Abstract—The objective of this study was to investigate the method for pig weight estimation by using image processing and artificial neural networks. Eighty-eight crossbred pigs (Large White  Landrace  Duroc Jersey) were used. Pigs were individually weighted, measured heart girth and body length. Thereafter, the top-view images of pigs were captured, and the ratio of pig pixels to total area (image) was analyzed by using Python programming. The data was divided into two groups as training set (n=62) and testing set (n=26). The correlation of body weight and heart girth as well as body length and image was determined by Pearson correlation. The training set was used to develop equations of pig weight by regressing analysis and Artificial Neural Networks (ANN). The Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE) were used to measure an error of estimation. The results showed that the high positive correlation with body weight was observed in image, heart girth, and body length (0.930, 0.872 and 0.849, respectively). With regard to regression analysis, the equation including image showed a higher accuracy (R² = 0.866) when compared to the equations including heart girth (R² = 0.760) or body length (R² = 0.721) as well as the equation including both heart girth and body length (R² = 0.835). For ANN analysis, the model including image expressed a better fit (R² = 0.892) when compared to the equation obtained from regression analysis. Furthermore, ANN analysis showed lower MAD (0.618) and MAPE (6.243) when compared to regression analysis (MAD=0.630 and MAPE=6.410). In conclusion, image processing is a quick method to estimate body weight without casing stress to the pigs. The use of ANN is an alternative method to increase the accuracy of the model for pig weight estimation.
 

Index Terms—artificial neural networks, body weight, estimation, image processing, pig

Cite: Chanwit Kaewtapee, Choawit Rakangtong, and Chaiyapoom Bunchasak, "Pig Weight Estimation Using Image Processing and Artificial Neural Networks," Journal of Advanced Agricultural Technologies, Vol. 6, No. 4, pp. 253-256, September 2019. Doi: 10.18178/joaat.6.4.253-256