ORIGINAL ARTICLE Estimating Oil and Protein Content of Sesame Seeds Using Image Processing and Artiﬁcial Neural Network Mahdieh Parsaeian 1 · Mojtaba Shahabi 2 · Hamid Hassanpour 2 Received: 15 September 2019 / Accepted: 19 March 2020 © 2020 AOCS Abstract Image processing has many applications in different ﬁelds of agriculture. The present study aimed to use image processing techniques and artiﬁcial neural net- works (ANN) to estimate oil and protein contents of ses- ame genotypes without the use of time-consuming and costly laboratory methods. The proposed method accurately estimates the parameters in sesame seeds without des- tructing the genetically valuable material. In this study, a set of 138 morphological features were extracted from the digital image of 125 sesame seed genotypes. A multilayer perceptron (MLP) ANN was then employed to estimate oil and protein contents and determine the relationship between estimated values and laboratory-measured values. The efﬁciency of this model was compared to radial bases function (RBF), extended RBF (ERBF), GRNN, M5-Rule, M5-Tree, support vector machine regression, and linear regression models. Results showed that MLP performed better in estimating qualitative parameters of seeds in the sesame germplasm. The model estimated oil content with an root mean square error (RMSE) of 2.13% (the accuracy of 97.87%) and an R 2 of 0.93. Protein content was estimated by an RMSE of 0.378% (the accuracy of 99.62%) and an R 2 of 0.96. Keywords Artiﬁcial intelligence models  Image processing  Qualitative traits  Sesame J Am Oil Chem Soc (2020). Introduction Sesame is one of the most ancient oilseeds in the world, whose highly nutritious seeds contain high levels of oil (34.4–63.2%), protein (17–32%), minerals, and fat-soluble vitamins (Hiremath et al., 2007; Uzun et al., 2008). Presently, different germplasms of sesame are grown throughout the world. These germplasms display a high diversity in nutri- tional indices and in morphology. Agriculture researchers have always been trying to estimate these nutritional parame- ters and apply this diversity in breeding programs in order to produce high-quality sesame seeds (Bedigian, 2010). Oil and protein are two primary qualitative traits of sesame seeds whose laboratory measurements are time-consuming and require expensive devices that are not available to all researchers. In addition, these measurements are often per- formed on powdered seed samples, so they may destroy genetically valuable seeds. This paper presents a software- based method to estimate oil and protein contents of sesame seeds by using digital image of sesame seeds. The images taken from a given object (e.g., sesame seeds) reﬂect its physi- cal features and can be used for various purposes. According to Araujo et al. (2018), physical features such as length, width, and hardness of sesame seeds affect their quality. In addition to the use of the image processing technique to identify Supporting information Additional supporting information may be found online in the Supporting Information section at the end of the article. * Mahdieh Parsaeian mahparsa_cb@yahoo.com 1 Department of Agronomy and Plant Breeding Sciences, Shahrood University of Technology, C.P. 3619995161. University Blvd., Shahrood, Iran 2 Department of Computer Engineering, Shahrood University of Technology, C.P. 3619995161. University Blvd., Shahrood, Iran J Am Oil Chem Soc (2020) DOI 10.1002/aocs.12356 J Am Oil Chem Soc (2020)