Face Recognition

Abstract

The primary role of this paper is to bring out a clear investigation on the hypothesis of face recognition as brought forth by Bruce and Young in their writings of 1986. The paper will feature things like facial expression and the impact they have on one’s identity. Facial expression will be one of the variables. Other things that will be used as variables include types of information derived from one’s facial expression and emotions. However the ability to get accurate information from facial expressions of people will be another variable, together with how quickly individuals are in a position to respond in the right way.

Keywords: variables, emotion, accuracy, response, facial expression.

Face Recognition

Introduction

            There are many forms of information that can be derived from the face of any individual. Various writers in psychology have addressed the issue of facial expression and how different messages can be realized from the face of a person. Developing a theoretical model and establishing terms of comprehending and discussing methods of recognizing familiar faces will be well handled in this paper. The other topic of discussion will be on the relationship existing between recognition and other aspects of face processing. It has been established that there seven different types of information that is realized from any seen face. The distinctive types are labeled as pictorial, structural, visually derived semantic, identity-specific semantic, name, expression, and facial speech codes (Mindick, 2010).
            At any point the functional model is believed to be a process where structural encoding methods offer descriptions of analyzing facial speech codes. However, the method still examines expression and face recognition units. The process of recognizing familiar faces entails the process of matching the products of structural encoding and the preceding information already in store structural codes that tell more about the appearance of familiar faces, which is already apprehended in face recognition units. The identity-semantic codes are said to be identified by any person identity nodes where at the same time name codes are realized from. According to discussions with the various writers, the cognitive scheme is found to play an active role in deciding on how close the original match is sufficiently close in indicating a real recognition or resemblance (Lorrimer, 2009). The functional model is found to be useful in bringing together information from different sources that include experiments carried out in laboratories. Moreover, the functional model helps in studying of daily errors, as it ensures studies of patients who possess varying cerebral injury complications. The functional models are at the same time used to bring out a clear distinction between processes responsible for objects, word, and face recognition (Liew, 2009).

The model function is known to be an excellent tool that has been used in psychology to learn more on facial recognition. Initially, it was not easy to find out more about individuals unless they said something or someone was familiar with them. After developing the model, it has become easy to find out more about individuals using their faces. Their emotions are part of their facial expressions, and it has been established that the face of an individual will give complete information on whether they are happy, sad or bored. Some facial expressions like a smiling face show one is happy and welcoming, but a serious face may be an indication that someone is tired and not interested in what is being said or discussed (Hill, 2010).
            A human face will at all times provide information to a perceiver. As discussed, it can tell about moods, objectives, and attentiveness, and at some point it can be the best way of identifying someone. It is true there are many ways of identifying a person, but the face can be one of the best ways, as some psychologists have proved it. At times voice, body shape, gait and clothing can be used as different ways of learning the identity of a person. However, this is because there are different fields that demand different dressings and body size. Nevertheless, the face remains the most distinctive and broadly used method of learning more about a person’s identity. This is true because according to a report released by the medicine department on the loss of ability to be acquainted with faces experienced by neurosurgical patients, this d8isability has been found to have effects on their lives (Huer, 1990).
            In the urge of understanding face processing as a paramount issue, there is the need to determine how people can make good use of all information realized from their faces. As discussed earlier any information that can be derived from the face is called a code. These systems are assumed not to be the functional components themselves that are utilized during face processing system. However, these codes are said to be the end results of the operation of the already in place functional components. The ability to have various methods of coding facial information offers a suitable set of terms when discussing face processing facial messages derived. However, there some important questions that have been put forward when examining more on the topic of face and identity. Some of those questions include; what diverse information codes are used in facial processing? What functional components handle the generation and access to these varying systems? These two issues are known to have remained useful to the world of psychology, in particular when identifying a person through their face (Baudon, 2011).
1. What different Codes are involved in face processing?

The codes involved in face processing can be discussed using a photograph or a picture of one’s face. A pictorial system is said to be generated by the photo of a face. Though the graphic system is said to be a description of an image, at any point it should not be equated with the view-specific message derived that is upgraded in the continuous way. The pictorial code is found to comprise things like lighting, grain, and any flaws found in any given photograph, as well as capturing more on the pose and expression as depicted in the picture. A match at a particular level of a pictorial code can be used to expound more on the opinion of the one in the photo; it can be a source of yes/no recognition memory. However, all this may not be enough ; hence, it will be great to learn more about facial changes on individuals for this will help in coming up with concrete information about the identity of such an individual ( Brouwers, 2007). The pictorial code is found to be a more general code that is formed from any visual pattern of an image. Even then, graphic coding is considered to be more general, and its importance lies in the interpretation, as per what individual can see on a given paper (Bruce, 2012). A pictorial code is useful for daily life because individuals come across different faces every day. However, the study is paramount since after studying it clearly, it will be possible to learn more from one’s face without struggling. The research paper will help on making sure that when discussing something with someone one can withdraw any topic that seems to be boring as per one’s facial expression.
2. Functional components in the human processing system

It is true that recognition memory experiments can be understood in terms of the way the codes are formed. Somehow, everyday recognition of known faces can be discussed through the use of sequential accessibility of various systems. However, at times it is possible for different people to get different messages from any observed system. The bottom line is that the use of a face is crucial especially when learning more about an individual. This topic will help in learning more about how important it is to arouse individuals so as to find out more about their emotions that are expressed through their faces. It is easy to learn about individuals through their facial expressions. This is because once they are provoked they show their reactions on their faces where signs of amusement or discouragement are shown (Young, 1986).
            There are beliefs that one is responsible for their faces. It is true their people who have stinging faces but with clean hearts. However, there others who are found to possess a natural smile on their face but with crooked hearts. This is why at some point it is good to interact with individuals because using the face alone may not give enough information (Woodward, 2003). However, loving and caring will always have a smile on their face while hurting people will at all times have a scary face that lacks any sign of a smile. Moreover, this study checks more on emotions, different people respond differently to both sad and good news. This means there are some who will look composed even in times of problems while others will break into tears. During happiness, some people will be screaming while others will only have a smiling face (Carter, 2012).
Experiment
Recognition of Emotions from full upright and upside faces

This experiment shows more on how it is possible to interpret two types of faces. The experiment is about one H.J.A, who was born back in 1920 who was an American. By 1981, H.J.A was diagnosed with the posterior cerebral artery. According to some investigations carried on earlier, it is clear that H.J.A had some visual agnosia, prosopagnosia, alexia, achromatopsia and topographical. After a short time, the stroke resulted in inbilateral lesions that extended to the anterior temporal lobe. Finally, it was noted that H.J.A was severely impaired by both the face identification, where he could not identify twenty famous faces. H.J.A was found to have a problem with familiarity discrimination, where at some point he was not able to expound more on familiar faces provided to him. Due to H.J.A having a prosopagnosia it was hard for him to have 100% recognition ability (Clark, 2005).

General method

The H.J.A procedure was put into comparison with other four age match male controls, who were aged between 74-86 years (Control A: 86, control B: 74, control C: 81 control D: 74). It was established that individuals from the controlled ages had no cases of the psychiatric disorder. Except control A, all others had a vision that had been corrected to standard. The other controls except A were found to have cases of seeing problems and distant stimuli (Terry, 1994). Control C was said to have a small blind area of the field. Except C, all other controls were used to perform the upright versus the upside down facial emotion recognition task. Both Control A and Control B were used in undertaking the composite task on the top halves, and both control A and control C on bottom halves. According to the end results of the experiment, there was no proof of any varying performance existing between the controls as a function of age (Cohen, 1986).
Materials and Results
            There was the use of a 75 high-resolution color images, which of 25 different individuals. However, the used pictures were to be viewed from frontal viewpoints. The images used expressed three types of emotions that included happiness, anger and fear. There used images were standardized 15 cm from the top. The pictures were gotten from some volunteers who were aged between 18 to 31 years old. The volunteers had been instructed to portray several emotional facial expressions. The types of emotions were grouped into six categories that included; happiness, sadness, fear, disgust, anger, neutral and any other that could be useful for the experiment. According to the experiment for every emotion, there was at least over 83% consent for the grouping as at control subjects (Gates, 2011).

            The entire experiment was a two-choice motion discrimination that needed participating individuals to say the type of emotion that was being expressed. The reason happiness and anger were highly used was because it was easier to discriminate the two from other forms of motions on both bottom and top parts of the face ( Simon, 2005).According to the report individuals made great mistakes when they were identifying emotion displayed at the top regions of the face for both happiness and anger. When using the bottom parts, it was not easy to judge when disgust was being expressed. During the experiment, it was not easy to recognize butthi emotions, especially from the top part. (Stathopoulou, 2010).  On the other it was difficult to realize anger emotions expressed on the bottom parts. Both the top and bottom parts of every face were cut into two parts horizontally, where the nose was the bridge. The experiment was repeated with different individuals who were told to say whether the pictures represented happiness or anger (Gong, 2000).

Discussions and results

            As presented in the above chart H.J.A is found to have done better than chance level with the upright faces where he got over 83% correct. On the other part of the down faces, he got on 38%. This means it was not easy to judge emotions being expressed by the lower part of the face. When inverted faces were used it was not easy to get, the correct emotion being expressed by the provided picture. As from the experiment, it is clear judging happiness and anger emotions was easy especially on the upper part of the face when compared to the lower part of the face (Rakover, 2001).This means that it is easy to learn more on one’s face using the top part of the face when compared to the lower half of the face. Making judgments on disgust emotion is not easy as compared to happiness and anger. There are still limitations to this experiment because at times what someone sees on a given picture may different from what another person is seeing the same picture. With such differences on observation responses given about a particular facial expression might be difficult and this may lead to a situation of misjudgment (Gay, 2012).

Reference

Baudouin, J., & Humphreys, G. (2011). Compensatory strategies in processing facial emotions: Evidence from prosopagnosi. Hal.

Brouwers, A. (2007). Emotions in wood: Carving the expressive face. Fresno, CA: Linden Pub.

Bruce, V., & Young, A. (2012). Face perception. London: Psychology Press.

Bruce, V. & Young, A. (1986).Understanding face recognition. British Journal of Psychology, 77, 305-327.

Carter, S. (2012). Facial expressions: Dynamic patterns, impairments and social perceptions. Hauppauge, N.Y.: Nova Science Publisher’s.

Clark, A. (2005). Psychology of moods. New York: Nova Science.

Cohen, G. & Faulkner, D. (1986). Memory for proper names: Age differences in retrieval. British Journal of Developmental Psychology, 4, 187-197.

Gates, K. (2011). Our biometric future: Facial recognition technology and the culture of surveillance. New York: New York University Press.

Gong, S., & McKenna, S. (2000). Dynamic vision from images to face recognition. London: Imperial College Press.

Gray, B. (2012). Face to face with emotions in health and social care. New York, NY: Springer.

Heuer, F. &Reisberg, D. (1990). Vivid memories of emotional events: the accuracy of remembered minutiae. Memory & Cognition, 18 (5), Sep, pp. 496-506.

Hill, D. (2010). About face the secrets of emotionally effective advertising. London: Kogan Page.

Liew, A., & Wang, S. (2009). Visual speech recognition: Lip segmentation and mapping. Hershey, PA: Medical Information Science Reference.

Lorrimer, C. (2009). Emotions (Large print Ed.). Bath: Chivers.

Mindick, N., & Alperin, G. (2010). Understanding facial recognition disorders in children prosopagnosia management strategies for parents and professionals. Philadelphia: Jessica Kingsley.

Rakover, S., & Cahlon, B. (2001). Face recognition cognitive and computational processes. Amsterdam: John Benjamins Pub.

Simon, M. (2005). Facial expressions: A visual reference for artists. New York: Watson-Guptill

Stathopoulou, I., & Tsihrintzis, G. (2010). Visual affect recognition. Amsterdam: IOS Press.

Terry, W. S. (1994). On the relative difficulty in recalling names and occupations.American Journal of Psychology, 107(1), 85-94.

Woodward, J. (2003). Biometrics a look at facial recognition. Santa Monica, Calif.: RAND.