Computers and Electronics in Agriculture 76 (2011) 189–197 Contents lists available at ScienceDirect Computers and Electronics in Agriculture journal homepage: www.elsevier.com/locate/compag Original papers Determination of body measurements on the Holstein cows using digital image analysis and estimation of live weight with regression analysis Sakir Tasdemir a,∗ , Abdullah Urkmez b , Seref Inal c a Department of Computer Technology and Programming, Technical Science College, Selcuk University, Konya, Turkey b Department of Electrical Electronics Engineering, Faculty of Engineering and Architecture, Selcuk University, Konya, Turkey c Department of Zootechnics, Faculty of Veterinary Medicine, Selcuk University, Konya, Turkey article info Article history: Received 6 June 2010 Received in revised form 25 January 2011 Accepted 2 February 2011 Keywords: Digital image analysis Regression Body measurements Live weight abstract In this study, the body measurements (BMs) of Holstein cows were determined using digital image analysis (IA) and these were used to estimate the live weight (LW) of each cow. For this purpose, an image capture arrangement was established in a dairy cattle farm. BMs including wither height (WH), hip height (HH), body length (BL), hip width (HW), plus the LWs of cows were first determined manually, by direct measurement. Then the digital photos of cows were taken from different directions synchronously and analyzed by IA software to calculate WH, HH, BL and HW of each cow. After comparing the BMs obtained by IA with the manual measurements, the accuracy was determined as 97.72% for WH, 98.00% for HH, 97.89% for BL and 95.25% for HW. The LW estimation using BMs was then performed by the aid of the regression equations, and the correlation coefficient between the estimated and real (manual) LW values obtained by weighing was calculated as 0.9787, which indicates the IA method is appropriate for LW estimation of Holstein cows. © 2011 Elsevier B.V. All rights reserved. 1. Introduction Since the numbers and capacities of dairy cattle farms are increasing with every passing day, the computer-aided studies for the management of these farms become more important and are widely used in daily life. The management decisions based on live weight (LW), milk production and feed consumption in dairy cattle breeding are significant in terms of reflecting the efficiency of the farm, the care applied in the farm, the feeding level and the present condition of the cattle. The variations in milk yield, feed consump- tion and LW between two calving of a cow can be observed in Fig. 1. The out-of-range properties negatively and significantly affect the economical efficiency and the resistance of cows to diseases. For instance, the negative variations especially in LWs can indicate health problems, inappropriate environmental conditions or feed- ing faults; therefore, LW monitoring in dairy cows becomes very important (National Research Council of the National Academies, 2001; Ensminger et al., 1990; Wilson et al., 1997; Tasdemir et al., 2008). LW is determined by the weighing process performed in cat- tle farms, especially by constructing a weighing place that will weigh the cows while they are passing or standing still on it. Some problems can be faced with the weighing device in terms of the ∗ Corresponding author. Tel.: +90 332 2232380; fax: +90 332 2410185. E-mail address: stasdemir@selcuk.edu.tr (S. Tasdemir). accuracy of the calibration or proper working due to environmen- tal conditions. A staff should be provided to organize and control the weighing process. Although it is aimed to measure the weight of the animals with minimum stress, minor injuries of cattle can be sometimes encountered during the weighing process. Therefore, the farmers prefer not to allocate place for weighing tools, staff and finance. The estimation of LW by using BMs has been made for a long time. However, the BMs made on cows may result in dangerous events due to the animals being under stress during the process of forcing the animals to position them for an accurate BM. Addi- tionally; the possibility of having wrong measurements is also very high. Therefore, due to such unfavorable reasons, the farmers accept not keeping abreast of having LW information or perform the weighing process rarely (Wilson et al., 1997; Tasdemir et al., 2008; Enevoldsen and Kristensen, 1997; Heinrichs et al., 1992). In recent years, computer aided image acquisition and process- ing techniques are in widespread use in various stock management activities such as digital IA in animal breeding, husbandry, etc. And the image analysis technique has been successfully used to esti- mate animal body weight indirectly from its dimensions that some of these studies are given in the following. Visual image analysis and digital image analysis have been applied to determine and follow the body measurements, live weights and growths of pigs, rabbits, chickens and cattle (Negretti et al., 2007; Wet et al., 2003; Mollah et al., 2010; Ozkaya and Yalcin, 2008; Wang et al., 2008; Pastorelli et al., 2006). 0168-1699/$ – see front matter © 2011 Elsevier B.V. All rights reserved. doi:10.1016/j.compag.2011.02.001