GB2414613A - Modifying pixels in dependence on surrounding test region - Google Patents

Abstract

An image processing method for processing an input image comprising plural elements to generate an output image comprises the steps of, for each image element in at least a portion of the image, detecting an image property (preferably luminance) of image elements in a test region (preferably square) surrounding that image element, and modifying that image element in dependence on that property, in particular by averaging the image element's luminance with the minimum luminance across the test region. The method is for use in a system which detects an object, such as a face, in an image and can track the face and/or compare it with a number of stored faces. The system may be a videoconferencing or surveillance system. Also described are methods for: comparing a test region of an image with reference regions for recognition; comparing images in a set and selecting those which have least similarity with the others; and associating an identifier with each of two tracked objects, determining if they are similar in appearance, counting the number of images in which both occur and if the number is below a threshold, changing the identifier of one to the other.

Description

1 2414613

IMAGE PROCESSING

This invention relates to image processing.

Although the invention has wider application, technical background will now be s described with reference to object detection. In particular, the background will be discussed with respect to face detection for clarity of the description.

Many human-face detection algorithms have been proposed in the literature, including the use of so-called eigenfaces, face template matching, deformable template matching or neural network classification. None of these is perfect, and each generally has associated advantages and disadvantages. None gives an absolutely reliable indication that an image contains a face; on the contrary, they are all based upon a probabilistic assessment, based on a mathematical analysis of the image, of whether the image has at least a certain likelihood of containing a face. Depending on their application, the algorithms generally have the threshold likelihood value set quite high, to try to avoid false detections of faces.

The success of object detection can depend on the lighting conditions at the time the object was acquired.

This invention provides an image processing method for processing an input image comprising plural image elements to generate an output image, the method comprising the steps, for each image element in at least a portion of the input image: detecting an image property of image elements in a test region surrounding that image element, the test region representing a subset of the input image; modifying the image element in dependence on the detected image property, to generate a corresponding image element of the output image.

The invention provides a technique for altering, for example, the image contrast of an image, and can render the altered image more useful for (for example) object detection such as face detection.

Various further respective aspects and features of the invention are defined in the appended claims.

Embodiments of the invention will now be described, by way of example only, with reference to the accompanying drawings, throughout which like parts are defined by like numerals, and in which: Figure 1 is a schematic diagram of a general purpose computer system for use as a face detection system and/or a non-linear editing system; Figure 2 is a schematic diagram of a video camera-recorder (camcorder) using face detection; Figure 3 schematically illustrates a video conferencing system; Figures 4 and 5 schematically illustrate a video conferencing system in greater detail; Figure 6 is a schematic diagram illustrating a training process; Figure 7 is a schematic diagram illustrating a detection process; Figure 8 schematically illustrates a face tracking algorithm; Figures 9a to 9c schematically illustrate the use of face tracking when applied to a video scene; lO Figure 10 is a schematic diagram of a face detection and tracking system; Figure 11 schematically illustrates a similarity detection technique; Figure 12 schematically illustrates system performance for different training sets; and Figures 13a and 13b schematically illustrate trial results.

The description of Figures 1 to 9c summarises the teaching of application number PCT/GB2003/005186. Reference is made to that application for fuller details of the technical features summarised here. Features disclosed in PCT/GB2003/005186 which are not explicitly referred to in the following summary description should still be considered as (at least optional) features of the present detection arrangement.

The following description will refer to face detection and/or tracking as aims of the various techniques. However, it should be appreciated that the techniques are applicable to detecting and/or tracking many different types of objects. An example is that of detecting cars. Accordingly, the references to faces are merely to provide a framework to make the description easier to follow. The term "face" is not necessarily to be taken as implying any

limitation in the description that follows.

Figure 1 is a schematic diagram of a general purpose computer system for use as a face detection system and/or a non-linear editing system. I he computer system comprises a processing unit lO having (amongst other conventional components) a central processing unit (CPU) 20, memory such as a random access memory (RAM) 30 and non-volatile storage such as a disc drive 40. The computer system may be connected to a network SO such as a local area network or the Internet (or both). A keyboard 60, mouse or other user input device 70 and display screen 80 are also provided. The skilled man will appreciate that a general purpose computer system may include many other conventional parts which need not be described here.

Figure 2 is a schematic diagram of a video camera-recorder (camcorder) using face detection. The camcorder 100 comprises a lens 110 which focuses an image onto a charge coupled device (CCD) image capture device 120. The resulting image in electronic form is processed by image processing logic 130 for recording on a recording medium such as a tape cassette 140. The images captured by the device 120 are also displayed on a user display which may be viewed through an eyepiece 160.

To capture sounds associated with the images, one or more microphones are used.

These may be external microphones, in the sense that they are connected to the camcorder by a flexible cable, or may be mounted on the camcorder body itself. Analogue audio signals lo from the microphone (s) are processed by an audio processing arrangement 170 to produce appropriate audio signals for recording on the storage medium 140.

It is noted that the video and audio signals may be recorded on the storage medium in either digital form or analogue form, or even in both forms. Thus, the image processing arrangement 130 and the audio processing arrangement 170 may include a stage of analogue to digital conversion.

The camcorder user is able to control aspects of the lens 1 lO's performance by user controls 180 which influence a lens control arrangement 190 to send electrical control signals 200 to the lens 110. Typically, attributes such as focus and zoom are controlled in this way, but the lens aperture or other attributes may also be controlled by the user.

Two further user controls are schematically illustrated. A push button 210 is provided to initiate and stop recording onto the recording medium 140. For example, one push of the control 210 may start recording and another push may stop recording, or the control may need to be held in a pushed state for recording to take place, or one push may start recording for a certain timed period, for example five seconds. In any of these arrangements, it is technologically very straightforward to establish from the camcorder's record operation where the beginning and end of each "shot" (continuous period of recording) occurs.

The other user control shown schematically in Figure 2 is a "good shot marker" (GSM) 220, which may be operated by the user to cause "metadata" (associated data) to be stored in connection with the video and audio material on the recording medium 140, indicating that this particular shot was subjectively considered by the operator to be "good" in some respect (for example, the actors performed particularly well; the news reporter pronounced each word correctly; and so on).

The metadata may be recorded in some spare capacity (e.g. "user data") on the recording medium 140, depending on the particular format and standard in use.

Alternatively, the metadata can be stored on a separate storage medium such as a removable MemoryStickRTM memory (not shown), or the metadata could be stored on an external s database (not shown), for example being communicated to such a database by a wireless link (not shown). The metadata can include not only the GSM information but also shot boundaries, lens attributes, alphanumeric information input by a user (e. g. on a keyboard - not shown), geographical position information from a global positioning system receiver (not shown) and so on.

In So far, the description has covered a metadata-enabled camcorder. Now, the way in which face detection may be applied to such a camcorder will be described.

The camcorder includes a face detector arrangement 230. Appropriate arrangements will be described in much greater detail below, but for this part of the description it is sufficient to say that the face detector arrangement 230 receives images from the image processing arrangement 130 and detects, or attempts to detect, whether such images contain one or more faces. The face detector may output face detection data which could be in the form of a "yes/no" flag or may be more detailed in that the data could include the image eo ordinates of the faces, such as the coordinates of eye positions within each detected face.

This information may be treated as another type of metadata and stored in any of the other formats described above.

As described below, face detection may be assisted by using other types of metadata within the detection process. For example, the face detector 230 receives a control signal from the lens control arrangement 190 to indicate the current focus and zoom settings of the lens 110. These can assist the face detector by giving an initial indication of the expected image size of any faces that may be present in the foreground of the image. In this regard, it is noted that the focus and zoom settings between them define the expected separation between the camcorder 100 and a person being filmed, and also the magnification of the lens 110. From these two attributes, based upon an average face size, it is possible to calculate the expected size (in pixels) of a face in the resulting image data.

A conventional (known) speech detector 240 receives audio information from the audio processing arrangement 170 and detects the presence of speech in such audio information. The presence of speech may be an indicator that the likelihood of a face being present in the corresponding images is higher than if no speech is detected. s

Finally, the GSM information 220 and shot information (from the control 210) are supplied to the face detector 23O, to indicate shot boundaries and those shots considered to be most useful by the user.

Of course, if the camcorder is based upon the analogue recording technique, further s analogue to digital converters (ADCs) may be required to handle the image and audio information.

As a further example of the use of these detection techniques, Figure 3 schematically illustrates a video conferencing system. Two video conferencing stations 1100, 1110 are connected by a network connection 1120 such as: the Internet, a local or wide area network, lo a telephone line, a high bit rate leased line, an ISDN line etc. Each of the stations comprises, in simple terms, a camera and associated sending apparatus 1130 and a display and associated receiving apparatus 1140. Participants in the video conference are viewed by the camera at their respective station and their voices are picked up by one or more microphones (not shown in Figure 3) at that station. The audio and video information is transmitted via the network 1120 to the receiver 1140 at the other station. Here, images captured by the camera are displayed and the participants' voices are produced on a loudspeaker or the like.

It will be appreciated that more than two stations may be involved in the video conference, although the discussion here will be limited to two stations for simplicity.

Figure 4 schematically illustrates one channel, being the connection of one camera/sending apparatus to one display/receiving apparatus.

At the camera/sending apparatus, there is provided a video camera 1150, a face detector 1160 using the techniques described above, an image processor 1170 and a data formatter and transmitter 1180. A microphone 1190 detects the participants' voices.

Audio, video and (optionally) metadata signals are transmitted from the formatter and transmitter 1180, via the network connection 1120 to the display/receiving apparatus 1140.

Optionally, control signals are received via the network connection 1120 from the display/receiving apparatus 1140.

At the display/receiving apparatus, there is provided a display and display processor 1200, for example a display screen and associated electronics, user controls 1210 and an audio output arrangement 1220 such as a digital to analogue (DAC) converter, an amplifier and a loudspeaker.

In general terms, the face detector 1160 detects (and optionally tracks) faces in the captured images from the camera 1150. The face detections are passed as control signals to the image processor 1170. The image processor can act in various different ways, which will be described below, but fundamentally the image processor 1170 alters the images captured by the camera 1150 before they are transmitted via the network 1120. A significant purpose behind this is to make better use of the available bandwidth or bit rate which can be carried by the network connection 1120. Here it is noted that in most commercial applications, the s cost of a network connection 1120 suitable for video conference purposes increases with an increasing bit rate requirement. At the formatter and transmitter 1180 the images from the image processor 1170 are combined with audio signals from the microphone 1190 (for example, having been converted via an analogue to digital converter (ADC)) and optionally metadata defining the nature of the processing carried out by the image processor 1170.

lo Figure 5 is a further schematic representation of the video conferencing system.

Here, the functionality of the face detector 1160, the image processor 1170, the formatter and transmitter 1180 and the processor aspects of the display and display processor 1200 are carried out by programmable personal computers 1230. The schematic displays shown on the display screens (part of 1200) represent one possible mode of video conferencing using face detection and tracking, namely that only those image portions containing faces are transmitted from one location to the other, and are then displayed in a tiled or mosaic form at the other location.

The present embodiment uses a face detection technique arranged as two phases.

Figure 6 is a schematic diagram illustrating a training phase, and Figure 7 is a schematic diagram illustrating a detection phase.

Unlike some previously proposed face detection methods, the present method is based on modelling the face in parts instead of as a whole. The parts can either be blocks centred over the assumed positions of the facial features (so-called "selective sampling") or blocks sampled at regular intervals over the face (so-called "regular sampling"). The present description will cover primarily regular sampling, as this was found in empirical tests to give the better results.

In the training phase, an analysis process is applied to a set of images known to contain faces, and (optionally) another set of images ("nonface images") known not to contain faces. The process can be repeated for multiple training sets of face data, representing different views (e.g. frontal, left side, right side) of faces. The analysis process builds a mathematical model of facial and nonfacial features, against which a test image can later be compared (in the detection phase).

So, to build the mathematical model (the training process 310 of Figure 6) , the basic steps are as follows: 1. From a set 300 of face images normalised to have the same eye positions, each face is sampled regularly into small blocks.

2. Attributes are calculated for each block; 3. The attributes are quantised to a manageable number of different values.

s 4. The quantised attributes are then combined to generate a single quantised value in respect of that block position.

5. The single quantised value is then recorded as an entry in a histogram. The collective histogram information 320 in respect of all of the block positions in all of the training images forms the foundation of the mathematical model of the facial features.

One such histogram is prepared for each possible block position, by repeating the above steps in respect of a large number of test face images. So, in a system which uses an array of 8 x 8 blocks, 64 histograms are prepared. In a later part of the processing, a test quantised attribute is compared with the histogram data; the fact that a whole histogram is used to model the data means that no assumptions have to be made about whether it follows a parameterised distribution, e.g. Gaussian or otherwise. To save data storage space (if needed), histograms which are similar can be merged so that the same histogram can be reused for different block positions.

In the detection phase, to apply the face detector to a test image 350, successive windows in the test image are processed 340 as follows: 6. The window is sampled regularly as a series of blocks, and attributes in respect of each block are calculated and quantised as in stages 1-4 above.

7. Corresponding "probabilities" for the quantised attribute values for each block position are looked up from the corresponding histograms. That is to say, for each block position, a respective quantised attribute is generated and is compared with a histogram previously generated in respect of that block position (or with multiple histograms in the case of multiple training sets representing different views). The way in which the histograms give rise to "probability" data will be described below.

8. All the probabilities obtained above are multiplied together to form a final probability which is compared against a threshold in order to classify the window as "face" or "nonface". It will be appreciated that the detection result of "face" or "nonface" is a probability-based measure rather than an absolute detection. Sometimes, an image not containing a face may be wrongly detected as "face", a so-called false positive. At other times, an image containing a face may be wrongly detected as "nonface", a so-called false negative. It is an aim of any face detection system to reduce the proportion of false positives and the proportion of false negatives, but it is of course understood that to reduce these proportions to zero is difficult, if not impossible, with current technology.

As mentioned above, in the training phase, a set of "nonface" images can be used to generate a corresponding set of "nonface" histograms. Then, to achieve detection of a face, the "probability" produced from the nonface histograms may be compared with a separate threshold, so that the probability has to be under the threshold for the test window to contain a face. Alternatively, the ratio of the face probability to the nonface probability could be compared with a threshold.

Extra training data may be generated by applying "synthetic variations" 330 to the lo original training set, such as variations in position, orientation, size, aspect ratio, background scenery, lighting intensity and frequency content.

Further improvements to the face detection arrangement will also be described below.

Face Tracking A face tracking algorithm will now be described. The tracking algorithm aims to improve face detection performance in image sequences.

The initial aim of the tracking algorithm is to detect every face in every frame of an image sequence. However, it is recognised that sometimes a face in the sequence may not be detected. In these circumstances, the tracking algorithm may assist in interpolating across the missing face detections.

Ultimately, the goal of face tracking is to be able to output some useful metadata from each set of frames belonging to the same scene in an image sequence. This might include: Number of faces.

"Mugshot" (a colloquial word for an image of a person's face, derived from a term referring to a police file photograph) of each face.

Frame number at which each face first appears.

Frame number at which each face last appears.

Identity of each face (either matched to faces seen in previous scenes, or matched to a face database) The tracking algorithm uses the results of the face detection algorithm, run independently on each frame of the image sequence, as its starting point. Because the face detection algorithm may sometimes miss (not detect) faces, some method of interpolating the missing faces is useful. To this end, a Kalman filter is used to predict the next position of the face and a skin colour matching algorithm was used to aid tracking of faces. In addition, because the face detection algorithm often gives rise to false acceptances, some method of rejecting these is also useful.

The algorithm is shown schematically in Figure 8.

In summary, input video data 545 (representing the image sequence) is supplied to a face detector of the type described in this application, and a skin colour matching detector 550. The face detector attempts to detect one or more faces in each image. When a face is detected, a Kalman filter 560 is established to track the position of that face. The Kalman lo filter generates a predicted position for the same face in the next image in the sequence. An eye position comparator 570, 580 detects whether the face detector 540 detects a face at that position (or within a certain threshold distance of that position) in the next image. If this is found to be the case, then that detected face position is used to update the Kalman filter and the process continues.

If a face is not detected at or near the predicted position, then a skin colour matching method 550 is used. This is a less precise face detection technique which is set up to have a lower threshold of acceptance than the face detector 540,so that it is possible for the skin colour matching technique to detect (what it considers to be) a face even when the face detector cannot make a positive detection at that position. If a "face" is detected by skin colour matching, its position is passed to the Kalman filter as an updated position and the process continues.

If no match is found by either the face detector 450 or the skin colour detector 550, then the predicted position is used to update the Kalman filter.

All of these results are subject to acceptance criteria (see below). So, for example, a face that is tracked throughout a sequence on the basis of one positive detection and the remainder as predictions, or the remainder as skin colour detections, will be rejected.

A separate Kalman filter is used to track each face in the tracking algorithm.

It is noted that the tracking process is not limited to tracking through a video sequence in a forward temporal direction. Assuming that the image data remain accessible (i.e. the process is not real-time, or the image data are buffered for temporary continued use), the entire tracking process could be carried out in a reverse temporal direction. Or, when a first face detection is made (often part-way through a video sequence) the tracking process could be initiated in both temporal directions. As a further option, the tracking process could be run in both temporal directions through a video sequence, with the results being combined so that (for example) a tracked face meeting the acceptance criteria is included as a valid result whichever direction the tracking took place.

Advantages of the tracking algorithm The face tracking technique has three main benefits: It allows missed faces to be filled in by using Kalman filtering and skin colour tracking in frames for which no face detection results are available. This increases the true acceptance rate across the image sequence.

It provides face linking: by successfully tracking a face, the algorithm automatically lO knows whether a face detected in a future frame belongs to the same person or a different person. Thus, scene metadata can easily be generated from this algorithm, comprising the number of faces in the scene, the frames for which they are present and providing a representative mugshot of each face.

False face detections tend to be rejected, as such detections tend not to carry forward between images.

Figures 9a to 9c schematically illustrate the use of face tracking when applied to a video scene.

In particular, Figure 9a schematically illustrates a video scene 800 comprising successive video images (e.g. fields or frames) 810.

In this example, the images 810 contain one or more faces. In particular all of the images 810 in the scene include a face A, shown at an upper left-hand position within the schematic representation of the image 810. Also, some of the images include a face B shown schematically at a lower right hand position within the schematic representations of the images 8 10.

A face tracking process is applied to the scene of Figure 9a. Face A is tracked reasonably successfully throughout the scene. In one image 820 the face is not tracked by a direct detection, but the skin colour matching techniques and the Kalman filtering techniques described above mean that the detection can be continuous either side of the "missing" image 820. The representation of Figure 9b indicates the detected probability of face A being present in each of the images, and Figure 9c shows the corresponding probability values for face B. To distinguish between the track for face A and the track for face B. unique (at least with respect to other tracks in the system) identification numbers are assigned to each track. ]1

In the system described above and in PCT/GB2003/005186, during face detection and tracking, a person's track is terminated if the face turns away from the camera for a prolonged period of time or disappears from the scene briefly. On returning to the scene, the face is detected again but a different track is started, and the new track is given a different s identification (ID) number.

So-called "face similarity" or "face matching" techniques will now be described.

The aim of face similarity is to recover the identity of the person in these situations, so that an earlier face track and a later face track (relating to the same person) may be linked together. In this arrangement, at least in principle, each person is assigned a unique ID 0 number. When the person returns to the scene, the algorithm attempts to reassign the same ID number by using face matching techniques.

The face similarity method is based on comparing several face "stamps" (images selected to be representative of that tracked face) of a newly encountered individual to several face stamps of previously encountered individuals. Note that face stamps need not be Is square. Several face stamps belonging to one individual are obtained from the face detection and tracking component of the system. As described above, the face tracking process temporally links detected faces, such that their identity is maintained throughout the sequence of video frames as long as the person does not disappear from the scene or turn away from the camera for too long. Thus the face detections within such a track are assumed to belong to the same person and face stamps within that track can be used as a face stamp "set" for one particular individual.

A fixed number of face stamps is kept in each face stamp set. The way in which face stamps are selected from a track is described below. Then, a "similarity measure" of two face stamp sets will be described. There will then follow a description of how the similarity 2s method is used within the face detection and tracking system. But first, Figure 10 will be described, in order to place the face similarity techniques into the context of the overall tracking system.

Figure 10 schematically illustrates a face detection and tracking system, as described above, but placing the face similarity functionality into a technical context. This diagram summarises the process described above and in PCT/GB2003/005186.

At a first stage 2300, so-called "area of interest" logic derives thoseareas within an image at which face detection is to take place. At those areas of interest, face detection 2310 is carried out to generate detected face positions. Then face tracking 2320 is carried out to generate tracked face positions and IDs. Finally, the face similarity function 2330 is used to match face stamp sets.

Selection of stamps for the face stamp set In order to create and maintain a face stamp set, a fixed number (n) of stamps is selected from a temporally linked track of face stamps. The criteria for selection are as follows: 1. The stamp has to have been generated directly from face detection, not from colour tracking or Kalman tracking. In addition, it is only selected if it was detected using histogram lo data generated from a "frontal view" face training set.

2. Once the first n stamps have been gathered (by following, for example, a forward temporal order through the images constituting the face track), the similarity (see below) of each new stamp available from the track (in the temporal order) with the existing face stamp set is measured. The similarity of each face stamp in the track with the remaining stamps in the stamp set is also measured and stored. If the newly available face stamp is less similar to the face stamp set than an existing element of the face stamp set is to the face stamp set, that existing element is disregarded and the new face stamp is included in the face stamp set.

Stamps are chosen in this way so that, by the end of the selection process, the largest amount of variation available is incorporated within the face stamp set. This tends to make the face stamp set more representative for the particular individual.

If fewer than n stamps are gathered for one face stamp set, this face stamp set is not used for similarity assessment as it probably does not contain much variation and is therefore not likely to be a good representation of the individual.

This technique has applications not only in the face similarity algorithm, but also in selecting a set of representative pictures stamps of any object for any application.

A good example is in so-called face logging. There may be a requirement to represent a person who has been detected and logged walking past a camera. A good way to do this is to use several pictures stamps. Ideally, these pictures stamps should be as different from each other as possible, such that as much variation as possible is captured. This would give a human user or automatic face recognition algorithm as much chance as possible of recognising the person.

Similarity measure In comparing two face tracks, to detect whether they represent the same individual, a measure of similarity between the face stamp set of a newly encountered individual (setB) and that of a previously encountered individual (sets) is based on how well the stamps in s face stamp setB can be reconstructed from face stamp sets. If the face stamps in setB can be reconstructed well from face stamps in sets, then it is considered highly likely that the face stamps from both setA and setB belong to the same individual and thus it can be said that the newly encountered person has been detected before.

The same technique is applied to the arrangement described above, namely the selection of face images for use as a face stamp set representing a particular face track. In that case, the similarity between each newly encountered candidate face stamp and the existing stamps in the set, and the mutual similarity between stamps within the existing set, would be considered in the same way as a the similarity between a stamp from setB and

stamps from setA in the description that follows.

A stamp in face stamp setB is reconstructed from stamps in setA in a block-based fashion. This process is illustrated schematically in Figure 11.

Figure 11 schematically shows a face stamp setA having four face stamps 2000, 2010, 2020, 2030. (Of course it will be understood that the number four is chosen merely for clarity of the diagram, and that the skilled person could select a different number for an actual implementation). A stamp 2040 from face stamp setB is to be compared with the four stamps of sets.

Each non-overlapping block 2050 in the face stamp 2040 is replaced with a block chosen from a stamp in face stamp sets. The block can be chosen from any stamp in setA and from any position in the stamp within a neighbourhood or search window 2100 of the original block position. The block within these positions which gives the smallest mean squared error (MSE) is chosen to replace the block being reconstructed by using a motion estimation method. (A good motion estimation technique to use is one which gives the lowest mean squared error in the presence of lighting variations while using a small amount of processing power). Note that the blocks need not be square. In the example shown, a block 2060 is replaced by a nearby block from the stamp 2000; a block 2070 by a block from the face stamp 2010; and a block 2080 by a block from the face stamp 2020, and so on.

When a face stamp is being reconstructed, each block can be replaced by a block from a corresponding neighbourhood in the reference face stamp. But optionally, in addition to this neighbourhood, the best block can also be chosen from a corresponding neighbourhood in the reheeled reference face stamp. This can be done because faces are roughly symmetrical. In this way, more variation present in the face stamp set can be utilised.

Each face stamp used is of size 64x64 and is divided into blocks of size 8x8. The face stamps used for the similarity measurement are more tightly cropped than the ones output by the face detection component of the system. This is in order to exclude as much of the background as possible from the similarity measurement.

To crop the image, a reduced size is selected (or predetermined) - for example 50 pixels high by 45 pixels wide (allowing for the fact that most faces are not square). The lo group of pixels corresponding to a central area of this size are then resized so that the selected area fills the 64x64 block once again. This involves some straightforward interpolation. The resizing of a central non-square area to fill a square block means that the resized face can look a little stretched.

The choice of a cropping area (e.g. a 50 x 45 pixel area) can be predetermined or can be selected in response to attributes of the detected face in each instance. Resizing in each case to the 64x64 block means that comparisons of face stamps - whether cropped or not - take place at the same 64x64 size.

Once the whole stamp is reconstructed in this way, the mean squared error between the reconstructed stamp and the stamp from setB is calculated. The lower the mean squared error, the higher the amount of similarity between the face stamp and face stamp sets.

In the case of a comparison between two face stamp set, each stamp in face stamp setB is reconstructed in the same way and the combined mean squared error is used as the similarity measure between the two face stamp sets.

Thus the algorithm makes full use of the fact that several face stamps are available for each person to be matched. Furthermore the algorithm is robust to imprecise registration of faces to be matched.

In the system described above, newly gathered face stamp sets are reconstructed from existing face stamp sets in order to generate a similarity measure. The similarity measure obtained by reconstructing a face stamp set from another face stamp set (A from B) is usually different from when the latter face stamp set is reconstructed from the former one (B from A). Thus, in some cases, an existing face stamp set could give a better similarity measure when reconstructed from a new face stamp set than vice versa, for example if the existing face stamp set were gathered from a very short track. Therefore in order to increase the likelihood of successful merges between similar faces, the two similarity measures can be combined (e.g. averaged).

A further optional variation will now be described. When a face stamp is being reconstructed, each block is replaced by a block of the same size, shape and orientation from s the reference face stamp. But if the size and orientation of a subject are different in the two face stamps, these face stamps will not be well reconstructed from each other as blocks in the face stamp being reconstructed will not match well with blocks of the same size, shape and orientation. This problem can be overcome by allowing blocks in the reference face stamp to take any size, shape and orientation. The best block is thus chosen from the reference face lo stamp by using a high order geometric transformation estimation (e.g. rotation, zoom, amongst others). Alternatively the whole reference face stamp can be rotated and resized prior to reconstructing the face stamp by the basic method.

In order to make the similarity measure slightly more robust to lighting variations, each face stamp is first normalised to have a mean luminance of zero and a variance of one.

Use of face similarity component within the object tracking system It has been seen that object tracking allows a person's identity to be maintained throughout a sequence of video frames as long as he/she does not disappear from the scene.

The aim of the face similarity component is to be able to link tracks such that the person's identity is maintained even if he/she temporarily disappears from the scene or turns away from the camera.

During the operation of the face detection and object tracking system, a new face stamp set is initiated each time a new track is started. The new face stamp set is initially given a unique (i.e. new compared to previously tracked sets) ID. As each stamp of the new 2s face stamp set is acquired, its similarity measure (S') with all the previously gathered face stamp sets is calculated. This similarity measure is used to update the combined similarity measure (S,-1) of the existing elements of the new face stamp set with all the previously gathered face stamp sets in an iterative manner: USE = 0.9 *S,-1 + O.l *IS, where the superscript j denotes comparison with the previously gathered face stamp set j.

If the similarity of the new face stamp set to a previously encountered face stamp set is above a certain threshold (T) and the number of elements in the new face stamp set is at least n (see above), then the new face stamp set is given the same ID as the previous face stamp set. The two face stamp sets are then merged to produce just one face stamp set containing as much of the variation contained in the two sets as possible by using the same similarity-comparison method as described in the above section.

The new face stamp set is discarded if its track terminates before n face stamps are gathered.

If the similarity measure of the new face stamp set is above the threshold T for more than one stored face stamp set, this means that the current person appears to be a good match to two previous people. In this case an even more severe similarity threshold (i.e. an even lower difference threshold) is required to match the current person to either of the two previous persons.

lo In addition to the similarity criterion, another criterion can help in deciding whether two face stamp sets should be merged or not. This criterion comes from the knowledge that two face stamps sets belonging to the same individual cannot overlap in time. Thus two face stamp sets which have appeared in the picture at the same time for more than a small number of frames can never be matched to each other. This is done by keeping a record of all the face stamp sets which have ever co-existed in the picture, using a co-existence matrix. The matrix stores the number of frames for which every combination of two face stamp sets have ever coexisted. If this number is greater than a small number of frames, e.g. 10 frames (to allow for the period during which a track can sometimes float off a face for a few frames prior to being deleted), then it is not permitted to merge the two face stamp sets into the same ID. An example of a coexistence matrix for five people (tracks) numbered ID 1 to ID 5 will now be given: track TD

_

1 234 0 0 87 5 2 0 54 22 0 0 3 0 22 43 0 0 cd 4 87 0 0 102 5 The matrix shows that: ID 1 has appeared for a total of 234 frames (though these may not have been contiguous). It has never appeared in shot at the same time as IDs 2 or 3, and therefore it could potentially be merged with one of these people in future. It has co existed with ID 4 for 87 frames and so should never be merged with this person. It lo has also co-existed for 5 frames with ID 5. This is less than the threshold number of frames and so these two IDs can still potentially be merged together.

ID 2 has appeared for a total of 54 frames (though these may not have been contiguous). It has only ever co-existed with ID 3, and so may not ever be merged with this person. However, it can potentially be merged with IDs 1,4 or 5 in future, should the faces have a good match.

ID 3 has appeared for a total of 43 frames (though these may not have been contiguous). It has only ever co-existed with ID 2, and so may not ever be merged with this person. However, it can potentially be merged with IDs 1,4 or 5 in future, should the faces have a good match.

ID 4 has appeared for a total of 102 frames (though these may not have been contiguous). It has never appeared in shot at the same time as IDs 2 or 3, therefore it could potentially be merged with one of these people in future. It has co-existed with ID 1 for 87 frames and so should never be merged with this person. It has also co existed for 5 frames with face 5. This is less than the threshold number of frames and so these two IDs can still potentially be merged together.

ID 5 has appeared for a total of just 5 frames (though these may not have been lo contiguous). It has co-existed with IDs 1 and 4 for all these frames, but may still be merged with either of them because this is less than the threshold. It may also be merged with IDs 2 or 3, since it has never co-existed with these IDs.

If two IDs are merged due to high face similarity, the co-existence matrix is updated by combining the co-existence information for the two merged IDs. This is done by simply summing the quantities in the rows corresponding to the two IDs, followed by summing the quantities in the columns corresponding to the two IDs.

e.g. if ID 5 were merged with ID 1, the co-existence matrix above would become: 1239 0 092 54 220 22 430 492 0 0102 If ID I were subsequently merged with ID 2, the co-existence matrix above would become: 1 293 22 92 3 22 43 0 4 92 0 102 It should be noted that: ID 1 cannot no be merged with any further existing people.

A convention is used in this embodiment whereby the lowest ID number is always retained after two IDs have been merged.

IDs are not permitted to be merged while they are both still present in the picture.

lo In the similarity detection process for generating and for merging face stamp sets, a face stamp typically needs to be reconstructed several times from other face stamps. This means that each block needs to be matched several times using a motion estimation method.

For some motion estimation methods, the first step is to compute some information about the block that needs to be matched, irrespective of the reference face stamp used. As the motion IS estimation needs to be carried out several times, this information can be stored alongside the face stamp, so that it doesn't need to be calculated each time a block has to be matched, thus saving processing time.

The following description relates to improvements to the face detection and object tracking technology with the aim of improving performance on images acquired under unusual (or at least less usual) lighting conditions.

Methods to improve robustness to lighting variations The methods used to improve robustness to lighting variations include: (a) additional training using extra samples containing a large range of lighting variations; (b) contrast adjustment to reduce the effect of sharp shadows.

A further enhancement, normalization of histograms, helps in improving face detection performance as the need for tuning one parameter of the face detection system is removed.

The test sets for these experiments contain images acquired under unusual lighting conditions. The first set is labelled as "smaller training set" (curve --a--) in Figure 12, and contains a mixture of frontal faces (20%), faces looking to the left (20%), faces looking to the right (20%), faces looking upwards (20%) and faces looking downwards (20%). The performance of the face detection system on this test set is shown before and after these improvements in Figure 12. The second test set contains sample images captured around the lo office. Sample results are shown in Figures 13a and 13b and are described below.

Additional data in the histogram training set In order to cope with different lighting conditions, extra face samples can be added to the training set. These face samples preferably contain more lighting variation than the face samples in the training set originally used. As can be seen from Figure 12, the enlarged ("Combined") training set (curve -- --) resulted in a slight improvement compared to the use of the smaller training set only (red curve).

Normalisation of histograms It was previously found that an appropriate threshold for detection using the histogram for the frontal pose was slightly lower than when using the histograms for the off frontal poses. Because of this a bias had to be added to the probability maps for the frontal pose prior to combining the probability maps from each pose. This frontal bias had to be experimentally determined whenever changes were made to the histogram training component of the face detection system.

However this bias can instead be included within the histogram training component such that similar thresholds can be used for detection on both frontal and off-frontal probability maps. Thus the frontal and offfrontal histograms can be said to be normalised with respect to one another. Referring to Figure 12, the "smaller" and "combined" curves in the graph have been generated before the experimental determination of an appropriate frontal bias. The curve ----- was generated using norrnalised histograms and demonstrates that a better performance can be achieved than when a non-optimal bias is used.

Contrast adjustment It has been observed that faces on which sharp shadows were present were less likely to be successfully detected. Therefore a pre-processing operator was devised to try and diminish the effect of shadows. It works by centring a window (smaller than the whole image under test) around each pixel in the input image and averaging the pixel value in the centre of the window with the minimum pixel intensity value within the window. Thus the value of every pixel in the output image (Iou,pu,) is given by Ioupu(x) = (If) + min(W)) / 2, where W is a window centred over pixel x.

in The size of the neighbourhood window used in this embodiment is 7x7 pixels. Face detection is then carried out as usual on the processed image. The improvement obtained is shown as the curve --a-- in Figure 12. It can be seen that this novel operator has had a significant impact on the performance of the face detection system. (It is noted that a similar arrangement where the "window" comprised the whole image was tested and found not to provide this advantageous effect.

This technique is particularly useful where objects such as faces have to be detected in harsh lighting environments such as in a shop, and can therefore have application in so- called "digital signage" where faces are detected of persons viewing a video screen showing advertising material. The presence of a face, the length of time the face remains, and/or the number of faces can be used to alter the material being displayed on the advertising screen.

Sample images The performance of the face detection system before and after the suggested improvements on a few sample images is shown in Figures 13a and 13b. lithe images on the left and right hand sides show the result of face detection before and after the improvements respectively. As can be seen, both frontal and off-frontal faces under harsh lighting can now be successfully detected.

References H. Schneiderrnan and T. Kanade, "A statistical model for 3D object detection applied to faces and cars," IEEE Conference on Computer Vision and Pattern Recognition, 2000.

H. Schneiderman and T. Kanade, "Probabilistic modelling of local appearance and spatial relationships for object recognition," IEEE Conference on Computer Vision and Pattern Recognition, 1998.

to H. Schneiderman, "A statistical approach to 3D object detection applied to faces and cars," PhD thesis, Robotics Institute, Carnegie Mellon University, 2000.

Claims (22)

1. An image processing method for processing an input image comprising plural image elements to generate an output image, the method comprising the steps of, for each image element in at least a portion of the input image: detecting an image property of image elements in a test region surrounding that image element, the test region representing a subset of the input image; and modifying the image element in dependence on the detected image property, to lo generate a corresponding image element of the output image.

2. A method according to claim 1, in which the image property is an image element luminance.

3. A method according to claim 2, in which the image element is modified so as to cause the image element's luminance to be closer to a minimum image element luminance across the test region.

4. A method according to claim 3, in which the image element's luminance is averaged with the minimum image element luminance across the test region.

5. A method according to any one of the preceding claims, in which the test region is a region surrounding the image element under consideration.

2s

6. A method according to claim 5, in which the test region comprises an array of image elements substantially centred around the image element under consideration.

7. A method according to claim 6, in which the array is a square array.

8. A method according to any one of the preceding claims, in which the image elements are pixels.

9. A method according to any one of the preceding claims, comprising the step of: performing object detection on the output image.

10. A method according to claim 9, in which the objects are faces.

11. A method according to any one of the preceding claims, in which the input image is an image from a video sequence.

12. An image processing method substantially as hereinbefore described with reference to the accompanying drawings.

lo

13. Computer software having program code for carrying out a method according to any one of the preceding claims.

14. A providing medium for providing program code according to claim 13.

15. A medium according to claim 14, the medium being a storage medium.

16. A medium according to claim 14, the medium being a transmission medium

17. Image processing apparatus for processing an input image comprising plural image elements to generate an output image, the apparatus comprising: means, operable in respect of each image element in at least a portion of the input image, to detect an image property of image elements in a test region surrounding that image element, the test region representing a subset of the input image, and to modify the image element in dependence on the detected image property, to generate a corresponding image element of the output image.

18. Image processing apparatus substantially as hereinbefore described with reference to the accompanying drawings.

19. Video conferencing apparatus comprising apparatus according to claim 17 or claim 18.

20. Surveillance apparatus comprising apparatus according to claim 17 or claim 18.

21. A camera arrangement comprising apparatus according to claim 17 or claim 18.

22. A digital signage arrangement comprising apparatus according to claim 17 or claim 18.