WO2003081533A2

WO2003081533A2 - Classifying pixels as natural or synthetic image content

Info

Publication number: WO2003081533A2
Application number: PCT/IB2003/001100
Authority: WO
Inventors: Matteo Marconi; Andrea Rizzi; Mario Trevisan
Original assignee: Koninklijke Philips Electronics N.V.
Priority date: 2002-03-26
Filing date: 2003-03-12
Publication date: 2003-10-02
Also published as: CN1656516A; EP1490834A2; WO2003081533A3; JP2005521169A; AU2003212574A8; AU2003212574A1; TW200404268A

Abstract

Method of analyzing an image composed of a matrix of pixels, each pixel being defined by at least one parameter value arranged in a parameter matrix (Y). The method comprises the steps of performing a differentiation operation on the parameter matrix (Y) resulting in a plurality of differentiation entries (D) arranged in a matrix. Sets of neighboring differentiation entries having nearly the same differentiation entry are determined. A path length is determined for the pixels in each set, indicating a number of entries in that set. Based on the path length and differentiation entry, a pixel is classified as natural or synthetic image content.

Description

Analyzing an image composed of a matrix of pixels

The invention relates to a method of analyzing an image. The invention also relates to a computer program product, an apparatus, a processor device system and a computer-readable medium.

CRT/LCD monitors, i.e. monitors applicable for computers and computer systems are characterized by a high resolution and a low brightness. These display systems, hereinafter termed as monitors, are typically used to display synthetic contents, e. g. text or graphics. They are currently more and more in demand for displaying natural contents, e. g. images or video. In particular, compared to TN-monitors, CRT-monitors are characterized by a high resolution and by a lower brightness. This is due to the fact that originally the content displayed on monitors, e. g. monitors for computers etc., was exclusively synthetic and, in particular, was essentially represented by text. This type of content clearly needs a high resolution to be enjoyable to the user but this also causes a decrease of brightness, for example due to a required small spot size of the electron beam in a CRT.

Synthetic content is hereinafter to be understood as a content of an image which, compared to a natural content, has a somewhat higher degree of order due to its synthetic origin. Besides the above-mentioned example of a text as a synthetic content, icons, symbols and any kind of a somewhat constructed form, graphics or pictures have to be understood as a synthetic content. In contrast, a natural content is hereinafter to be understood as any image of a natural origin, in particular not a constructed origin like digitized photos, video clips and similar images, which are part of an arbitrary input composite raster image.

Today's situation has changed considerably: Internet and multimedia technologies (like DVD and image storage and transmission) have caused an increase of natural TV-like contents in monitor applications. This new situation causes a series of problems for monitors because they were originally not designed for displaying synthetic as well as natural contents. In particular, this problem is faced by any monitor for PC applications, in particular CRT- and LCD-monitors and flat monitors. Furthermore, such a problem is faced as well by any related processor device system like video cards, video chips, multimedia chips, processor units, frame buffers and VRAM -memories, which are adapted to process images comprising synthetic as well as natural contents.

Images comprising synthetic and natural contents are referred to as having a composite content. Currently common display devices, in particular monitor devices, devices and processor device systems are required to perform image processing with a high resolution and a negligible loss of brightness and also with an acceptable processing performance and time for images of composite content.

There are already enhancement solutions that can significantly improve performances, in particular visual performances. To effectively enhance the performance of image processing, such processing may be applied and restricted to specific areas of a display system, e. g. of a screen, in which natural contents are present. Such a "window-based" manual selection made by the user is a simple though ineffective method to identify areas, which can be adopted when the whole window content is a natural one.

Detection schemes for image detection based on fuzzy detection rules as described in US 6,195,459 Bl may be applicable, but may have a lack of reliability.

Unfortunately, the same approach cannot be used for composite contents within the same window as is typical of web pages, because application of enhancement techniques for pure text or graphics may cause a significant loss of their perceived visual quality. Video enhancement algorithms applied in order to obtain a significant improvement of the quality of natural images displayed on monitors, however, are detrimental when applied to pure texts or graphics. Therefore, the result of such algorithms applied is always insufficient.

Consequently, the ability of reliably distinguishing between natural and synthetic content for any kind of image of composite content becomes important.

It is an object of the invention to provide an improved method of analyzing an image, i.e. in particular for detecting which areas of the image contain a natural image content and which areas contain a synthetic image content of a digital image of composite content. Furthermore, it is an object of the invention to provide a computer program product, an apparatus, a processor device system and a computer-readable medium with which such a method can be performed.

The invention is defined by the independent claims. The dependent claims define advantageous embodiments. The basic advantage of the invention is that the method according to the invention makes it possible to automatically adapt image processing to the image content that is displayed or processed at a particular moment. The basic idea is that the natural image content can be distinguished from the synthetic image content. The distinction is performed in accordance with the basic idea of the invention by means of a mix of local image information and global image information. Global information is information about the sets like the path length. Local information is provided by the differentiation entries for each pixel.

Other applications that could benefit from this kind of distinction are image compression techniques, which could use separate encoding schemes for natural and synthetic image content, respectively. In particular, this concerns image compression techniques for e.g. encoding video images and text/graphics.

The proposed method as described above can be substantially divided into three steps each comprising a surprising perception.

In a first step, the method processes one or more relevant parameter values of the pixels. Furthermore, local image information is given by a differentiation of the parameter matrix, while global image information is given by sets of neighboring pixels having the same differentiation entry.

Regarding the second step, thorough experimental observations have shown that the probability of finding long paths is very low for natural image contents. The probability decreases with the increase of a differentiation entry. On the contrary, this probability is higher in synthetic image contents. The concept is to use this characteristic to distinguish a natural image content, on the one hand, and a synthetic image content, on the other hand, in composite image contents. In particular, regarding composite image contents, this perception can be explained by observing that natural image contents are more "fragmented" than synthetic image contents so that it is more difficult that path lengths of natural image contents become very long. With regard to a comparison of natural image contents and synthetic image contents in general, it is therefore more unlikely that paths of a natural image content become very long. As a consequence, the third step of the method performs a threshold operation using a threshold function T(D). The length of each set is computed: if a combination of the path length and differentiation entry exceeds the threshold, all the pixels belonging to the set are considered as synthetic and the set is labeled as belonging to synthetic image content. Otherwise, the pixels are considered as natural and the set is labeled as belonging to natural image content.

Regarding gradient values, the threshold for natural image contents is higher because natural images are generally characterized by lower gradients between pixels so that long sets are more probable. With regard to a comparison of lower gradients and higher gradients, long sets are therefore more probable for natural image contents in the case of lower gradients. On the contrary, the threshold has to be lower with high gradient values because they are typical of synthetic images.

The proposed method provides an improved quality of distinguishing natural image content from synthetic image content comprised in an image of composite content. In an advantageous configuration, a pixel is classified as background image content, if the differentiation entry for that pixel in the differentiation entries D is not more than a minimum entry value. The improvement arises from the perception that pixels with a low value are considered separately because they represent backgrounds and could belong either to synthetic image contents or to natural image contents. Thus, all sets with a value not more than the minimum entry value are labeled as belonging to background image contents, irrespective of the path length.

A further improved configuration is achieved if the predetermined maximum difference value is zero. This configuration reduces processing times.

It is also advantageous if the at least one parameter value corresponds to a luminance of the pixels. The luminance is a relevant parameter for analyzing the image, because it contains the major part of the image energy and of the information about shapes, in other words, what is needed for content detection.

It is a further advantage if the differentiation entry for a pixel is determined by selecting a maximum value of two gradients: - a first gradient of the luminance as a function of a location of the pixel in the matrix in a first direction along a row of pixels in the matrix, and - a second gradient of the luminance as a function of the location in the matrix in a second direction along another row of pixels in the matrix perpendicular to the first direction. The first and second gradients may be the positive or negative value of the gradients or the absolute value of the gradients.

It is a further advantage if the minimum entry value is zero. It has been found to be a suitable value for classifying a pixel as background image content. In a further advantageous configuration, pixels in a background set having pixels classified as background image content are classified as natural image content, if

- the background set has less than a predetermined number of neighboring sets having pixels classified as synthetic image content, and

- the background set has a minimum number of adjacent sets having pixels classified as natural image content, and are otherwise classified as synthetic image content.

The pixels labeled as background image content are converted either to be synthetic image content or natural image content by performing a relationship analysis of the pixels labeled as background image content. This may be performed by analyzing the surrounding image contents of the background image content.

A further improvement is achieved if those pixels in a set classified as natural image content are classified as synthetic image content if the neighboring sets have pixels classified as synthetic image content, and the path length of the set is below a threshold length. It is important that this last-mentioned improvement step is executed after the previously mentioned steps to improve correct detection of the image content.

In a further advantageous configuration, the method may be complemented by a third part. In the third part, irregularities within areas with mainly pixels labeled as natural image content are corrected. In particular, a series of adjacent pixels classified as synthetic image content are classified as natural image content if a length of the series is below a maximum length.

A further advantageous configuration provides that in areas of the image having pixels classified as natural image content: a saturation parameter value is checked for each pixel, and - if a percentage of pixels having a saturation parameter value higher than a saturation threshold value exceeds a threshold percentage, the pixels in that area are classified as synthetic image content.

It is finally also an advantage if - absolute values d of differentiation entries of pixels in an area of the image classified as natural image content are generated,

- a histogram H(d) is generated having a range of absolute values d between zero and a maximum range value, - containing a count of a number of pixels in that area having the same absolute value d as a function of the range of absolute values d having peaks at an absolute value d if - adjacent histogram values H(d-l), H(d+1) are smaller than H(d), and

H(d) is the highest value in a range of absolute values d between the absolute value d and the maximum range value, and

- the pixels in that area are classified as synthetic image content if: a lowest value of absolute values d for which H(d) has a peak exceeds a first threshold distance, or a difference between absolute values (d) belonging to two adjacent peaks of the histogram H(d) exceeds a second threshold distance.

The histogram of the absolute values of the differentiation entries is used to verify whether areas of the image classified as natural image content are really natural.

The object regarding the computer program product is solved according to the invention by a computer program product executing the method as proposed, when executed on a computer.

In particular, an improvement of the computer program product provides the following pseudo-code on threshold utilization:

V pixel in position (i,j) calculateD (i, j) (gradient value) calculateP (i, j) (path length) calculateT (D (i, j)) (threshold function, taken from a look up table) if D(i, j) = o then S(i, j) is labeled as BACK else fif P(i, j)≥T(D(i, j))then S(i, j) is labeled as SYNT

{ ifP(i,j)<T(D(i,j))thenS(i,j)islabeledasNAT

The labels i and j are used to label the entries of the respective matrix, S(i,j) is a semantic matrix containing the image content (natural, synthetic or background) for each pixel.

The problem regarding the apparatus is solved according to the invention by an apparatus comprising circuitry and/or computer programs for analyzing an image composed of a matrix of pixels, each pixel being defined by at least one parameter value, the values of the at least one parameter value for each pixel being arranged in a parameter matrix (Y), the apparatus comprising processing circuitry for carrying out the method of claim 1 as described before. The apparatus may be a computer, a display device, monitor, a television or any other product comprising a display device or having processing circuitry for processing images.

The object regarding the processor device system and/or computer-readable medium is solved by a processor device system and/or a computer readable medium having a computer program product loaded for executing the method as proposed.

These and other aspects of the cabinet and the apparatus of the invention will be further elucidated and described with reference to the drawings, in which: Fig. 1 is a flow chart illustrating a first embodiment of the method;

Fig. 2 shows a threshold function used in the first embodiment;

Fig. 3 is a flow chart illustrating a second embodiment complementing the first embodiment.

Fig. 1 depicts in three steps the main features regarding the proposed method of analyzing an image.

The symbols used in Fig. 1 are:

Y the parameter matrix comprising parameter values of a matrix of pixels composing the image,

D the gradient matrix containing the differentiation entries of the parameter values,

P the path matrix. It contains the path length for each pixel.

S the semantic matrix. For each pixel it contains one of the three labels NAT, SYNT or BACK as will be described below.

An image is composed of a matrix of pixels. Each pixel is defined by at least one parameter value. The parameter values of the matrix of pixels are arranged in a parameter matrix Y. The parameter values are usually available in a digital form. It is advantageous if the luminance is used as a parameter. In a first step, a gradient operation 1 is performed on the luminance parameter values of matrix Y and the gradient is provided by a multitude of differentiation entries arranged in a differentiation matrix D.

In a second step, sets of neighboring differentiation entries are identified which mutually deviate by not more than a predetermined maximum difference value. For each set, a path length is determined by a path finder 2 indicating the number of entries in the set.

An alternative which simplifies the necessary calculations is to render the predetermined maximum difference value equal to zero.

In a third step, a threshold check 3 is performed by checking for each pixel whether a combination of a differentiation entry and the path length of that pixel exceeds a predetermined threshold function T(D).

By comparing, for each set, the variables of path length and differentiation entry with the threshold function T(D), the pixels related to the set are classified as synthetic image content SYNT if the variables exceed the threshold function T(D) and are classified as natural image contents NAT if the variables remain below the threshold function T(D).

Fig. 2 depicts a preferred threshold function T(D) as used in an advantageous embodiment. The threshold function is given as function of an absolute value d of a differentiation entry. In natural images, lower gradients between pixels are generally more probable, resulting, statistically seen, in longer path lengths for low gradients. This results in a preferred threshold function T(D) as shown in Fig. 2, wherein the threshold function T(D) decreases when the absolute value of the differentiation entry d increases. In a comparison step in Fig. 1, the differentiation entries are compared with a minimum entry value.

Pixels having differentiation entries below or equal to the minimum entry value are classified as background image content BACK. As pixels classified as background image content BACK may belong to synthetic image content SYNT as well as to natural image content NAT, further processing is required as will be shown hereinafter.

It is advantageous if the minimum entry value is zero. As a result of the steps described so far, the semantic matrix S can be composed, containing one of the labels NAT, SYNT or BACK for each pixel. With regard to the gradient operation, many operators may be suitable to perform this task, but it has been found after experimental tests that results do not differ significantly by using different gradient operators. Therefore it is advantageous to use the simplest norm from a computational point of view, i.e. the max-norm:

where D(i, j) denotes the matrix D with the plurality of the differentiation entries labeled i in

the row direction and labeled j in the column direction, and where — , — denote

the partial differentiation of the matrix Y with respect to the entries in the row direction and the column direction, respectively.

In particular, a formula according to

D(i, j) = max , { \Y(i, j) - Y(i - 1, j)\, \Y(i, j) - Y(i, j - 1)| }

may be provided. In general, any kind of gradient operation is suitable like:

D(i, j) = I (Y(i, j) - Y(i - 1, j)), (Y(i, j) - Y(i, j - 1)) 1 „

= {¥ (i , j) - Y(i - 1, j)) ^N +(Y(i, j) ^~ Y(i, j - 1)) " ,

wherein N is an integer.

When N = 2, this results in the usual Euclidean norm:

D(i, j) = t](Y(i, j) - Y(i - 1, j))² + (Y(i, j) - Y(i, j - 1))²

When N = ∞, this results in the max-norm as used in an advantageous embodiment. For each pixel, a differentiation entry may be stored in an extra memory.

However, in a preferred embodiment, the extra memory for storing the matrix of differentiation entries D is not necessary. The matrix Y may be stored in a frame memory. For each pixel for which the differentiation entry has been calculated, one may store this differentiation entry in the same frame memory in which the corresponding parameter value was stored, because this parameter value is never used any more in the subsequent steps of the method. To do this, one may need only an extra line memory.

As a result of part 1 of the method, one of the three possible labels NAT, SYNT or BACK has been assigned to each pixel. Sets having pixels classified as background image content BACK values are to be processed further as shown in the flow chart of Fig. 3. These sets are uniform areas of the image. Usually, a uniform area represents the background of an image and for this reason it may belong both to a natural content or/and to a synthetic content of an image. For example, white areas of a landscape sky may appear uniform after quantization due to JPEG- compression and in the same way a text of a diagram has a uniform background. The processing of the sets in uniform areas is performed in two steps: a back path processing step 4, followed by a short-NAT-Paths processing step 5.

Two distinctive properties have been identified which have to be verified for a uniform area that belongs to a natural image: 1. The area of the image surrounding a uniform area should not include (or should include only a little number of) text characters or graphic parts, in other words, it should not contain too many sets with pixels classified as SYNT. 2. The uniform area must be at least partially adjacent to sets having pixels classified as NAT. Otherwise, there is no reason for considering them as part of a video image. Two properties are verified in the back path processing step 4 by analyzing the semantic matrix S. If a set with pixels classified as BACK with these properties is found, the pixels in that set are converted to NAT, otherwise they are converted to SYNT. As a result of the back path processing step 4, an adapted semantic matrix S 1 is generated, containing pixels classified as NAT or SYNT. In an advantageous embodiment, the above two properties are used to classify pixels in a background set having pixels classified as background image content BACK. The pixels in the background set are classified as natural image content if the following two properties are met:

1. the background set has less than a predetermined number of neighboring sets having pixels classified as synthetic image content SYNT, and

2. the background set has a minimum number of adjacent sets having pixels classified as natural image content NAT.

In all other cases, the pixels in the background set are classified as synthetic image content SYNT. The result of the operation mentioned above is the adapted semantic matrix SI, containing pixels classified as NAT or SYNT.

When the backgrounds are correctly classified, a preferred embodiment continues to convert, in the short NAT-path processing step 5, sets classified as NAT which are both isolated and too short to be considered as natural image content. These sets may be called short-NAT-paths and are considered as spurious paths, because they often result from little icons or from parts of synthetic images compressed with JPEG. In the short-NAT-path processing step 5, the pixels in a short NAT path are converted to SYNT. The result of the short NAT-path processing is stored in a second adapted semantic matrix S2. It is important to note that the order of the last two steps should not be inverted.

In fact, it often happens that a little part of a natural image is isolated from the rest of the image by the background. These kinds of paths may be called true short-NAT- paths because they are paths classified by a preferred embodiment as belonging to natural images, which are too short but are not false detections like the biggest part of the short- NAT-paths. If a preferred embodiment processes short-NAT-paths before BACK- parts, all the short-NAT-paths are converted to SYNT; therefore it could happen that some true short- NAT-paths, which are subsets of short-NAT-paths, are converted to SYNT, too. This would lead to a decrease of the detection performances. Thus, maintaining the right described order of the steps avoids the undesired effect.

As shown in Fig. 3 after the BACK path processing step 4 and short-NAT- paths processing step 5, the algorithm produces, as output, the second adapted semantic matrix S2 that contains only two kinds of labels: NAT and SYNT. Each pixel is classified with one of these two labels. The sets of pixels labeled NAT represent an output mask. Such a mask often contains some irregularities both within it and on the boundaries. Therefore, an irregularity reduction operation step 6 is applied in an advantageous embodiment in order to reduce these irregularities.

The second adapted semantic matrix is scanned both in row and in column direction. In doing so, it is possible to characterize the following two situations: the "mask to no-mask"-transition and the opposite "no-mask to mask"-transition. The first term refers to a situation in which the algorithm first encounters a pixel belonging to the mask and afterwards encounters a pixel that does not belong to it. The second term refers to the opposite situation. When a "mask to no-mask"-transition is found in a line, a counter is increased until an opposite transition occurs, or the line is complete. Then the counter is evaluated; if its value is below a certain threshold, all the pixels from the last "mask to no-mask"-event are converted into pixels belonging to the mask.

In other words, series of adjacent pixels classified as synthetic image contents SYNT are classified as natural image content NAT if a length of the series is below a maximum length.

This kind of processing eliminates the biggest part of mask irregularities.

Finally two tests Tl, T2 are performed at the end of the processing with the objective of increasing the level of confidence of the detection of natural areas.

A first test Tl as shown in Fig. 3 is performed on a color saturation parameter of the pixels in the mask. Saturation values Sv of the saturation parameter are evaluated pixel by pixel in areas classified as natural.

The saturation value Sv for each pixel can be derived from RGB color components of that pixel by the formula:

mm {R,G,B}

(R + G + B)I 3

A saturation threshold value Sv is determined for each pixel, and a percentage of pixels in the mask whose saturation value is above the saturation threshold value is determined. If the percentage of pixels is above the saturation threshold value, this mask is considered as a synthetic area and the related pixels and paths are labeled as synthetic image content SYNT.

Finally, a second test T2 is performed on a histogram of the differentiation entries for each area recognized as natural. It has been found that such a histogram has to meet two criteria in the case of natural images. Therefore, the objective of the second test is to verify these criteria on areas detected as natural image content NAT, and to keep the classification of tested areas as natural image content NAT, if the histogram of that area meets both criteria. Otherwise, the classification is changed into synthetic image content SYNT.

In an advantageous embodiment, absolute values d of differentiation entries of the pixels in the area under test are used to generate a histogram H(d) as a function of the absolute values d.

In an alternative embodiment, positive and negative values of the differentiation entries are used. The histogram H(d) of absolute values d contains for each value of d a number of pixels in the area under test having the value d as absolute value of the differentiation entry.

The absolute value d may vary from zero to a maximum range value. The maximum range value corresponds to a maximum differentiation entry which occurs when two adjacent entries in the parameter matrix Y have a maximal difference, for example, due to a transition from zero luminance to a maximum luminance value, or vice versa.

A peak in the histogram H(d) is defined on the basis of the following criteria: 1) H(d) is a relative maximum, that is H(d) > H(d - 1) and H(d) > H(d + 1); 2) H(d) is the absolute maximum in the range (d, maximum range value).

In histograms of images with natural image content NAT, like video images, all the peaks (if more than one) appear at a low gradient, and the distance between the peaks is very small. In histograms of text and graphics images, the distance between peaks is noticeably higher than for video images, and the first peak often appears at a much higher absolute value than in video images. After processing a wide number of input images, appropriate threshold values for a first threshold distance, being the absolute value of d for a first peak with the lowest value of d, and for a second threshold distance between adjacent peaks have been found.

Based on the above-mentioned two threshold values, the two criteria to be met for areas with natural image content NAT in order to keep this classification are:

1) The first peak must appear at an absolute value d below the first threshold distance, and

2) The distance between two consecutive peaks has to be smaller than the second threshold distance.

In an advantageous embodiment, the classification applying the criteria is executed as follows: absolute values d of differentiation entries of pixels in an area of the image classified as natural image content (NAT) are generated, a histogram H(d) is generated

- having a range of absolute values d between zero and a maximum range value, - containing a count of a number of pixels in that area having the same absolute value d as a function of the range of absolute values d

- having peaks at an absolute value d if

- adjacent histogram values H(d-l), H(d+1) are smaller than H(d), and - H(d) is the highest value in a range of absolute values d between the absolute value d and the maximum range value, and - the pixels in that area are classified as synthetic image content (SYNT) if: a lowest value of absolute values d for which H(d) has a peak exceeds a first threshold distance, or

- a difference between absolute values (d) belonging to two adjacent peaks of the histogram H(d) exceeds a second threshold distance.

A final mask M as shown in Fig. 3, i.e. an area with pixels labeled as NAT that has kept the classification of natural content NAT after the two tests Tl, T2, represents, with a good level of confidence, a natural area within the image.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. Use of the verb "comprise" and its conjugation does not exclude the presence of elements or steps other than those stated in a claim. The article "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the device claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Claims

CLAIMS:

1. A method of analyzing an image composed of a matrix of pixels, each pixel being defined by at least one parameter value arranged in a parameter matrix (Y), the method comprising the steps of: performing a differentiation operation on the parameter matrix (Y) to provide a plurality of differentiation entries (D) arranged in a matrix, determining sets of neighboring differentiation entries mutually deviating by not more than a predetermined maximum difference value, determining a path length for each set indicating a number of the neighboring differentiation entries in the set and allocating said path length to each pixel in said set, - classifying a pixel

- as synthetic image content (SYNT), if a combination of the path length allocated to said pixel and the differentiation entry for said pixel exceeds a threshold function (T(D)), and

- as natural image content (NAT), if the combination of the path length allocated to said pixel and the differentiation entry for said pixel is lower than the threshold function (T(D)).

2. A method as claimed in claim 1 , characterized in that a pixel is classified as background image content (BACK), if the differentiation entry for said pixel in the differentiation entries (D) is not more than a minimum entry value.

3. A method as claimed in claim 1, characterized in that the predetermined maximum difference value is zero.

4. A method as claimed in claim 1, characterized in that the at least one parameter value corresponds to a luminance of the pixels.

5. A method as claimed in claim 4, characterized in that the differentiation entry for a pixel is determined by selecting a maximum value of two gradients: a first gradient of the luminance as a function of a location of the pixel in the matrix in a first direction along a row of pixels in the matrix, and a second gradient of the luminance as a function of the location in the matrix in a second direction along another row of pixels in the matrix perpendicular to the first direction.

6. A method as claimed in claim 2, characterized in that the minimum entry value is zero.

7. A method as claimed in claim 2, characterized in that pixels in a background set having pixels classified as background image content (BACK) are classified as natural image content (NAT), if

- the background set has less than a predetermined number of neighboring sets having pixels classified as synthetic image content (SYNT), and the background set has a minimum number of adjacent sets having pixels classified as natural image content (NAT), and are otherwise classified as synthetic image content (SYNT).

8. A method as claimed in claim 7, characterized in that those pixels in a set classified as natural image content (NAT) are classified as synthetic image content (SYNT) if - the neighboring sets have pixels classified as synthetic image content (SYNT), and the path length of the set is below a threshold length.

9. A method as claimed in claim 1, characterized in that a series of adjacent pixels classified as synthetic image content (SYNT) are classified as natural image content (NAT) if a length of the series is below a maximum length.

10. A method as claimed in claim 1, characterized in that in areas of the image having pixels classified as natural image content (NAT): a saturation parameter value is checked for each pixel, and - if a percentage of pixels having a saturation parameter value higher than a saturation threshold value exceeds a threshold percentage, the pixels in that area are classified as synthetic image content (SYNT).

11. A method as claimed in claim 1, characterized in that absolute values d of differentiation entries of pixels in an area of the image classified as natural image content (NAT) are generated, a histogram H(d) is generated having a range of absolute values d between zero and a maximum range value, - containing a count of a number of pixels in that area having the same absolute value d as a function of the range of absolute values d having peaks at an absolute value d if

- adjacent histogram values H(d-l), H(d+1) are smaller than H(d), and

- H(d) is the highest value in a range of absolute values d between the absolute value d and the maximum range value, and

- the pixels in that area are classified as synthetic image content (SYNT) if: a lowest value of absolute values d for which H(d) has a peak exceeds a first threshold distance, or a difference between absolute values (d) belonging to two adjacent peaks of the histogram H(d) exceeds a second threshold distance.

12. A computer program product storable on a computer readable medium comprising software means for executing the method as claimed in claim 1.

13. An apparatus for analyzing an image composed of a matrix of pixels each pixel being defined by at least one parameter value, the values of the at least one parameter value for each pixel being arranged in a parameter matrix (Y), the apparatus comprising processing means for carrying out the method of claim 1.

14. A processor device system and/or computer-readable medium having a computer program stored thereon for executing the method as claimed in claim 1.