Face Detection and Recognition

This research paper is based on our project 'Real Time Multiple Face Recognition'. Purpose behind developing 'Face Recognition' technique is to enhance and strengthen the existing security systems. The key is to analyze the facial outline of the individual in real time which follows Principle Component Analysis (PCA) theory. Eigen face distance vector is used to determine whether the outline detected is a legitimate face. The captured Eigen faces are then compared with the training faces already stored in the database to complete recognition process. The bottom line is, the way human beings determine and distinguish among various human faces, this technique works on the same concept.

This research paper is based on our project 'Real Time Multiple Face Recognition'. Purpose behind developing 'Face Recognition' technique is to enhance and strengthen the existing security systems. The key is to analyze the facial outline of the individual in real time which follows Principle Component Analysis (PCA) theory. Eigen face distance vector is used to determine whether the outline detected is a legitimate face. The captured Eigen faces are then compared with the training faces already stored in the database to complete recognition process. The bottom line is, the way human beings determine and distinguish among various human faces, this technique works on the same concept.

Face recognition is one among several applications of digital image process. It involves the automated identification of a private in an exceedingly digital image. There are several algorithms through which this process may be carried out. Here, we have a tendency to describe techniques and implementation elements of face recognition.

DETECCIÓN DE ROSTROS EN IMAGENES, CON Python y "opencv". Es sabido que una de las posibilidades que nos ofrece la librería "opencv" es la de detectar distintos tipos de elementos en una imagen, vídeo, grabación.., mediante el uso de clasificadores, los cuales, consisten, basicamente en archivos "xml", que contienen el dataset que se encargará de ir analizando cada región de la imagen, y determinando (mediante sucesivas pruebas) si la información de dicha región se corresponde con el elemento a detectar. Así, existen, ya creados, clasificadores, diseñados específicamente, para detectar elementos muy variados (personas, ojos, manos, vehículos, matriculas, animales…etc). En esta ocasión vamos a aplicar un clasificador orientado a la detección de rostros humanos en una imagen, el cual aplicaremos sobre un archivo llamado "abba.png", que mostramos a continuación:

We present in this communication a new method to localize a face in an image. The originality of work presented consists on the use of vectors of geometrical moments like entries to a Forward Back- Propagation neural network which provide at its output layer a vector of co-ordinates in (R,�) representing pixels surrounding the face contained in the treated image.

Image processing is widely used in many applications, including medical imaging, industrial manufacturing, and security systems. Often the size of the image is very large, the processing time has to be very small and usually real-time constraints have to be met. Therefore, during the last decades there has been an increasing interest in the development and the use of parallel algorithms in image processing.

This paper describes aspects of Digital Image Processing with special reference to object detection. Image Processing is important part in a manner of Artificial Intelligence in Machines can see the outer world entity and recognize them by image processing techniques. In this section we describe what object detection is and what are the improvements can be done using OpenCV used to recognize objects by machines or systems. This paper defines There are 3 key contributions, first is to Introduction of a new image representation named as the “Integral Image” which permits the features used by our detector to be calculated very rapidly, then focusing on Learning algorithm, and finally of  Contribution is a method for joining classifiers in a cascade-Haar features classifiers which permits training regions of the picture to be rapidly discarded while spending more computation on capable object-like regions.

Face recognition has been a fast growing, challenging and interesting area in real time applications. A large number of face recognition algorithms have been developed in last decades. In this paper an attempt is made to review a wide range of methods used for face recognition comprehensively. This include PCA, LDA, ICA, SVM, Gabor wavelet soft computing tool like ANN for recognition and various hybrid combination of this techniques. This review investigates all these methods with parameters that challenges face recognition like illumination, pose variation, facial expressions.

The facial identification and recognition have a major demand in technical field mainly in the field of security purpose. Face identification and recognition is the important field for verification purpose especially in the case of attendance system. Maintaining the attendance is very important in all the institutes for checking the presence of students. Every Schools and Colleges has its own method in this regard. Some Schools and Colleges are taking attendance manually using the traditional pen and paper or file based approach. The system has developed a lot for deploying an easy way and a secured manner of taking down the attendance. The system has first captures an image of all the students and stores the information into database. The system it stores more number of the image into a face coordinates structures. Next time whenever the registered student enters the premises the system recognizes the student and marks his attendance along with the time.

The problem is to develop a fast trainable system for face detection in a real-world application. Motivation: Most object detection tasks in computer vision are computationally extensive because of a) the large amount of input data that has to be processed and b) the use of complex classifiers that are robust against pose and illumination changes. Speeding-up the classification is therefore of major concern when developing systems for real-world applications. We investigate two methods for speed-ups [8]: feature reduction and hierarchical classification.

Face recognition technology has been one of the most important fields that emerged during past two decades since the demand for identifying a person by analysing an image escalated exponentially.
A face recognition system is a computer application which identifies and verify a person’s face automatically from a digital image. To successfully identify a face, a given face’s facial features would be compared to already existing face database’s facial features. The most similar image would be selected and presented as the identified face for the given face. Facial recognition could be used in many applications of security stream such as passport photo verification, access control, payment verifications, criminal identification and many more. In this project, a generic face recognition application is developed which could be adopted in many streams. 
There are there main phases in a face recognition system. First phase is acquiring images and pre-possessing them. Pre-processing images would help to reduce the drastic changes of images with the illumination of each input image. Furthermore it would help to process the images easily by reducing dimensions and would increase the accuracy of identifying a face and decrease the processing time. The second Phase is training the data set. It is important to have a database of faces of each individual which we can use to compare with the input face. The last phase is identification of a given face.
Principal Component Analysis (PCA) is a commonly used feature extraction technique and in this project I have illustrated how it is implemented to reduce the dimensions and how it could work with Euclidian distance image classifier to identify a person’s image successfully.

Face recognition is an emergent research area, spans over multiple disciplines such
as image processing, computer vision and signal processing, machine learning. Face
recognition is mainly used for identity authentication/identification, security access
control and intelligent human-computer interaction.
This work compares holistic and hybrid face recognition methods. The hybrid face
feature extraction in which local features were derived using Multi Scale Block Local
Binary Patterns (MB-LBP) and global features are derived using Principal Component
Analysis (PCA). For a facial image a spatially enhanced, concatenated representation
is obtained by deriving a histogram from each grid that an input image
is divided. These histograms were projected to lower dimensions by applying PCA
to create eigenfaces. The holistic face representation of a subject was derived by
projecting several images of the subject into lower dimensions applying PCA.
There are several parameters affect the performance of local descriptor based face
recognition system viz: image size, grid size, operator scale and available codes. Impact
of these parameters on performance of FRS are not explored much in literature.
This thesis aims to study empirically the effect of these parameters for FRS configured
in verification mode.

The objective of this work is to automatically recognize faces from video sequences in a realistic, unconstrained setup in which illumination conditions are extreme and greatly changing, viewpoint and user motion pattern have a wide variability, and video input is of low quality. At the centre of focus are face appearance manifolds: this thesis presents a significant advance of their understanding and application in the sphere of face recognition. The two main contributions are the Generic Shape-Illumination Manifold recognition algorithm and the Anisotropic Manifold Space clustering.

The Generic Shape-Illumination Manifold algorithm shows how video sequences of unconstrained head motion can be reliably compared in the presence of greatly changing imaging conditions. Our approach consists of combining a priori domain-specific knowledge in the form of a photometric model of image formation, with a statistical model of generic face appearance variation. One of the key ideas is the reillumination algorithm which takes two sequences of faces and produces a third, synthetic one, that contains the same poses as the first in the illumination of the second.

The Anisotropic Manifold Space clustering algorithm is proposed to automatically determine the cast of a feature-length film, without any dataset-specific training information. The method is based on modelling coherence of dissimilarities between appearance manifolds: it is shown how inter- and intra-personal similarities can be exploited by mapping each manifold into a single point in the manifold space. This concept allows for a useful interpretation of classical clustering approaches, which highlights their limitations. A superior method is proposed that uses a mixture-based generative model to hierarchically grow class boundaries corresponding to different individuals.

The Generic Shape-Illumination Manifold is evaluated on a large data corpus acquired in real-world conditions and its performance is shown to greatly exceed that of state-of-the-art methods in the literature and the best performing commercial software. Empirical evaluation of the Anisotropic Manifold Space clustering on a popular situation comedy is also described with excellent preliminary results.

FACES (Faces, Art, and Computerized Evaluation Systems) is a project that, after two years of research support from the National Endowment for the Humanities (NEH), has established proof of concept for the application of face recognition technology to works of portrait art.  In the application of face recognition technology to photographed human faces, a number of difficulties are inherent in a real or perceived alteration of appearance of the face through variations in facial expression, age, angle of pose, and so on.  With works of portrait art, not only do all these problems pertain, but these works also have their own additional challenges.  Most notably, portrait art does not provide what might be called a photographic likeness but rather one that goes through a process of visual interpretation on the part of the artist.  After establishing the initial parameters of the application of this technology, the main goal of FACES has been to test the ability of the FACES algorithm to restore lost identities to works of portrait art, something our research has shown is clearly feasible.
Our work has also suggested a number of other potential applications, both using the FACES algorithm and employing basic concept of FACES in an altered form.For example an altered form of the technology used in FACES might also be used to study a wide range of other applications such as adherence or non-adherence to widely recognized artistic canons, formal or informal; the identification of variations in the practice of an individual artist (over time, with different subjects, with different genres, after exposure to external influences, and so on); probable bodies of work of anonymous artists; difference in larger bodies of works (art historical "big data"); and even to detect the change of masons in medieval building.

FACES was conceived of by myself and I am Project Director and Principal Investigator.  The FACES project is a collaboration of the humanities (art history) and the sciences (computer science).  This article, of which I am the author, presents FACES from the point of view of the humanities, that is, how this technology generally works, what the parameters of its application to portrait art are at this time, what its advantages are, and so on.  The computer science basis of the study has appeared in a leading computer science journal [Ramya Srinivasan, Conrad Rudolph, and Amit Roy-Chowdhury, "Computerized Face Recognition in Renaissance Portrait Art," Signal Processing Magazine 32:4 (July 2015) 85-94].  These two papers are meant to operate as a pair.

Face recognition is one of the challenging problems in the area of pattern detection and recognition. It is practically
applicable in different automated systems for security purpose, access control, public security, desktop login and many
more. Due to vagueness and intricacy in face pattern, there need more exercise in order to enhance the quality of face
recognition. For this purpose, we propose a robust and reliable computational model for face recognition. In this model,
two Transformation methods such as discrete wavelet transform (DWT) and discrete sine transform (DST) along with local
based feature representation namely: local binary pattern (LBP) and local phase quantization are used to extract numerical
features from face images. Irrelevant, noisy, and redundant features are eradicated using Minimum redundancy maximum
relevance (mRMR). Various classification learners such as K-nearest neighbor (KNN), Support vector machine (SVM) and
Probabilistic Neural Network (PNN) are utilized. SUMS facial dataset and 10-folds cross validation test are used to
evaluate the performance of classification algorithms. Our proposed model achieved quite promising performance, which is 92.1% accuracy. This achievement is ascribed with the discrimination power of hybrid space and SVM. It is anticipated
that the proposed computational model might be helpful for academia and researchers in face detection and recognition.

Human face recognition systems have gained a considerable attention during last decade due to its vast applications in the field of computer and advantages over previous biometric methods. There are many applications with respect to security, sensitivity and secrecy. Face detection is the most important and first step of recognition system. This paper introduces a new approach to face detection systems using the skin color of a subject. This system can detect a face regardless of the background of the picture, which is an important phase for face identification. The images used in this system are color images which give additional information about the images than the gray images provide.

With the increase in automative population, accident rates are rising rapidly, one of the major reasons is the state of drowsiness or fatigue. Such fatal incidents can be prevented if the driver is warned in time. With time, several drowsiness alarm systems are been implemented, the system monitors driver's movements through various techniques, one of the most considerable one is face detection, Open Computer Vision is widely used to detect driver's movements for a long period of time. A comparative study on different types of approach is summarized in this paper. The main agenda is to help the society to understand more about the techniques and find the most convenient method for them.

We present in this communication a new method to localize a face in an image. The originality of work presented consists on the use of vectors of geometrical moments like entries to a Forward Back-Propagation neural network which provide at its output layer a vector of coordinates in (R,θ) representing pixels surrounding the face contained in the treated image. Very known for their orthogonality and their rotational invariability, the geometrical moments of Zernike are calculated here to form the feature vectors supplied to the input layer of the network. The experimental results of the application of our method on images of the XM2VTS database are presented.

This research paper is based on our project 'Real Time Multiple Face Recognition'. Purpose behind developing 'Face Recognition' technique is to enhance and strengthen the existing security systems. The key is to analyze the facial outline of the individual in real time which follows Principle Component Analysis (PCA) theory. Eigen face distance vector is used to determine whether the outline detected is a legitimate face. The captured Eigen faces are then compared with the training faces already stored in the database to complete recognition process. The bottom line is, the way human beings determine and distinguish among various human faces, this technique works on the same concept.

—Face detection is an interesting area in research application of computer vision and pattern recognition, especially during the past several years. It is also plays a vital role in surveillance systems which is the first steps in face recognition systems. The high degree of variation in the appearance of human faces causes the face detection as a complex problem in computer vision. The face detection systems aimed to decrease false positive rate and increase the accuracy of detecting face especially in complex background images. The main aim of this paper is to present an up-to-date review of face detection methods including feature-based, appearance-based, knowledge-based and template matching. Also, the study presents the effect of applying Haar-like features along with neural networks. We also conclude this paper with some discussions on how the work can be taken further. Keywords—face detection; feature based face detection; human face detection; haar-like features; neural networks.

This paper presents a approach on how to reduce
stress and fatigability in the user’s eyes, muscles and  also
backbone when  the user is using a computer. The study uses image processing technique for the detection of the face of the user. The monitor of the desktop computer is connected with a DC motor that will auto align itself to the face of the user in order to make sure it is in front of the user’s face. If the user moves its head sideward the monitor will align and this will help the user to have movements of the bone and also muscles on its back. The movement of the monitor through the microcontroller  and  also  the face detection part was programmed on the python software.

Face detection, plays an important role in many applications such as face recognition, face tracking, human computer interface and video surveillance. In this paper we propose a Hybrid face detection algorithm that could detect faces in color images with different complex ...

Recently, a number of applications of automatic facial expression recognition systems havesurfaced in many different research fields. The automatic facial expression recognition problem is a very challenging problem because it involves in three sub-problems: 1) face detection, 2) facial expression feature extraction, and 3) expression classification. This paper presents an automatic facial expression recognition system based on self-organizing feature maps, which provides an effective solution to the aforementioned three sub-problems. The performance of the proposed system was computed on twowell-known facial expression databases. The average correct recognition rates were over 90%

Though a lot of research has already been done in the field of Face Recognition, one amongst the remaining challenges is recognizing multiple faces in weird conditions in a large group size. A robust face recognition system has been developed which detects faces in multiple, occluded, posed images obtained under low illumination conditions. The detector is a trained 34 layered Residual Network which obtains an accuracy of 98.4% on Visual Geometry Group Dataset [1]. A hybrid model has been proposed by combining the Residual Network detector with the novel approach of face embedding using triplet loss function [2] for recognition. The numerical and graphical results attached in the report depict the effectiveness of the proposed model for a variety of conditions. A 22 layered Inception Network has been trained for feature extraction and it achieves an accuracy of 99.5% on Labeled Faces in the Wild Dataset [3]. To achieve a similar accuracy on real life scenarios different methods like dimensionality reduction and data augmentation have been implemented. A mobile application has also been developed which utilizes the above described hybrid model for identification of people present in a large group. This application outweighs the fingerprint biometric in terms of speed, cost and group size.

Humans make use of facial expression to communicate in their day to day interactions with each other, which comes naturally without much effort. Facial expression is essentially a communication and interaction between humans and where other information like speech is not available; it becomes what one can depend on to transmit emotion or reactions of an individual. Hence, human expression recognition with high recognition is still an interesting task. This study is aimed at implementing face detection and expression recognition using fuzzy rule interpolation (FRI) technique. This follows through a development of specifications for fuzzy rule interpolation in emotion recognition using the viola jones algorithm as the detection algorithm and local binary pattern (LBP) algorithm for the feature extraction. The extended Cohn Kanade (CK+) face database was used for the experimentation of the system. The classification of the various expressions was achieved by the image category classifier of Matlab.

This work is motivated by two important trends in consumer computing: (i) the growing pervasiveness of mobile computing devices, and (ii) the users' desire for increasingly complex but readily acquired and manipulated information content. Specifically, we develop and describe a system for 3D model creation of an object, using only a standard mobile device such as a smart phone. Our approach applies the structured light projection methodology and exploits multiple image input such as frames from a video sequence. In comparison with previous work, a significant further challenge addressed here is that of lower quality input data and limited hardware (processing power and memory, camera and projector quality). Novelties include: (i) a comparison of projection pattern detection approaches in the context of a mobile environment - a robust method combining colour detection and a phase congruency descriptor is proposed, (ii) a model for single view reconstruction which exploits epipolar, coplanarity and topological constraints, (iii) the use of mobile device sensor data in the iterative closest point algorithm used to register multiple partial 3D reconstructions, and (iv) two heuristics for determining the order in which buffered single view based reconstructions are merged. Our experiments demonstrate that visually appealing results are obtained in a speedy manner which does not require specialist knowledge or expertise from the user.

Major injuries and death in accidents have roots in drowsiness. Sleepiness is a main result of insufficient sleep. It is vital to explore drowsiness and its level. There are various sorts of methods in the forms of subjective and objective approaches. The goal of this study was to detect the association of subjective and interpretive drowsiness with facial dynamic changes. This experimental study was conducted in the Virtual Reality Lab, in Khaje-Nasir Toosi University of Technology, Tehran Iran on 40 drivers in 2015. Facial dynamic changes (eyes, mouth and eyebrows), Karolinska Sleepiness Scale (KSS) and Observer Rating of Drowsiness (ORD) were applied. The neural network and Viola-Jones were utilized for facial characteristics detection. Statistical analyses were conducted using SPSS version 21. Thirty-four drivers got drowsy during the test. They were selected randomly among suburban drivers at the age in a range of 26 to 60 yr old. Descriptive statistics of the dynamic changes i...

This research paper investigates the running of object detection algorithms on low-end devices to detect individuals in images while leveraging cloud-based services to provide facial verification of the individuals detected. The performance of three computer vision object detection algorithms that utilize Convolutional Neural Networks (CNN) are compared: SSD MobileNet, Inception v2 and Tiny YOLO along with three cloud-based facial verification services: Kairos, AmazonWeb Service Rekognition (AWS) and Microsoft Azure
Vision API. The results contribute to the limitations of running CNN based algorithms to solve vision tasks on low-end devices and highlights the limitations of using such devices and models in an application domain such as a home-security solution.

Face detection is considered as a challenging problem in the field of image analysis and computer vision. There are many researches in this area, but because of its importance, it needs to be further developed. Successive Mean Quantization Transform (SMQT) for illumination and sensor insensitive operation and Sparse Network of Winnow (SNoW) to speed up the original classifier based face detection technique presented such a good results......

Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in the real world. While inherently insensitive to visible spectrum illumination changes, IR images introduce specific challenges of their own, most notably sensitivity to factors which affect facial heat emission patterns, e.g.\ emotional state, ambient temperature, and alcohol intake. In addition, facial expression and pose changes are more difficult to correct in IR images because they are less rich in high frequency detail which is an important cue for fitting any deformable model. In this paper we describe a novel method which addresses these major challenges. Specifically, to normalize for pose and facial expression changes we generate a synthetic frontal image of a face in a canonical, neutral facial expression from an image of the face in an arbitrary pose and facial expression. This is achieved by piecewise affine warping which follows active appearance model (AAM) fitting. This is the first publication which explores the use of an AAM on thermal IR images; we propose a pre-processing step which enhances detail in thermal images, making AAM convergence faster and more accurate. To overcome the problem of thermal IR image sensitivity to the exact pattern of facial temperature emissions we describe a representation based on reliable anatomical features. In contrast to previous approaches, our representation is not binary; rather, our method accounts for the reliability of the extracted features. This makes the proposed representation much more robust both to pose and scale changes. The effectiveness of the proposed approach is demonstrated on the largest public database of thermal IR images of faces on which it achieved 100% identification rate, significantly outperforming previously described methods.

This research paper is based on our project 'Real Time Multiple Face Recognition'. Purpose behind developing 'Face Recognition' technique is to enhance and strengthen the existing security systems. The key is to analyze the facial outline of the individual in real time which follows Principle Component Analysis (PCA) theory. Eigen face distance vector is used to determine whether the outline detected is a legitimate face. The captured Eigen faces are then compared with the training faces already stored in the database to complete recognition process. The bottom line is, the way human beings determine and distinguish among various human faces, this technique works on the same concept.

d law enforcement applications. Hence it is unsurprising that it continues to be one of the most active research areas of computer vision. Even after over three decades of intense research, the state-of-the-art in face recognition continues to improve, benefitting from advances in a range of different research fields such as image processing, pattern recognition, computer graphics, and physiology. Systems based on visible spectrum images, the most researched face recognition modality, have reached a significant level of maturity with some practical success. However, they continue to face challenges in the presence of illumination, pose and expression changes, as well as facial disguises, all of which can significantly decrease recognition accuracy. Amongst various approaches which have been proposed in an attempt to overcome these limitations, the use of infrared (IR) imaging has emerged as a particularly promising research direction. This paper presents a comprehensive and timely r...

Face recognition is diversely used in modern biometric and security applications. Most of the current face recognition techniques show good results in a constrained environment. However, these techniques face many problems in real-world scenarios such as low-quality images, temporal variations and facial disguises creating variations in facial features. The reason for these deteriorating results is the employment of hand-crafted features having weak generalization capabilities and neglecting the complexities associated with domain adaption in case of deep learning models. In this paper, we have studied the efficacy of deep learning methods incorporating simple noise-based data augmentation for disguise invariant face recognition (DIFR). The proposed method detects face in an image using Viola Jones face detector and classifies it using a pre-trained Convolutional Neural Network (CNN) fine-tuned for DIFR. During transfer learning, a pre-trained CNN learns generalized disguise-invariant features from facial images of several subjects to correctly identify them under varying facial disguises. We have compared four different pre-trained 2D CNNs, each with different number of learning parameters, based on their classification accuracy and execution time for selecting a suitable model for DIFR. Comprehensive experiments and comparative analysis have been conducted on six challenging facial disguise datasets. Resnet-18 gives the best trade-off between accuracy and efficiency, by achieving an average accuracy of 98.19% with an average execution time of 0.32 seconds. The promising results achieved in these experiments reflect the efficiency of the proposed method and outperforms the existing methods in all aspects.

The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).

d law enforcement applications. Hence it is unsurprising that it continues to be one of the most active research areas of computer vision. Even after over three decades of intense research, the state-of-the-art in face recognition continues to improve, benefitting from advances in a range of different research fields such as image processing, pattern recognition, computer graphics, and physiology. Systems based on visible spectrum images, the most researched face recognition modality, have reached a significant level of maturity with some practical success. However, they continue to face challenges in the presence of illumination, pose and expression changes, as well as facial disguises, all of which can significantly decrease recognition accuracy. Amongst various approaches which have been proposed in an attempt to overcome these limitations, the use of infrared (IR) imaging has emerged as a particularly promising research direction. This paper presents a comprehensive and timely review of the literature on this subject. Our key contributions are (i) a summary of the inherent properties of infrared imaging which makes this modality promising in the context of face recognition; (ii) a systematic review of the most influential approaches, with a focus on emerging common trends as well as key differences between alternative methodologies; (iii) a description of the main databases of infrared facial images available to the researcher; and lastly (iv) a discussion of the most promising avenues for future research.

Image processing is widely used in many applications, including medical imaging, industrial manufacturing, and security systems. Often the size of the image is very large, the processing time has to be very small and usually real-time constraints have to be met. Therefore, during the last decades there has been an increasing interest in the development and the use of parallel algorithms in image processing. This paper presents and evaluates a method for introducing parallelism into an image processing application. The method is based on algorithmic skeletons for low, medium and high level image processing operations. They provide an easy-touse parallel programming interface. To evaluate this approach, face recognition is implemented twice on a highly parallel processing platform, once via skeletons, once directly and highly optimized. It is demonstrated that the skeleton approach is extremely convenient from a programmers point of view, while the performance penalty of using skeletons is well below 10% in our case study.