Prediction of output moisture content of dill from hot-air conveyor belt dryer using machine vision

Document Type : Research Paper


1 Department of Biosystems Engineering, Faculty of Agriculture, University of Kurdistan, Sanandaj, Iran

2 Department of Biosystems Engineering, Faculty of Agriculture, University of Kurdistan, Sanandaj, Iran.


Predicting the output moisture content of product from the conveyor belt hot air dryer for controlling the drying process is one of important parameters. Therefore, in this research, a conveyor belt dryer with a hot air flow equipped with a machine vision system was developed. Dryer also consists of air temperature and conveyor belt speed controlling section, lighting and imaging system. The control sections for air temperature and conveyor belt speed include SSR relays and a programmed algorithm in MATLAB software environment. The machine vision section comprises three cameras placed at the beginning, middle, and end of the conveyor belt. In this study, experiments were conducted at two temperature levels of 50 and 60 °C and three levels of conveyor belt speed for each treatment. Then, using the developed image processing algorithm in MATLAB, the changes in shrinkage were extracted and analyzed. Finally, the out moisture content of the product from dryer was modeled using the ANN. The results of this study indicated that the out moisture content and shrinkage of the dried product are dependent on temperature of dryer and speed of the conveyor belt. Specifically, with an increase in temperature and a decrease in conveyor belt speed, the degree of shrinkage increases Finally, results revealed that the ANN with 4-12-1 structure had best prediction performance with 1.06e-6, 1.24e-6, 9.46e-7 of RMSE and 0.9999, 0.9999, 0.9999 of R, respectively for training, validation and testing data.


Main Subjects

Prediction of output moisture content of dill from hot-air conveyor belt dryer using machine vision

Extended Abstract


Due to the fact that high moisture content of agricultural products such as dill promotes the growth and activity of microorganisms. Therefore, they are typically dried before being introduced to the market to prevent biochemical reactions. Due to the disadvantages of traditional methods of the drying agricultural products, Hot-air conveyor belt dryers as industrial dryers are commonly used to dry of the agricultural products due to their simplicity of operation, easy access and cost-effective. But the systems or sensors that are used to correctly determine or measure the final moisture level from the output of this dryer have low accuracy or are not common due to their other disadvantages (Mizukami et al., 2006; Rywotycki, 2003). Today, machine vision and artificial neural network demonstrated their ability for online monitoring of drying processes and process modeling respectively. The application of these technologies to control the drying process are being widely developed (Li & Chen, 2020; Rezaei et al., 2019; Su et al., 2015). Suprapto & Riyanto (2020) studied the process of drying grapes in a conveyor belt dryer equipped with a machine vision system. Machine vision system was used to image the grapes during drying and neural network was used for modeling. Our research aimed to investigate the feasibility and application of machine vision in conveyor belt dryers for measuring moisture content and controlling the drying process. We found that there was a lack of studies focusing on this specific area.

Materials and Methods

Dill used in the experiments. The initial and final moisture content of products exit from the dryer was determined by AOAC (1980) method. In this study, a conveyor belt hot air dryer equipped with a machine vision system was developed (Fig. 1). This dryer consists of machine vision, conveyer belt, heater, SSR rely, temperature and belts speed control program. The machine vision system including three webcams (Logitech C920, FULL HD-1920*1080 pixels-30fps-Switzerland) were installed in the entrance, exit and middle part of the dryer (with equal distances from each other). The images taken by these webcams were transferred to the computer through a USB cable and received with the help of MATLAB 2018b software. Two LED tube lamps (230 v, power 18W, G13 base, length 1.20 m, manufactured by Pars Shahab Company, Iran) were used for lighting. The experiments was done with two levels of air temperature (50 and 60 C) and three levels of belt speed for each air temperature (Table 1).

An image processing algorithm was developed to extract features from the image. The first step to develop the desired algorithm is image segmentation to remove the background from the images (Fig. 2). After segmenting the images, shrinkage as a feature was extract following equation:


Where  the number of pixel of object with camera in the middle and exit of dryer and   is the number of pixel with camera in the entrance of the dryer. Also the shrinkage difference between cameras extracted with flowing equations:




For modeling using the neural network in this study, ∆A12, ∆A23, ∆A13, and the initial moisture content (MC0) were considered as inputs, while the moisture content output from the dryer (MCf) was considered as the model's output.

Results and Discussions

The Fig. (9-a), (9-b), and (9-c) show images captured by the first, second, and third cameras, respectively, for under-drying conditions (conveyor speed of 1.7 cm/min), desired drying conditions (conveyor speed of 0.6 cm/min), and over-drying conditions (conveyor speed of 0.35 cm/min) at a temperature of 50 °C. The surface shrinkage of the samples is clearly visible from the images. The images captured by the first camera have similar conditions in almost all experimental treatments because the initial samples entering the dryer were identical. However, variations in the appearance of the samples are observed in the images captured by the second and third cameras. These variations are due to the loss of moisture, which is manifested in the form of shrinkage of the samples.

Table 3 presents the results of training the model for predicting moisture content. By examining the results obtained from this modeling, the network with a structure of 4-12-1 was found to be the best model with RMSE values of 0.0657, 0.2494, and 0.4657, and R values of 0.9999, 0.9999, and 0.9998 for training, evaluation, and testing, respectively.

Adak, N., Heybeli, N., & Ertekin, C. (2017). Infrared drying of strawberry. Food Chemistry, 219, 109-116.
Callan, N. W., Johnson, D. L., Westcott, M. P., & Welty, L. E. (2007). Herb and oil composition of dill (Anethum graveolens L.): Effects of crop maturity and plant density. Industrial Crops Products, 25(3), 282–287.
Chen, J., Zhang, M., Xu, B., Sun, J., & Mujumdar, A. S. (2020). Artificial intelligence assisted technologies for controlling the drying of fruits and vegetables using physical fields: A review. Trends in Food Science & Technology, 105, 251–260. Doi:10.1016/j.tifs.2020.08.015
Canter, P. H., Thomas, H., & Ernst, E. (2005). Bringing medicinal plants into cultivation:opportunities and challenges for biotechnology. Trends in Biotechnology, 23(4), 180-185.
Chasiotis, V., Tzempelikos, D., Mitrakos, D., & Filios, A. (2021). Numerical and experimental analysis of heat and moisture transfer for Lavandula x allardii leaves during non-isothermal convective drying. Food Engineering, 311, 110708.
Chakravartula, S.S., Bandiera, A., Nardella, M., Bedini, G., Ibba, P., Massantini, R., & Moscetti, R. (2023). Computer vision-based smart monitoring and control system for food drying: A study on carrot slices. Computers and Electronics in Agriculture, 206, 107654.
Doymaz, I., Tugrul, N., & Pala, M. (2006). Drying characteristics of dill and parsley leaves. Food Engineering, 77(3), 559-565.
Erbay, Z., & Icier, F. (2010). A review of thin layer drying of foods: theory، modeling، and experimental results. Critical Reviews in Food Science and Nutrition, 50(5), 441–464.
Esturk, O., & Soysal, Y. (2010). Drying properties and quality parameters of dill dried with intermittent and continuouse microwawe-convection air treatments. Journal of Agricultural Sciences, 16, 26-36.
Hedayat, M., Mortezapour, H., Maghsoudi, H., Shamsi, M. (2016). Performance investigation of a heat recovery assisted solar dryer for mint drying. Iranian Journal of Biosystem Engineering, 46(4), 379-388, (In Persian).
Kaveh, M., Amiri Chayjan, R., & Khezri, B. (2018). Modeling drying properties of pistachio nuts, squash and cantaloupe seeds under fixed and fluidized bed using data-driven models and artificial neural networks. Journal of Food Engineering, doi: 10.1515/ijfe-2017-0248.
Kasali, S., Minaei, S., & ayyari, M. (2019). Effect of the drying process on saffron petals color features using machine vision. Saffron Agronomy & Technolog, 7(1), 81-91, (In Persian).
Li, H. & Chen, S. (2020). A neural network based model predictive control scheme for grain dryers. Drying technology, 38(8), 1079-1091.
Li, X., Liu,Y., Gao, Z., Xie, Y., & Wang, H. (2021). Computer vision online measurement of shiitake mushroom (Lentinus edodes) surface wrinkling and shrinkage during hot air drying with humidity control. Journal of Food Engi-neering, 292, 110253. doi:10.1016/j.jfoodeng.2020.110253
Midilli, A., Kucuk, H., & Yapar, Z.A. (2002). New model for single-layer drying. Drying Technology, 20(7), 1503.
Mizukami, Y., Sawai, Y., & Yamaguchi, Y. (2006). Moisture content measurement of tea leaves by electrical impedance and capacitance. Biosystems Engineering, 93(3), 293-299.
Motevali, A., Younji, S., Amiri Chayjan, R., Aghilinategh, N., & Banakar, A. (2013). Drying kinetics of dill leaves in a convective dryer. International Agrophysics. 27, 39-47.
Martynenko, A. (2016). Improvement of kiwifruit drying using computer vision system (CVS) and ALM clustering method. Drying Technology, 35, 709–723. doi:10.1080/07373937.2016.1208665.
Omari, A., Behroozi, N., & Faroogh, S. (2018). Drying kinetic and artificial neural network modeling of mushroom drying process in microwave-hot air dryer. Food Process Engineering, 41(7), e12849. doi: 10.1111/jfpe.12849.
Rywotycki, R. (2003). Electric sensor for prompt measurement of moisture content in solid food products. Food Process Engineering, 25(6): 473-483.
Rezaei, S., Behroozi-Khazaei, N., & Darvishi, H. (2019). Microwave power adjusting during potato slice drying process using machine vision. Computers and Electronics in Agriculture, 160, 40–50. doi:10.1016/J.COMPAG.2019.03.013
Seyedabadi, E., Khojastehpour, M., & Abbaspour-fard, M, H. (2019). Online measuring of quality changes of banana slabs during convective drying. Engineering in Agriculture, Environment and food, 12, 111-117.
Su, Y., Zhang, M., & Mujumdar, A. S. (2015). Recent development of smart drying technology. Journal of Drying Technology, 33(3), 260-276.
Suprapto, S., & Riyanto, E. (2020). Grape drying process using machine vision based on multilayer perceptron networks. Indonesian Journal of Science & Technology, 5(3), 382-394.
Sabzevari, M., Behroozi-Khazaei, N., & Darvshi, H. (2021). Developing the Microwave- Hot Air Dryer with Power Density Control System Using Kinetic Modeling of Banana Slice. Iranian Journal of Biosystem Engineering, 52(4), 567-584, (In Persian).
Wannapakhe, S., Chaiwong, T., Dandee, M., & Prompakdee, S. (2012). Hot air dryer with closed-loop oscillating heat pipe with check valves for reducing energy in drying process. Procedia Engineering, 32: 77-82.
Wankhade, P. K., Sapkal, R. S., & Sapkal, V. S. (2013). Drying characteristics of okra slices on drying in hot air dryer. Procedia Engineering, 51, 371-374.
Yadollahinia, A., Latifi, A., & Mahdavi, R. (2009). New methods for determination of potato slice shrinkage during drying. Computers and Electronics in Agriculture, 65 (2), 268–274.
Zhu, G., Raghavan, G.S.V., Xu, W., Pei, Y., & Li, Z. (2023). Online Machine Vision-Based Modeling during Cantaloupe Microwave Drying Utilizing Extreme Learning Machine and Artificial Neural Network. Foods, 12, 1372. doi:10.3390/foods12071372
Zanoelo, E.F., Abitante, A., & Meleiro, L.A.C. (2008). Dynamic modeling and feedback control for conveyors-belt dryers of mate leaves. Journal of Food Engineering, 84, 458–468.