Mass modeling of Bam orange with ANFIS and SPSS methods for using in machine vision

•Mass modeling of Bam orange with ANFIS and SPSS methods for using in machine vision was conducted.•ANFIS and SPSS models were employed to predict the mass of orange based on perimeter and (width/length) inputs.•The coefficient of determination (R2) of best model for ANFIS and SPSS were 0.936999 and 0.919 respectively.•The results showed that ANFIS can be properly used for mass prediction. Orange is a citrus fruit which is rich in vitamins and minerals and other nutrients. Getting the relationship between physical properties of orange and its mass can create tremendous change in the packaging industry. The Iranian orange fruits used in this study consisted of Bam cultivars that they got from Kermanshah–Iran (longitude: 7.03°E; latitude: 4.22°N). One hundred samples were randomly selected. All the measurements were carried out at the laboratory with temperature of 24°C during 2days. Fourteen parameters were got by image processing for each orange. ANFIS and SPSS models were employed to predict the mass based on perimeter and (width/length) value as inputs. The coefficient of determination (R2) for ANFIS and SPSS were 0.936999 and 0.919 respectively. To evaluate the ANFIS model, samples were divided into two sets, 70% of data was used for training the model and 30% of data was used to test the model. So, The ANFIS model with less error percentage can be used to design and develop sizing systems.