In this research some water quality parameters in fish pond includes pH, Electrical Conductivity (EC), Total Dissolved Solids (TDS) and Turbidity (Turb) were determined by standard methods and predicted by image processing using smart phone and artificial neural network. All experiments carried out in Kappur ponds in Sonqor city, Kermanshah province. Samples collected from three different depths. The 12 parameters consisted of 6 color features (red, green, blue, black, gray and white), and 6 tissue features (mean, standard deviation, softness, third torque, uniformity and entropy) were extracted from image samples and were selected as inputs to the neural network model. Based on the results, network with structure of 12-15-4 (12 neurons in the input layer, 15 neurons in the hidden layer and 4 neurons in the output layer) was the best model for predicting the parameters with R2 of 0. 913, 0. 993, 0. 994 and 0. 958 for pH, TDS, EC and Turb, respectively. These values for RMSE were 0. 054, 1. 835, 3. 766 and 0. 262, respectively.