not retained. Approxi- mately 3 g of curd and 5 g of whey were then accurately weighed into preweighed aluminum dishes for determination of total solids of curd and whey, respectively, by drying in triplicate in a convection oven at 102 ° C for 16 h (Fagan et al., 2007). The yield of whey was ex- pressed as a percentage of the initial weight of milk used in each trial. A computer vision system was coupled to a 10-L cheese vat, as shown in Figure 1, to measure color changes in the curd/whey mixture during syneresis (Figure 2). The computer vision system used in this study con- sisted of a high-quality 3-CCD Sony XC-003P camera (Sony Corporation, Tokyo, Japan) connected to a computer for image analysis with an IC-RGB frame grabber (Imaging Technology, Billerica, MA). Images were captured under 2 fluorescent lamps (Imaging Technology) with plastic light diffusers. The camera captured images ( ∼ 100 mm 2 ) of the surface of the curd/whey mixture during syneresis while the mixture was being stirred. Images were captured at t = 5 or 6 min and at 1-min intervals thereafter up to t = 85 min. Care was taken to capture each image at the same stirrer position. Each image was subdivided into areas of curd or whey, respectively, according to a color threshold. This was achieved by converting each image into a greyscale image, de-noising it using a 2-dimensional adaptive noise- removal filter (Lim, 1990), enhancing the image con- trast-limited adaptive histogram equalization (MathWorks, 1998), and defining a threshold value between curd and whey based on human perception to ensure clear separation of the curd and whey, using Matlab V 6.5.1 (The Mathworks Inc., Natick, MA). The areas of white ( A w ) and yellow ( A y ) in each image were determined mathematically, and their ratio ( a wy = A w / A y ) was calculated and used as a parameter to follow syneresis. Red, green, and blue ( RGB ) values averaged across the images were also recorded using Matlab V 6.5.1 and used to follow syneresis. These RGB values were used to calculate ∆ E RGB using the Euclidean formula Eq. [1], to give a computer vision metric as a function of time with respect to the initial image captured at t = 5 min or 6 ...
Similar publications
Nowadays, wheat has spread all over the world due to its extensive usability. The colour of wheat grits is very important for the milling and baking industry because it determines the colour of the products made from it. The instrumental colour measuring is used, first of all, for durum wheat. We investigated the relationship between colour charact...
The homogeneity of wood color in a batch to be marketed is of fundamental importance, as it will reflect in products quality resulting from its processing. In this context, this study aimed to evaluate, through colorimetric technique, the colorimetric parameters of Eucalyptus spp. wood from 25 clones and classify them into groups, according to colo...
The objective of this study was to develop simple mathematical models for the prediction of the total anthocyanin content of fruits and vegetables, using colorimetry. Phenolic extracts of 13 species of fruits and vegetables were produced using 70% acidified ethanol and 70% ethanol. The quantification of the total anthocyanins of the extracts was pe...
Optical characterization of time sequential stereoscopic 3D display is made investigating its temporal behavior for all grey level transitions. OptiscopeSA, dedicated to luminance and temporal behavior measurements of LCD displays is used. The transmittance and response time of the shutter glasses is measured. The grey to grey level response times...
Cecum impaction has been known as cases of intestinal obstruction in mature cattle. Cecum dilatation, with or without its twisting, occurs separately. The complication may be seen at any age but its most occurrence frequencies are in 4 to 7 years old cows. It seems that cecum dilatation occurs before its twisting. The reason of cecum dilatation is...
Citations
... CV methods necessitate the utilization of cameras and controlled illumination setups to capture images of dairy products. These techniques exhibit versatility, extending beyond the assessment of optimal cutting times [10]. Combining CV methods with artificial intelligence (AI) has found application in various tasks, including the classification of cheese ripeness in entire cheese wheels [11] and the inspection and grading of cheese meltability [12]. ...
The production of cheese, a beloved culinary delight worldwide, faces challenges in maintaining consistent product quality and operational efficiency. One crucial stage in this process is determining the precise cutting time during curd formation, which significantly impacts the quality of the cheese. Misjudging this timing can lead to the production of inferior products, harming a company’s reputation and revenue. Conventional methods often fall short of accurately assessing variations in coagulation conditions due to the inherent potential for human error. To address this issue, we propose an anomaly-detection-based approach. In this approach, we treat the class representing curd formation as the anomaly to be identified. Our proposed solution involves utilizing a one-class, fully convolutional data description network, which we compared against several state-of-the-art methods to detect deviations from the standard coagulation patterns. Encouragingly, our results show F1 scores of up to 0.92, indicating the effectiveness of our approach.
... CV methods necessitate the utilization of cameras and controlled illumination setups to capture images of dairy products. These techniques exhibit versatility, extending beyond the assessment of optimal cutting times [9]. Combining CV methods with artificial intelligence (AI) has found application in various tasks, including the classification of cheese ripeness in entire cheese wheels [10] and the inspection and grading of cheese meltability [11]. ...
The production of cheese, a beloved culinary delight worldwide, faces challenges in maintaining consistent product quality and operational efficiency. One crucial stage in this process is determining the precise cutting time during curd formation, which significantly impacts the quality of the cheese. Misjudging this timing can lead to the production of inferior products, harming a company's reputation and revenue. Conventional methods often fall short of accurately assessing variations in coagulation conditions due to the inherent potential for human error. To address this issue, we propose an anomaly detection-based approach. In this approach, we treat the class representing curd formation as the anomaly to be identified. Our proposed solution involves utilizing a one-class, fully convolutional data description network, which we compared against several state-of-the-art methods to detect deviations from the standard coagulation patterns. Encouragingly, our results show F1 scores of up to 0.92, indicating the effectiveness of our approach.
... Similar pH in Caulerpa extract was also found to be alkaline, as reported [28]. A previous study found that higher pH values can reduce the rate of syneresis in jellies, while lower pH values can cause the molecules to lose bonding, resulting in a weak or runny gel [29]. interaction between the amounts of extract and fructose. ...
... Similar pH in Caulerpa extract was also found to be alkaline, as reported [28]. A previous study found that higher pH values can reduce the rate of syneresis in jellies, while lower pH values can cause the molecules to lose bonding, resulting in a weak or runny gel [29]. ...
This study introduced a D-optimal design mixture to assess the physicochemical properties of a hydrocolloid-based functional food fortified with C. lentillifera. The combination incorporated vital jelly constituents, including extract (10–15%), sweeteners (20–29%), gelling agents (k-carrageenan and locust bean gum (LBG)), and preservatives (0–0.05%). The dependent variables were pH, Total Soluble Solid (TSS) value, and moisture content (MS). By employing the D-optimal design approach, a quadratic polynomial model was developed, demonstrating strong correlations with the experimental data with coefficient determinations (R2) of 0.9941, 0.9907, and 0.9989 for pH, TSS, and MS, respectively. Based on the D-optimal design, the study identified the optimum combination of significant factors with a desirability of 0.917, comprising 14.35% extract, 23.00% sucrose, 21.70% fructose, 26.00% k-carrageenan, 13.00% LBG, 1.95% CaCl2, and 0% methylparaben. The percentage of residual standard error (RSE) was less than 5%, indicating the reliability of the developed model. Furthermore, color analysis revealed significant differences among the jellies (p < 0.05). HPLC analysis demonstrated that the total sugar content in the fortified jellies was 28% lower compared to commercial jelly. Meanwhile, the bitterness level according to e-tongue showed a reduction of up to 90.5% when compared to the extract. These findings provide a valuable benchmark for the development of functional food products, ensuring their quality, safety, and extended shelf-life.
... Ultimately, curd properties and syneresis can determine the most important aspects of cheese making as sensory properties of cheeses and losses during the processing. Therefore, in last decades some empirical or instrumental methods were investigated for monitoring the syneresis during the "in-vat" processes of cheese making [9], [10], [13], [15], [11], [16]. After clotting, the cutting of curd is the first essential treatment can alter the curd loss dramatically. ...
More researches published data about the milk curd properties, evaluated the importance in the cheese making, but an analysis of importance of these properties in practical applications is usually lacking. We investigate the milk curd behaviour using different enzyme preparations at the cutting of curd. We focused on the well measurable properties as clotting time, viscosity of curd, texture properties an whey separation rate of cur at cutting time. Approximately five minutes difference was determined between the clotting times. Investigated the curd properties we found significant differences between the hardness on samples clotted with CHY MAX® M 1000 and NATUREN® Premium 145 enzymes. Other properties did not show significant differences, but in some case differences were remarkable. Discovered differences e.g. approx. 5% whey separation rate difference and the different trends of adhesive force and adhesiveness confirm that such studies should be carried out. Summarized effect of different enzymes can alter the cheese making technology in the practice, significantly. Considering every aspect, in our investigation the CHY MAX® M 1000 enzyme seemed the best.
... The results showed that the linear and interactive effects of spin speed (B) and centrifugation time (C) were significant (P < 0.01) on moisture content of chhana prepared using the fabricated model. Moisture content of cheese curd can be controlled by controlling the extent of syneresis (Everard et al. 2007). Hence, the moisture content and texture of chhana can be optimised by controlling the extent of syneresis. ...
The present study was aimed at applying centrifugation for the rapid removal of whey from chhana and investigating the effect of processing parameters on various attributes of chhana. A prototype model based on centrifugation was developed for rapid whey removal from chhana. The optimised spin speed and centrifugation time for manufacturing chhana using the developed system were 80 rpm and 7 min, respectively. Whey removal at centrifugation speed of 39.09 rpm for 2.57 min resulted in production of soft chhana with minimum hardness value (2.054 N).
... The change in colour of curd during cheese-making has been found to be a good indicator of syneresis. Computer vision measures the red, green and blue colour components of curd and can distinguish between curds and whey and, in conjunction with image processing software, can give a measure of curd particle size and quantity, although it is limited to one dimension (Everard et al., 2007). Computer vision and NIR are thus potential technologies for monitoring syneresis processes (Mateo et al., 2010). ...
Background
The rate or extent of whey expulsion or syneresis from cheese curds during stirring in-vat determines curd moisture levels, which subsequently influences cheese moisture content. The outward migration of whey depends on curd contraction and on the structure of the pores permitting whey movement. Curd syneretic properties are one of the least understood areas of cheese science, particularly when milk of varying composition is used.
Scope and approach
This review provides an insight into the mechanisms of curd formation and curd syneresis, and factors influencing syneretic properties in unconcentrated and concentrated milk and appraises syneresis measurement methods in terms of their relative strengths and weaknesses.
Key findings and conclusions
Direct measurement of moisture content of curds is recommended as a simple and reliable method for measurement of syneresis of industrial relevance and, although inline measurement for curd moisture prediction has been a significant development in the last decade, its application to commercial production is still limited. A review of previous studies found that experimental conditions and methodologies used to measure syneresis vary widely, making it difficult to compare data between studies. Overall, interactions between process variables employed determines whether syneresis is accentuated or inhibited, and this can be exploited by cheese producers to attain target curd moisture contents by varying process parameters, particularly when milk is concentrated prior to cheese-making. Furthermore, further studies should be focused on endogenous syneresis and casein network rearrangement to clearly elucidate this mechanism and its influence on macrosyneresis under dynamic conditions.
... In recent decades, novel rapid and nondestructive methods for evaluating cheese quality attributes are needed and developed (Abbas et al., 2012;Barreto et al., 2018;Downey et al., 2005). Unlike conventional methods, these novel methods acquire data without contact with samples, thus providing nondestructive measurements (Wu & Sun, 2013), and computer vision, near-infrared spectroscopy, Fouriertransformed infrared spectroscopy, Raman spectroscopy, hyperspectral imaging and other techniques have been developed for cheese production process monitoring (Currò et al., 2017;Everard et al., 2007;Ferragina et al., 2013;Loudiyi et al., 2018b;Vásquez et al., 2018), and determination of quality, geographical origin and adulteration of cheese products (Barreto et al., 2018;Cevoli et al., 2013;Subramanian et al., 2009b). ...
... Normally, the protein content of cheese varies inversely with the fat content (Fox et al., 2004). Moisture has the highest content in cheese, hence controlling moisture during cheese processing has technical connotation for final cheese quality (Everard et al., 2007;Fox et al., 2004). ...
... Attributes during syneresis and salting stages are defined as processing parameters in this review (Fig. 1). The curd shrinks because of the realignment of casein micelles, which leads to the exclusion of whey from the curd matrix, therefore, most of the moisture and lactose are removed during this process (Everard et al., 2007). Monitoring moisture change during this stage thus becomes very important. ...
Background: Cheese is produced around the world in a wide range of flavours, varieties, textures, and shapes, which can be used as a final product in human diet, and as an important ingredient in various foods. With consumer's continuing demand for quality cheese as well as increasing challenge from production facing the industry, nondestructive techniques are increasingly used to evaluate cheese quality. Scope and approach: Considering the rapid development of novel nondestructive techniques, relevant literatures in the past 15 years (2004–2018) are reviewed in this paper. The main quality attributes of cheese and the importance of evaluating these attributes are discussed. The principles, developments and applications of computer vision (CV), computed tomography (CT), X-ray system, magnetic resonance imaging (MRI), fluorescence spectroscopy, near-infrared (NIR) spectroscopy, Fourier transform infrared (FTIR) spectroscopy, hyperspectral imaging (HSI), Raman imaging, ultrasonic and acoustic sensing and other nondestructive techniques are discussed in this review. Key findings and conclusions: Among all nondestructive techniques used for cheese quality evaluation, fluorescence spectroscopy is the most used method for classification, NIR spectroscopy is mainly used for predicting chemical components, FTIR spectroscopy shows the greatest scope of applications, while CV, X-ray and MRI are only used for monitoring eye growth. HSI and Raman imaging begins to attract research interest, and synchronous fluorescence spectroscopy gradually replaces front-face fluorescence spectroscopy, whereas CV is no longer applied to cheese evaluation and literatures about NIR spectroscopy also becomes less in recent years. It is hoped that this review should provide information on current research gaps and set some directions for future studies.
... The aim of this paper is to give a comprehensive overview on the principles and applications of computer vision method and image analysis to the assessment of visual parameters in the quality evaluation of cheese, which correlates with quality and safety characteristics. Computer vision method was used routinely in the quality assessment of several dairy products like whey, desiccated milk, yoghurt, and cheese [19][20][21][22][23][24][25][26][27][28][29][30][31]. CVS with image analysis are being developed to assess the appearance criteria of cheese, such as color, shreddability, gas holes and mechanical openings, and oiling-off [26-27, 29-30, 32-34]. ...
... Computer vision techniques distinguished the effects of pH and stirring speeds, and it was shown that, with the inclusion of known factors and calibration to a range of operating conditions, there is the potential for predicting a syneresis endpoint. It was found that the accuracy of a computer-vision system for monitoring syneresis improves with size of field of view [22,103,114,[118][119]. Syneresis was studied using images captured of the surface of the curd/whey mixture, using five image texture analysis techniques by Fagan et al. [120]. ...
This review paper deals with literature analysis of modern computer vision and image analysis methods in cheese-quality evaluation. In this paper several cheese types made from cow’s milk were analyzed: soft, semihard, and hard cheese. All images shown in this paper were scanned with a flatbed scanner, and then processed using ImageJ software. Because with the most part of the external quality attributes evaluation is timeconsuming, due to visual inspection, computer vision provides a means to perform this task automatically. To evaluate various cheese external quality properties (color), and defects (mechanical openings – gas holes; rind defect – formation of calcium lactate crystals and excessive rind halo; amount and distribution of added ingredients; meltability and oiling-off) computer vision system has been successfully applied. Image analysis was used for measurement of the normal amount of gas production, and abnormal shape or distribution of eyes throughout the structure of Emmental and Tilsit cheese. Image analysis was used to determine the presence of rind halo cheese defect and to measure the area occupied by calcium lactate crystals on surfaces of naturally smoked Cheddar cheese samples. To improve empirical methods (Arnott and the Schreiber test) and to offer a new approach for evaluation of meltability and oiling-off of Mozzarella cheese, computer vision and image analysis method was applied. In addition, digital image analysis is used for evaluation of the addition of some ingredients and evaluation of the amount and distribution of added ingredients into the semi-cooked cheese with added paprika and herbs. Computer vision and digital image analysis represents an efficient and non-invasive technique able to investigate the cheese optical properties and give information concerning their composition and structure.
... Application of theory-based models for determining moisture levels in cheese adds complexity (Jimenez-Marquez et al. 2005). Thus, recent studies have explored the use of inline sensors to monitor syneresis during cheesemaking (Everard et al. 2007;Mateo et al. 2009b;Costa et al. 2012;Arango et al. 2015), which offers the possibility to determine curd moisture content in real time (Mateo et al. 2009c). In this context, the prediction of curd moisture using empirical model 8 or 10 may provide valuable information for modelling of curd moisture and drainage times during cheesemaking using initial milk moisture. ...
This study compared the in-vat moisture loss kinetics under fixed cheesemaking conditions during 75 min of stirring of curds prepared from protein-standardised milks produced from indoor cows fed total mixed ration (TMR), or outdoor cows fed grass only (GRA) or grass mixed with clover (CLO). Relative curd moisture as a function of time was fitted to different empirical equations, of which a logarithmic function gave the best fit to the experimental data. The moisture loss rate constant (k/min) was found to be similar for curds from protein-standardised TMR, CLO and GRA milks, showing minimal feed-induced variations in syneresis.
... Cutting the gel disrupts the gel structure creating cracks in the gel, which initiate syneresis by creating new interactions between para-casein molecules ( Dejmek and Walstra, 2004). The extent of cutting of rennet-induced milk gels determines the size of curd particles, which is related inversely to the velocity of whey exudation ( Everard et al., 2007) (14.2), and directly related to moisture content of the final curd ( Whitehead and Harkness, 1954;Czulak et al., 1969). Additionally, smaller curd particles provide more surface area for syneresis, which together with the increased velocity of whey release, increases the rate of syneresis. ...
Cheese manufacture involves the controlled destabilization of the casein micelle in milk by enzymatic hydrolysis of the surface ê-casein layer, acidifi cation to the isoelectric pH of the casein, or a combination of pH reduction to ~5.6 and high temperature (~90 °C) in rennet-curd, acid-curd and acid heat-curd cheeses, respectively. Under suitable conditions, the destabilized micelles undergo limited aggregation to form a gel, which is dehydrated to a curd with the desired moisture content by a series of unit operations including cutting the gel into pieces (curd particles), in situ acidifi cation, heating and stirring the curd particle/whey mixture, removal of the expressed whey, pressing and/or salting of the curd. Microstructurally, rennet-curd cheese is a matrix comprised of a hydrated calcium phosphate para -casein network that occludes the fat phase which occurs as discrete and coalesced globules or pools. The microstructure is infl uenced by the concentration of para -casein and the degree to which the component para - casein micelles are aggregated and fused, as affected by manufacturing operations. Macrostructurally, rennet-curd cheese is an assembly of curd particles or pieces (e.g., chips) that fuse to varying degrees according to their microstructure, which affects their potential to deform, and curd handling treatments (e.g., pressing) which effect the level of stress applied to the amalgam of curd particles/pieces. The matrix of acid- or acid heat-curd cheese is similar to that of rennet-curd cheese, but the network is formed from casein (with little, or no, bound calcium) or casein complexed with whey protein, denatured by high heat treatment of the milk prior to acidifi cation and gelation. Most acid-curd and acid heat-curd cheeses have a very uniform texture and lack a macrostructure as the curd particles, low in calcium and high in moisture, coalesce easily to form a structuralcontinuum. Heating of rennet-curd cheese to 90-100 °C in culinary applications leads to contraction and shrinkage of the para -casein network and liquefaction and coalescence of fat. These microstructural changes are the basis of the melt properties, including softening, fl ow and stretchability. Owing to their low pH, acid-curd cheeses generally tend to be unstable during heating, as refl ected by protein precipitation and the release of excess free moisture. The micro- and macro-structure of cheese has a major infl uence on various aspects of quality including composition, rheology, texture, cooking properties, opacity/translucence, and behaviour during curd processing operations such as portioning, shredding, slicing, and processed cheese manufacture
