Individual recognition refers to a subset of recognition that occurs when one organism identifies another one according to its unique distinctive characteristics [1]. Individual recognition might be achieved through several sensory modalities. It is assumed that animals form mental representations of several common features of conspecifics as well as of unique individual sets of features of particular conspecifics [2]. For example in hamsters, Mesocricetus auratus, various odours correspond to various parts of body. A hamster which has previously interacted with another individual will treat all the odours from various parts of the body as belonging to that individual. However, a naïve hamster will associate each odour with a different individual [3]. Individual recognition is equivalent to a particular form of categorization phenomenon [4]. One individual constitutes a category in itself that includes all the different features of this distinct individual. Individual recognition might play an important role in social life, as animals which recognize the identity of a group member also recognize its species, its gender, its kinship, and its social status. Individual recognition has been demonstrated in invertebrates, in reptiles, in birds, in fishes, and in mammals (e.g. [5]–[9] respectively). Although individual recognition might be based on several sensory modalities in several species, animals might be able to recognize a congener using only one sensory modality. For example, emperor penguins, Aptenodytes forsteri, are similar morphologically but have a vocal signature that allows individual recognition [10].

The capacity of visual individual recognition has been studied in many invertebrate as well as vertebrate species (for reviews: [1], [11]). Among invertebrates, Tibbetts [12] demonstrated that wasps visually recognized an individual using head patterns. More recently, Van der Velden et al. [13] showed that crayfish can recognize an individual previously met during a fight and that this recognition was based on facial width or other facial features. In various vertebrate species, face recognition is the process the most commonly used to achieve visual individual recognition. Experimental studies in birds, sheep or primates (for review: [11]) used 2-D photographs of faces as stimuli. Visual individual recognition was demonstrated through two-step experiments in which animals were trained to discriminate slides of conspecifics and were then presented with novel slides of the same conspecifics in transfer tests. For example, Parr et al. [14] showed that rhesus monkeys and chimpanzees recognize unfamiliar individuals using facial cues from digitized static images.

Electrophysiological studies provided additional indirect evidence of individual recognition. Thus in macaques and sheep, neuronal circuits in the temporal cortex responded preferentially to faces in contrast to other visual stimuli (e.g. [15], [16] respectively). In the brain of sheep, separate face sensitive populations of cells are either view-dependant or view-independent [17]. View-dependent cells are used primarily in accurate and rapid identification of faces. View-independent cells are implied in recognition processes. In sheep, Peirce et al. found a right brain hemisphere advantage in the recognition of familiar faces of conspecifics [18] but not in the recognition of human faces [19].

When using 2D-images, to assert a genuine capacity for individual visual recognition rather than pattern recognition, the stimuli should include both representations of unfamiliar individuals and those of familiar conspecifics living in the group of the subjects [4]. Stable relationships between social group members have likely facilitated individual visual recognition. If this facilitation exists we can assume that subjects treat the slides as representations of real animals [4]. Dasser [20] recorded the responses of two female long-tailed macaques and showed that these females recognized novel pictures (in transfer test) only if the pictures represented familiar group members. In sheep, Kendrick [21] showed that social familiarity improved the animals' ability to discriminate between the faces (frontal and profile views) of individuals from a familiar breed. Moreover Ryan and Lea [22] showed that hens, in a transfer test, performed better when they were presented with novel slides of familiar rather than unfamiliar hens.

So it seems that for social species it is easier to recognize familiar rather than unfamiliar faces. However, there are few studies evaluating the capacity of categorization of various representations of an individual within the context of visual individual recognition [4] which would require discrimination of individuals within the set of familiar individuals.

Cattle (Bos taurus) is a good candidate species for addressing these questions.

Bos taurus is as a domestic species which allows the testing of several subjects (with Prim'Holstein, the dairy breed the most represented). In addition, cattle provide a great intra and inter-breed variety of coat characteristics (colour and patterns) and morphological diversity. Hence cattle are a good model for studying individual visual recognition. In addition cattle have good capacities of visual discrimination and they are able to discriminate between live familiar conspecifics [23]. Also we previously showed that cattle can visually discriminate 2D-images of their own species from other domestic species [24]. There is clear evidence that cattle can use vision to recognize other cattle [25]–[28] but direct behavioural evidence that cattle can visually recognize other cattle is still lacking. The aim of this study was to evaluate visual individual recognition capacities in cattle. Responses were obtained through an instrumental conditioning using images of faces of individuals as discriminative stimuli with food as positive reward. Individual recognition would be assumed by asking: do subjects treat different face views of the same stimulus animal as equivalent and is there a difference of performance depending on the various orientations of the face? In Experiment 1, all images represented familiar cows (belonging to the same social group) from Prim'Holstein breed (PH). In Experiments 2, 3 and 4, images were from unfamiliar (unknown) individuals either from the same breed or other breeds (Normande N and Charolaise CH breeds). These breeds are respectively characterized by similar coat patterns as PH subjects but with a different colour (brown N instead of black PH) or a uniform white coat colour without any spotted pattern (CH). In the present study all heifers recognized familiar and unfamiliar individuals from their own breed. In addition almost all subjects recognized unknown individuals from different breeds, however with greater difficulty.

Eight PH heifers were tested with an instrumental conditioning with food reward. They were individually introduced into a test pen which included a central lane made of rows of straw bundle. A guillotine gate ended the central lane from which position heifers could see a pair of stimuli. When the subject had observed both stimuli, the experimenter lifted the gate. Then the heifer walked to the chosen image and accessed a reward placed behind an opaque panel (the test pen and procedures were described in more details in [24]). A test session included ten consecutive trials. Stimuli were photographs of head of heifers under various angles (frontal, profile, ¾ front views, ¾ back views and mirror views, Figure 1) on the same yellowish background. In the training phase, the same pair of stimuli was used in each trial. This pair was composed of a front view of the heifer to identify ( = sample individual) with a front view of another heifer (Figure 1). The subject had to choose the image of the other heifer to access to the reward. In generalization test, we used new photographs of the sample heifers and of other heifers, and the pair of stimuli was changed on each trial (Figure 2). The subject always had to choose the image of the other heifer to be rewarded. The criterion of success was for the heifer to make at least 8 correct choices per session in two consecutive sessions of 10 trials. The eight heifers were tested in four different experiments each of which made of a training phase and a generalization test. In the first experiment, we used images of familiar Prim'Holstein (FPH) heifers, in the second experiment images of unfamiliar Prim'Holstein (UPH) heifers, in the third experiment images of unfamiliar Normande (N) heifers and in the fourth experiment images of unfamiliar Charolaise (CH) heifers. Experiments 1 (FPH) and 2 (UPH), on the one hand, and experiments 3 (N) and 4 (CH), on the other hand, were paired. In each pair of experiments, half of the subjects were assigned to one experiment to start with (1 or 2 and 3 or 4). This procedure was intended to avoid a “carry-over” effect.

These results demonstrated efficient visual individual recognition in cattle achieved using 2D-images. Heifers treated equivalently all views of the head of one individual whether or not they had previously interacted with it. However social familiarity improved their performance. This confirms that cattle treated the 2D images as genuine representations of conspecifics and not as an arbitrary visual object. The more different the coat pattern was, compared to that of the subject, the more difficult was the recognition.

Subjects, trained to discriminate frontal views of two individuals, can recognize new views of the individual to be recognized compared to other individuals. This capacity was also demonstrated with unknown individuals and with individuals with a different coat colour or pattern, without prior interaction with the individuals to be recognized. Our results extend the cognitive capacities in cattle that we previously demonstrated for visual discrimination of species [24]. The cognitive capacities of visual individual recognition in cattle match those shown in other species like birds [22], [29], sheep [21], macaques [20], rhesus monkeys and chimpanzees [14]. Contrary to studies in other species, we used five different view angles (frontal view, profile views, ¾ front views, ¾ back views, mirror views) of the individual to be recognized combined with both right and left orientations, so a total of ten different orientations. In spotted breeds like Prim'Holstein or Normande cows, the right side is different from the left side. In sheep, Kendrick [30] showed that facial discrimination occurred with two face orientations (frontal and profile views). Ferreira et al. [31] showed, in the same species, that the learned discrimination of the profile views of a pair of unfamiliar adult faces did not improve subsequent discrimination of frontal views of the same pair. In our study heifers grouped all the different views of the same individual into a similar category. According to Zayan and Vauclair [4], these results may indicate that the polymorphous set of each known individual's features becomes mentally represented as a single natural category, comprising the morphological properties unique to each animal. However our results could also be interpreted as referring to a process of mental rotation of images. Based on this hypothesis, we may expect that the performance recorded in the generalization test (exp. 1 and 2) would be similar in the recognition of familiar and unfamiliar individuals. This prediction was not verified, indicating that a true social recognition occurs rather than a simple mental rotation process. The capacity of individual recognition extends to unknown individuals. This suggests that the subject formed an integrated representation of each conspecific built up from the set of specific features of an individual. Consequently cows might very rapidly be able to recognize new social partners.

The recognition process of a familiar individual was rather straightforward. This suggests that whatever a partner's physical orientation, a cow is able to maintain its partner's identification process. This is in line with the stability of herds of cattle [27]. The heifers recognized more easily a familiar individual than an unfamiliar one. Individual recognition was very likely facilitated by information acquired through recurrent social interactions within the group. In sheep, Kendrick et al. [21] showed that faces of socially familiar animals enhanced significantly the speed of learning the recognition task and in macaques, Dasser [20] demonstrated that the animals correctly matched facial views with novel slides of other body parts of the same animal only if that animal was a familiar group member. Kendrick et al. [32] showed also that there was a progressive increase in the number of cells in the brain which selectively encoded faces of members becoming familiar. Domestic cocks [33] and hens [22] recognized a familiar individual as easily as an unfamiliar one. These animals can discriminate the individuals as distinct categories but not necessarily as individual conspecifics. The fact that heifers had more difficulty to recognize unfamiliar individuals than familiar ones suggests that they likely consider 2D-images of conspecifics as genuine representations of live animals as Zayan and Vauclair asserted [4]. This assumption is supported by emotional responses observed during trials. Our subjects held their ears backward ten times more when processing images of unfamiliar individuals than when processing stimuli from familiar individuals. Ear postures were shown to be emotional cues in several mammalian species (horse [34], sheep (Désiré, 2006, unpublished data), dog [35] or wild canids [36]) while a backward position indicating a “negative anticipation”[37]. In addition, a short time spent to get to the guillotine gate could be interpreted as the high motivation of the heifers. Our subjects spent more time to go to the gate when processing recognition task of unfamiliar Charolaise images. These stimuli proved to be the most difficult to process by our subjects and lead to the greatest level of frustration (no reward). Therefore success rates, ear postures and readiness to perform the task all concur to confirm that our subjects were treating images as representations of live conspecifics.

We showed that the capacity of visual recognition of an unfamiliar individual could be extended even to individuals from a different breed with a different coat pattern. The heifers recognized individuals from Normande and Charolaise breeds, but this recognition was more difficult. Based on the reduced number of errors in the first sessions we can consider that a real generalization process was involved in the recognition of a cow of the same breed. In the recognition of a Normande or a Charolaise cow our results suggest a different mechanism. The lowest performances, compared to the previous ones, could be interpreted by the necessity to learn the different images corresponding to a particular individual. Whereas all heifers succeed in recognizing a Normande individual, the coat of which presenting some similarity to their own coat (spotted coat), with only one subject failing to reach the recognition criterion (after 250 trials) when presented with a Charolaise individual, the coat of which being of a uniform white colour, with no spots whatsoever. As it has been described in goats for mother recognition by kids [38], in cows it seems likely that coat markings or spots are important features for the recognition process. When chickens from different breeds interact, it seems that they performed breed rather than individual recognition [39]. In contrast, cows are able to perform individual recognition independently of the breed to which individuals belong. However subjects seemed disoriented when they had to base their recognition on features different from those they previously relied on. A same effect has been shown in humans who have more difficulties in recognizing dissimilar individual faces from different ethnic groups [40].

In our study the error rate changed accordingly when two stimuli in the discrimination task were under different orientations, and this effect was based on the breeds shown in the stimuli. However the error rate did not vary with the angle view of the sample individual. Our results are in agreement with those of Sato and Yoshikawa [26], who showed that their two cow subjects attended the same amount of time to the frontal, profile and back views of a cow stimulus. These results contrast with those of Bruce et al. [41] who showed, in humans, that the recognition of an unfamiliar individual was the easiest with ¾ frontal views and the most difficult with profile views. Perhaps, other features like attributes of faces (e.g. eyes, internal or external features) can have an influence on the performances in individual recognition. Configural cues are important in chimpanzee face processing [42] and Parr et al. [14] showed that the eyes were the most important cues for individual recognition in chimpanzees and macaques. In sheep Peirce et al. [18] showed that only familiar faces could be recognized using the internal features alone. External features could be used to identify both familiar and unfamiliar faces. Key facial features like ear position and appearance of the eyes were used for processing recognition of emotions in sheep [17]. Peirce and Kendrick [43] suggested that nerve cells in the right hemisphere may play a key role in the rapid identification of facial identity. Cells in the left hemisphere may be more specifically involved in slower processes associated with facial emotion recognition. Face-based emotion recognition was shown also in chimpanzees [44], [45] depending on several key features such as the shape of eyes or mouth. The sustained rather high rates of success in our experimental heifers suggest that social stimuli presented as 2D-images were appropriate stimuli facilitating picture recognition [11].

In conclusion we have demonstrated that cows are capable of visual individual recognition in discriminating within a similar category different views of one individual. This especially applies to familiar individuals, though this capacity also extends to unfamiliar individuals from the same or different breeds as the subjects. However the individual recognition task proved to be the most difficult when the visual features of the breed being tested were quite different, as with no spots, from that of the subject (spotted breed).