EP3005225A1 - Verfahren zum bewerten einer bildqualität eines bildes - Google Patents
Verfahren zum bewerten einer bildqualität eines bildesInfo
- Publication number
- EP3005225A1 EP3005225A1 EP14727447.6A EP14727447A EP3005225A1 EP 3005225 A1 EP3005225 A1 EP 3005225A1 EP 14727447 A EP14727447 A EP 14727447A EP 3005225 A1 EP3005225 A1 EP 3005225A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- image
- area
- tonal
- tonal range
- image area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V10/993—Evaluation of the quality of the acquired pattern
Definitions
- the present invention relates to the field of evaluating the image quality of an image.
- an identification document For the issuance of an identification document, a picture of a person to be identified is usually required, which is intended to enable later identification of the person. For this, the image quality of the image is of crucial importance.
- the image quality of an image is usually assessed by a person who views and judges the image.
- WO 2007/090727 proposes a method for automatically evaluating the image quality of an image, in which an evaluation file is evaluated. This method already allows a fast and automated evaluation of the image quality of an image, especially in the context of automated image capture.
- the invention is based on the finding that the above object can be achieved on the basis of differences in the tonal value range occurring in an image. With a small difference in the tonal range between image areas, therefore, a lower image quality of an image can be assumed than with a large one
- the tonal range indicates the number of color information or tonal levels in an image or image area. The tonal range is usually specified in bits. In the case of an RGB image with the three color channels R (red), G (yellow), B (blue), the tonal range for each color channel can be determined or compared. For RGB images, the tonal range or the difference in particular per color channel can be determined.
- the invention relates to a method for evaluating an image quality of an image, in particular an image of a person or an optical
- Security feature comprising: extracting a first image area of the image; Extracting a second image area of the image; Determining a first tonal range of the first image area; Determining a second tonal range of the second image area; and determining a difference between the first tonal range and the second tonal value to evaluate the image quality.
- the image may be in digital form as an image file.
- the extraction of the respective image area can, for example, by a pattern recognition or by a
- first image area is, for example, a person's face
- face recognition methods can also be used to determine the first image area.
- the step of determining the respective tonal range may be preceded by the step of determining a color space underlying the image. If the color space used is, for example, an RGB color space, tonal ranges of the respective R, G or B color channel can be determined and compared with one another to determine the difference between the tonal ranges. If the color space is not an RGB color space, then the color space is not an RGB color space.
- Tonwertumfucke the respective color channel determined and compared.
- This can be, for example, a CMYK color space with color channels for cyan (C), magenta (M), yellow (yellow, Y) and black (Key, K) or one by the International Commission on Illumination (Commission Internationale de l'Eclairage , CIE) standardized color space act.
- CIE International Commission on Illumination
- the image is a grayscale image, the overall tonal ranges can be determined and compared. According to one embodiment, the amount of difference already provides the rating of the image quality.
- the determined rating of the image quality may be compared with a reference score of a reference image quality.
- the image areas may additionally be compared with reference image areas.
- the image is an image of a person.
- the image is an image of an optical security feature.
- the image can represent any object.
- the first image area comprises an image of the face of a person or a facial area of a person.
- the facial area may be an eye area, mouth, forehead or chin area.
- the second image area comprises one of the following
- the first image area relates to a facial area, for example an eye area
- the second image area may relate, for example, to another facial area, for example a forehead. In this way, the difference in tonal range for different areas of the face can be used to evaluate the image quality of the image.
- the first image region comprises an image of a first subregion and the second image region comprises an image of a second subregion of an optical security feature.
- the optical security feature may include optical features, such as optically variable features, and for example, a hologram or kinegram be formed.
- optical security feature can also optical
- Printing inks for example, optically variable inks (OVD), include and be formed for example by a paint application or a color-changing inking.
- the first subregion and the second subregion of the optical security feature can be characterized by different optical properties in each case.
- the optical security feature is configured to provide the optical security feature
- Security feature can also be performed for optical security features with wavelength-dependent properties or viewing angle-dependent properties.
- the wavelength-dependent properties or viewing-angle-dependent properties can be based on reflection, emission, re-emission or transmission of light or electromagnetic radiation.
- the wavelength-dependent properties for example, by a
- Illumination of the optical security feature with white light, ultraviolet light or infrared light visible.
- the viewing angle-dependent properties can be visible, for example, by a change in the viewing angle with respect to the normal of a planar security feature.
- edge detection is performed, in particular by means of high-pass filtering, in order to obtain an edge image.
- the high-pass filtering can for example be carried out by a convolution with a filter impulse response.
- the filter impulse response may be in the form of a matrix, for example.
- the high-pass filtering can also be carried out in a transformed region, in which case, for example, the Laplace transformation or the Fourier Transformation can find application.
- the convolution can be realized by means of a Laplace operator.
- a tone spread of the edge image is performed.
- the step of determining the difference is determined and / or compared with a height of the first tonal range and / or a height of the second tonal range.
- the comparison can be performed per color channel according to one embodiment.
- Tonwert a color channel of the second image determined and compared.
- the color channels are assigned the same colors.
- a first color channel of the first image region or a second color channel of the second image region is determined for evaluating the image quality. As a result, for example, a color characteristic of the respective area can be detected.
- the respective color channel for the evaluation is compared with a color tone table.
- the color table may include different colors.
- a skin tone value of the first image area and / or the second image area is further compared with a skin tone table.
- the skin tint is an embodiment of the aforementioned tint table.
- the image quality is further evaluated by a
- the image quality is further evaluated
- Overlap range between shades of the first image area and shades of the second image area determined.
- the height of the overlap area indicates how the color spectrums of the first and second areas differ from each other.
- the image is provided by a digital image file.
- the digital image file can be obtained, for example, by means of an image detector, for example by means of a digital image camera or an image sensor.
- the invention relates to a device for evaluating an image quality of an image, comprising: a memory for providing a digital image file representing the image; and a processor which is designed
- the memory may be configured to transfer the digital image file via a
- a digital camera or an image sensor and / or can communicate with a communication network.
- the device is designed to carry out the method according to the invention.
- the invention relates to a computer program having a
- Program code is executed on a computer.
- the invention relates to a method for producing a
- Identification document Applying an optically detectable security feature to the body; Capturing an image of the optical security feature; and performing the method of evaluating an image quality of an image for evaluating the image
- the identification document may be one of the following identification documents: identity document, such as identity card, passport, access control card,
- Authorization card company card, tax stamp or ticket
- the identification document may further comprise an electronically readable circuit, for example an RFID chip.
- the identification document can be single-layered or multi-layered or paper and / or plastic-based.
- the identification document can be constructed from plastic-based films which are joined together to form a body by means of bonding and / or lamination, the films preferably having similar material properties.
- the body of the identification document can be constructed from plastic-based films which are joined together to form a body by means of bonding and / or lamination, the films preferably having similar material properties.
- Identification document can be used as a carrier and / or substrate for an optical
- the provision of the body of the identification document may include, for example, the production of the body of the identification document by means of gluing and / or laminating.
- optically detectable security feature on the body of the identification document, for example, by printing process, embossing process, High-pressure process gravure printing method, planographic printing method or printing process done.
- the detection of the image of the optical security feature can be realized, for example, by means of an image detector, for example an optical image-recording camera or an image sensor. Capturing the image of the optical image detector, for example an optical image-recording camera or an image sensor.
- Security feature may include an extraction of the image of the optical security feature from an image of the identification document.
- Performing the method of evaluating an image quality of an image may enable an evaluation of the image quality of the image of the optical security feature.
- By evaluating the image quality of the image of the optical security feature it is possible for example to evaluate the production quality of the identification document. Further embodiments will be explained with reference to the accompanying drawings. Show it:
- Fig. 1 is a schematic flow diagram of a method for evaluating an image quality of an image of a person
- Fig. 2 is a schematic illustration of an apparatus for evaluating an image quality of an image of a person
- FIG. 3 shows a schematic illustration of isolated image areas of an image of a person portrait
- FIG. 4 is a schematic representation of isolated image areas of an image of an optical security feature
- FIG. 5 is a schematic flow diagram of a method for producing an identification document.
- FIG. 1 shows a schematic flow diagram of a method 100 for evaluating an image quality of an image. The method 100 includes extracting 101 a first image area of the image, extracting 103 a second image area of the image, determining 105 a first tonal range of the first image area, determining 107 a second tonal range of the second image area, and determining 109 a difference between the first tonal range with the second
- Tonal range to evaluate the image quality.
- the steps of extraction 101, 103 may be performed in parallel or sequentially.
- the steps of determining 105, 107 may be performed in parallel or sequentially.
- the image areas may comprise different areas of an object, for example a face of a person, such as the eye area, chin part, end of the forehead.
- the image areas may include different objects of an image, such as a person's face, the person's hair, the person's torso, or a background image.
- the image file representing the image is first prepared photographically. This can be done, for example, by image processing or image optimization, in which the image as a whole is filtered, for example, in order to eliminate image noise.
- the color space is set for the processing.
- the color space to be used later in one of the subsequent steps of measuring or determining color tones is to be selected.
- the color space can be, for example, an RGB color space.
- the steps of extracting 101, 103 may be a pattern recognition or a
- Edge detection may be performed to highlight outlines of objects, such as an outline of a face and its parts, such as nose or eyes.
- a Tonwertsp Dahlung can be performed. This causes the use of the entire Tonwertspektrums, for example, 256 levels of brightness.
- the observable change lies in the
- the aforementioned image processing can contribute to at least partially evaluating the image quality of the image or its image regions for different image regions, and / or to compare the image quality, for example, with an external image quality or reference image quality.
- the expected image content for example in the case of an image of a person, or the expected image scene can be used. If, for example, an image scene is expected, as is the case with a passport photograph, for example, the image components and thus the image areas are already known. These are, for example, the face and adjacent regions of the first and second degree, for example hair, neck, torso, clothing, body or image background such as a canvas.
- 103 of the image areas can also be an edge detection and
- the edge detection is based on a mathematical function, such as a convolution.
- the convolution can be carried out, for example, by means of a matrix with m times n elements.
- a folding operator for example, a Laplace operator can be used, which acts as a high-pass filter and emphasizes edges. In one embodiment, this filter clears
- Image areas of the same tonal and / or brightness levels can be enhanced.
- edge areas or edge areas can be enhanced.
- a multicolored and / or detailed source image can be converted into an edge image.
- the edge image can then be optimized. For example, edge disturbances can be compensated by erosion and dilatation.
- Edge detection is exemplified based on convolution.
- Laplace operator for example, a Sobel operator, a Scharr operator, a Prewitt operator, a Roberts operator, a Kirsch operator and / or a Marr-Hildreth operator can also be used.
- edge detection also other mathematical methods, for example Canny algorithms, methods for contrast enhancement and / or methods for active edge search can be used.
- the exposure of image areas is performed based on an association of the image areas described by edges.
- the exposure of image areas is performed based on an association of the image areas described by edges.
- the geometric conformity of the source image may refer to the guidelines of the International Civil Aviation Organization (ICAO).
- IICAO International Civil Aviation Organization
- the geometric center of the image can first be calculated.
- the center of the image is, for example, the pixel coordinate with a height of 266 pixels and a width of 207 pixels.
- the center of the image is in the area of the face of a person. In this case, a tolerance of 20 pixels in height and width of the source image can be considered.
- Image areas are performed. For this, different methods can be combined or applied separately. The following methods can be applied to the source image, i. before applying the edge detection or the convolution matrix to the source image.
- the first method evaluates, based on color data from skin taps, the
- Another method captures all pixels with color values within a specified tolerance to the color value of the center of the image.
- a color value that deviates from skin tones but is associated with the face is also assigned to the face despite possibly existing color cast.
- Another method involves the eye pair, the nose and the mouth based on a given geometric pattern. The listed facial features can form a so-called golden triangle. Based on the known
- Axial geometry can be an oval or round edge line can be determined, which can correspond to the expected face shape. By specifying whether the person is a child or an adult, the choice of edge line can be made more reliable and / or faster. Glasses can be excluded from detection and declared as not belonging.
- Edge image i. after applying the edge detection or the convolution matrix to the source image.
- This method determines an overlap area between the
- Face area which is determined based on the edge detection
- Face area which is determined based on the hues of the skin areas, and thus generates the final edge lines of the face area.
- the exemption of the facial area adjacent personal areas can be separated. This can include, for example, the areas hair and neck.
- the described methods can be supplemented for example by methods which include a description of the image scene or a prior knowledge of the
- Picture scene for example, in terms of the position of neck and hair, use.
- the neck is searched or determined below the chin.
- the determination of the hair begins first in the area of the forehead and then continues along the face edges in the direction of the chin.
- Possible disturbances for the determination of hair such as no hair, headscarves, headbands or headdresses can be stored as a pattern.
- the determination of the hair can be stopped, for example. Headscarves, headbands or headdresses may be defined as belonging to the hair area.
- Image areas the methods described for edge detection, to determine the image scene and / or to determine adjacent shades can be used.
- the determination 105, 107 of a tonal range can then be performed separately for each of the determined image areas.
- the tonal range is represented by a value from a normalized value range, for example the normalized value range from 0 to 255.
- the tonal range is divided into ranges.
- a small range of tonal values can be present, for example, when the tonal range falls below a first predetermined threshold value and a second predetermined threshold value.
- An average tonal range can be present, for example, when the tonal range exceeds the first predetermined threshold and falls below the second predetermined threshold.
- a high tonal range may be present, for example, when the tonal range exceeds the first predetermined threshold and the second predetermined threshold.
- Tonwerticallys example, to a range of values from 0 to 255, the first predetermined threshold, for example, a value of 33 and the second predetermined threshold value has a value of 66.
- the tonal range has a value of 12
- there is a small tonal range if the tonal range has a value of 12.
- determining 105, 107 of the tonal range includes determining a spread or a spread of a tonal histogram.
- determining 105, 107 of the tonal range includes determining a spread or a scatter of a tonal histogram separately for each color channel.
- the spreading can be done by, for example, making a difference of a highest
- Tone value and a lowest tone value of a tone histogram can be determined, for example, by determining a variance or a
- the determination 109 of a difference between the tonal ranges includes, for example, the evaluation of the determined image areas. In this case, a comparison of all image areas to each other with respect to the respective Tonwertiquess done. Both the height of the tonal range, as well as the expression of the respective color channel can be used as a basis for evaluation.
- the image quality of the image is represented by a value from a normalized value range, for example the normalized value range from 0 to 255.
- the image quality of the image is divided into areas.
- a low image quality can be present, for example, if the image quality falls short of a first predetermined threshold and a second predetermined threshold.
- An average image quality can be present, for example, when the image quality exceeds the first predetermined threshold and falls below the second predetermined threshold.
- High image quality may be present, for example, when the image quality exceeds the first predetermined threshold and the second predetermined threshold.
- threshold value has a value of 33 and the second predetermined threshold value has a value of 66.
- the image quality is 12, For example, there is a low image quality.
- the picture quality is 45, then, for example, the picture quality is average.
- determining 109 a difference between the tonal ranges comprises forming an average of all tonal ranges of the extracted image portions to obtain a measure for evaluating the image quality.
- determining 109 a difference between the tonal ranges includes applying a mathematical mapping of the
- the image quality of the image is rated high if all image areas each have a high tonal range.
- the models can be extended and adapted to the described procedures.
- the first model is characterized in that all image areas have a small tonal range, i. no deep and middle values. This may indicate that there is a low contrast or a flattened image and the portrait of the print medium can not stand out in contrast.
- the second model is characterized in that the image area of the hair has a small tonal range, but the image areas around the face, the neck and the torso have a high or good tonal range. This may indicate that the person in the print medium appears hairless, since the low tonal range in the image background of the print medium is barely visible.
- the third model is characterized by the fact that all image areas have a small tonal range, ie no medium and bright values. This may indicate that the overall picture appears too dark on the print medium and the Portrait looks dark and low in detail due to the small tonal range on the print medium.
- the fourth model is characterized in that the image areas of the hair, the neck and the face have a small tonal range, i. no medium and bright values, and the image areas of the background and the torso have a low
- Tonal range i. no middle and low values. This may indicate that the person on the print media seems too dark and detailless.
- the four models described may refer to standard models for image capturing for identification documents.
- individual image areas can be analyzed or evaluated separately.
- a color cast and / or an achievement of skin tone values can be investigated.
- the examination of the color cast can be carried out, for example, by means of a measurement of the color values of the respective color channels and can enable a corresponding positive or negative evaluation with regard to the individual regions. Deviations from the color standard or missing values can be listed in detail.
- the examination of the skin tones can be carried out, for example, by matching the hues of the image areas of the face and neck with a skin tint. Deviations from the colors of the skin table in the evaluation can be represented as deviations from the color standard or missing values.
- the method 100 can be used both for evaluating an image quality of an image of a person, for example a portrait image, and for evaluating an image quality of an image of an optical security feature. Extracting 101 a first image area of the image, extracting 103 a second image area of the image, determining 105 a first tonal range of the first image area, determining 107 a second tonal range of the second image area, and determining 109 a difference between the first tonal value with the second tonal range may be used accordingly for evaluating an image quality of an image of an optical security feature.
- FIG. 2 shows a schematic representation of a device 200 for evaluating an image quality of an image.
- the device 200 comprises a memory 201, a
- the memory 201 is provided for providing a digital image file representing the image.
- the processor 203 is configured to extract a first image area of the image, to extract a second image area of the image, to determine a first tonal range of the first image area, a second tonal range of the second
- the memory 201 is configured to transfer a digital image file over the
- Receive communication interface 205 which can communicate with an image detector, such as a digital camera or an image sensor, and / or with a communication network.
- the communication interface 205 is configured to communicate with a digital camera and / or with a communication network.
- the communication interface 205 is further connected to the memory 201 and / or the processor 203.
- the apparatus 200 is configured to perform the method 100 for evaluating an image quality of an image.
- the processor 203 is configured to be
- FIG. 3 shows a schematic representation of isolated image areas of an image of a person portrait.
- Fig. 3a an exempted facial area 301 of the person is exemplified.
- Fig. 3b is an example of a free Torso Scheme 303 of
- the cut-out areas 301, 303, 305, 307 can, for example, by the
- Extracting 101, 103 of the image areas are provided.
- edge detection is performed, for example by means of high-pass filtering, in order to obtain an edge image.
- the provision of the cut-out regions 301, 303, 305, 307 can then take place on the basis of the obtained edge image.
- the tonal range is represented by a value from a normalized value range, for example the normalized value range from 0 to 255.
- the tonal range is divided into ranges.
- a small range of tonal values can be present, for example, when the tonal range falls below a first predetermined threshold value and a second predetermined threshold value.
- An average tonal range can be present, for example, when the tonal range exceeds the first predetermined threshold and the second falls below predetermined threshold.
- a high tonal range may be present, for example, when the tonal range exceeds the first predetermined threshold and the second predetermined threshold.
- Tonwerticallys example, to a range of values from 0 to 255, the first predetermined threshold, for example, a value of 33 and the second predetermined threshold value has a value of 66.
- the tonal range has a value of 12
- there is a small tonal range For example, if the tonal range has a value of 45, then there is, for example, an average tonal range.
- the tonal range has a value of 80, then there is a high tonal range.
- determining 105, 107 of the tonal range includes determining a spread or a spread of a tonal histogram.
- determining 105, 107 of the tonal range includes determining a spread or a scatter of a tonal histogram separately for each color channel.
- the spreading can be done by, for example, making a difference of a highest
- Tone value and a lowest tone value of a tone histogram Tone value and a lowest tone value of a tone histogram.
- the scattering can be determined, for example, by determining a variance or a
- the image quality of the image is represented by a value from a normalized value range, for example the normalized value range from 0 to 255.
- the image quality of the image is divided into areas.
- a low image quality can be present, for example, if the image quality is a falls below the first predetermined threshold and a second predetermined threshold.
- An average image quality can be present, for example, when the image quality exceeds the first predetermined threshold and falls below the second predetermined threshold.
- High image quality may be present, for example, when the image quality exceeds the first predetermined threshold and the second predetermined threshold.
- the first predetermined threshold value may have a value of 33 and the second predetermined threshold value may have a value of 66.
- the image quality has a value of 12, for example, the image quality is poor.
- the picture quality is 45, then, for example, the picture quality is average.
- the picture quality is 80, for example, the picture quality is high.
- determining 109 a difference between the tonal ranges includes forming an average of all tonal ranges of the tonal ranges
- determining 109 a difference between the tonal ranges includes applying a mathematical mapping of the
- Tonwerto for the range 301 medium, the range 303 high, the range 305 low and the range 307 medium so for example, the image quality can be rated as medium. If, for example, the tonal range for the region 301 is low, the region 303 is medium, the region 305 is high, and the region 307 is low, the image quality, for example, can be rated as low. This ensures that individual
- Image areas can have a different weighting in the evaluation of image quality.
- the image quality of the image is assessed as high if all image regions 301, 303, 305, 307 each have a high tonal range.
- FIG. 4 shows a schematic representation of isolated image regions of an image of an optical security feature 400.
- a first exposed image region 401 and a second exposed image region 403 are shown by way of example.
- the cleared areas 401, 403 may be provided, for example, by extracting 101, 103 of the image areas.
- edge detection is performed, for example by means of high-pass filtering, in order to obtain an edge image.
- the provision of the cut-out regions 401, 403 can then take place on the basis of the obtained edge image. For example, a determination 105, 107 of a tonal value circumference can be carried out in each case for the excluded regions 401, 403.
- the tonal range is represented by a value from a normalized value range, for example the normalized value range from 0 to 255.
- the tonal range is divided into ranges.
- a small range of tonal values can be present, for example, when the tonal range falls below a first predetermined threshold value and a second predetermined threshold value.
- An average tonal range can be present, for example, when the tonal range exceeds the first predetermined threshold and falls below the second predetermined threshold.
- a high tonal range may be present, for example, when the tonal range exceeds the first predetermined threshold and the second predetermined threshold.
- Tonwert For example, to a range of values from 0 to 255, the first predetermined threshold, for example, a value of 33 and the second predetermined threshold value has a value of 66. For example, if the tonal range has a value of 12, then there is a small tonal range. Does the Tonwertnic, for example, a value of 45, so there is, for example, an average Tonwerture. For example, if the tonal range has a value of 80, then there is a high tonal range.
- determining 105, 107 of the tonal range includes determining a spread or a spread of a tonal histogram.
- determining 105, 107 of the tonal range includes determining a spread or a scatter of a tonal histogram separately for each color channel.
- the spreading can be done by, for example, making a difference of a highest
- Tone value and a lowest tone value of a tone histogram Tone value and a lowest tone value of a tone histogram.
- the scattering can be determined, for example, by determining a variance or a
- determining 109 a difference between the respective tonal ranges may be performed to evaluate the image quality.
- the tonal values of the separated image areas and / or a comparison of the tonal values may be based on one or more
- Histograms are performed.
- the evaluation of the respective histogram can be divided, for example, with respect to a fault severity on two platforms.
- the position of the tonal values of the individual color channels per image or per image area can make a statement regarding the image saturation.
- the subjective perception can range from "colorless gray” (desaturated) to "color cast colorful” (saturated). Based on the comparison of the separated image areas introduces
- the smaller the tonal range of a separated image area the less unfavorable identical tonal positions of the adjacent image areas have on the contrast behavior.
- the distance between the tonal positions of the color channels of the individual image areas determines the subjective contrast perception.
- the TWU of all image areas is very small and their position and / or coordinates in the histogram are superimposed. As a result, the contrast of the areas is barely perceptible.
- the color cast can be analyzed very well via the scattering of the color channels.
- An example of this can be found in the appendix.
- a high-quality passport photo has a uniform overlay of the foot and mid regions of the color channels in the histogram. Remove the color channels in the histogram
- the respective defective color expression (for example "reddish") can be determined by means of a histogram.
- the image quality of the image is represented by a value from a normalized value range, for example the normalized value range from 0 to 255.
- the image quality of the image is divided into areas.
- a low image quality can be present, for example, if the image quality falls short of a first predetermined threshold and a second predetermined threshold.
- An average image quality can be present, for example, if the Image quality exceeds the first predetermined threshold and falls below the second predetermined threshold.
- High image quality may be present, for example, when the image quality exceeds the first predetermined threshold and the second predetermined threshold.
- the first predetermined threshold when normalizing the image quality to a value range of 0 to 255, the first predetermined threshold may have a value of 33 and the second predetermined threshold may have a value of 66. For example, if the image quality has a value of 12, for example, the image quality is poor. For example, if the picture quality is 45, then, for example, the picture quality is average. For example, if the picture quality is 80, for example, the picture quality is high.
- determining 109 a difference between the tonal ranges includes forming an average of all tonal ranges of the tonal ranges
- cut-out areas 401, 403 to obtain a measure of image quality.
- determining 109 a difference between the tonal ranges includes applying a mathematical mapping of the
- the image quality of the image is rated high when all image areas 401, 403 each have a high tonal range.
- the method 500 includes providing 501 a A body of the identification document, applying 503 an optically detectable security feature 400 to the body, capturing 505 an image of the optical security feature 400, and performing 507 the method 100 for assessing an image quality of an image for evaluating the image quality of the image of the optical security feature 400.
- the provision 501 of the body of the identification document may, for example, comprise the production of the body of the identification document by means of gluing and / or laminating.
- the application 503 of the optically detectable security feature 400 to the body of the identification document can be achieved, for example, by printing methods,
- the detection 505 of the image of the optical security feature 400 can be realized by means of an image detector, for example a digital image recording camera or an image sensor. Detecting 505 the image of the optical security feature 400 may include extracting the image of the optical security feature 400 from an image of the identification document.
- Performing 507 the method 100 for evaluating an image quality of an image may allow for evaluating the image quality of the image of the optical security feature. By evaluating the image quality of the image of the optical security feature.
- Security feature can be done, for example, an assessment of the manufacturing quality of the identification document. LIST OF REFERENCE NUMBERS
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102013105457.9A DE102013105457A1 (de) | 2013-05-28 | 2013-05-28 | Verfahren zum Bewerten einer Bildqualität eines Bildes |
| PCT/EP2014/060503 WO2014191290A1 (de) | 2013-05-28 | 2014-05-22 | Verfahren zum bewerten einer bildqualität eines bildes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP3005225A1 true EP3005225A1 (de) | 2016-04-13 |
Family
ID=50877248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP14727447.6A Ceased EP3005225A1 (de) | 2013-05-28 | 2014-05-22 | Verfahren zum bewerten einer bildqualität eines bildes |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP3005225A1 (de) |
| DE (1) | DE102013105457A1 (de) |
| WO (1) | WO2014191290A1 (de) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117372362A (zh) * | 2023-10-11 | 2024-01-09 | 长沙雄帝信安科技有限公司 | 一种图像质量评估方法和装置 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE50212936D1 (de) * | 2002-10-24 | 2008-12-04 | L 1 Identity Solutions Ag | Prüfung von Bildaufnahmen von Personen |
| DE102006005617B4 (de) | 2006-02-06 | 2023-10-12 | Bundesdruckerei Gmbh | Verfahren zur Bewertung der Qualität eines Bildes, Verfahren zur Herstellung eines Dokuments, Computerprogrammprodukt und elektronisches Gerät |
| DE102008052248B4 (de) * | 2008-10-18 | 2017-02-02 | Mühlbauer Gmbh & Co. Kg | Verfahren und Vorrichtung für die Überprüfung von Linsenstrukturen |
| DE102012021725A1 (de) * | 2012-11-06 | 2014-05-08 | Giesecke & Devrient Gmbh | Qualitätsprüfung eines Kippbildes einer Linsenstruktur |
-
2013
- 2013-05-28 DE DE102013105457.9A patent/DE102013105457A1/de active Pending
-
2014
- 2014-05-22 WO PCT/EP2014/060503 patent/WO2014191290A1/de not_active Ceased
- 2014-05-22 EP EP14727447.6A patent/EP3005225A1/de not_active Ceased
Non-Patent Citations (2)
| Title |
|---|
| None * |
| See also references of WO2014191290A1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2014191290A1 (de) | 2014-12-04 |
| DE102013105457A1 (de) | 2014-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102006005617B4 (de) | Verfahren zur Bewertung der Qualität eines Bildes, Verfahren zur Herstellung eines Dokuments, Computerprogrammprodukt und elektronisches Gerät | |
| EP3047424B1 (de) | Vorrichtung, system und verfahren zum identifizieren einer person | |
| EP3555811A2 (de) | Verifizierung eines sicherheitsdokuments | |
| EP1625936A2 (de) | Verfahren zur qualitativen Beurteilung eines Materials mit mindestens einem Erkennungsmerkmal | |
| DE102010016630A1 (de) | Verfahren und Gerät zur Charakterisierung von Hautunregelmäßigkeiten und Verfahren zur Bewertung der Anti-Aging-Wirkung eines Kosmetikprodukts | |
| EP3629232A1 (de) | Vorrichtung zum erkennen einer bildmanipulation in einem digitalen referenzgesichtsbild einer person | |
| DE102016115837A1 (de) | Verfahren für die Urheberschaftsbewertung eines Gemäldes sowie eine entsprechende Verwendung | |
| DE102015208087A1 (de) | Verfahren zum Generieren eines reflektionsreduzierten Kontrastbildes und diesbezügliche Vorrichtungen | |
| DE102017102556A1 (de) | Verfahren zur Verifizierung eines Sicherheitsdokuments sowie ein Sicherheitsdokument, eine Vorrichtung und ein Sicherheitselement | |
| WO2012013186A2 (de) | Verfahren und vorrichtung zur bestimmung der augentorsion | |
| EP3158543B1 (de) | Verfahren zum detektieren eines blickwinkelabhängigen merkmals eines dokumentes | |
| WO2014191290A1 (de) | Verfahren zum bewerten einer bildqualität eines bildes | |
| DE112019007066T5 (de) | Fälschungssicheres Papierprodukt basierend auf Mikrostrukturerkennung, Herstellungsverfahren sowie Authentifizierungsverfahren dafür | |
| EP2394250B1 (de) | Verfahren und vorrichtung zum verifizieren von dokumenten unter verwendung einer wavelet-transformation | |
| EP4075397B1 (de) | Verfahren zum identifizieren einer person anhand eines biometrischen gesichtsmerkmals mit hilfe eines mobilen geräts und mobiles gerät | |
| DE102015116708A1 (de) | Dokument und Verfahren zum Verifizieren eines Dokuments | |
| WO2018114471A1 (de) | Vorrichtung zum reduzieren eines farbstichs eines gesichtsbildes | |
| DE102023131282B3 (de) | Verfahren und Vorrichtung zum Prüfen eines Sicherheitselements für ein Sicherheitsdokument | |
| EP3089105A1 (de) | Verfahren zum generieren eines kontrastbildes einer objektbeschaffenheit und diesbezügliche vorrichtungen | |
| EP4005815B1 (de) | Sicherheitsdokument, verfahren zu seiner herstellung, elektronisches drucksystem und lesegerät | |
| DE102019114666A1 (de) | Rote-augen-korrektur-techniken | |
| EP3651059B1 (de) | Vorrichtung zum personalisieren eines identitätsdokumentes einer person | |
| EP4064221A1 (de) | Verfahren zum personalisieren eines id-dokuments sowie verfahren zum identifizieren einer person anhand biometrischer gesichtsmerkmale und id-dokument | |
| DE102023117683A1 (de) | Verfahren, Vorrichtung und System zum Erkennen einer Gesichtsmanipulation | |
| WO2017108428A1 (de) | Authentifikationsvorrichtung und verfahren zur optischen oder akustischen zeichenerkennung |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| 17P | Request for examination filed |
Effective date: 20151113 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| AX | Request for extension of the european patent |
Extension state: BA ME |
|
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20170719 |
|
| APBK | Appeal reference recorded |
Free format text: ORIGINAL CODE: EPIDOSNREFNE |
|
| APBN | Date of receipt of notice of appeal recorded |
Free format text: ORIGINAL CODE: EPIDOSNNOA2E |
|
| APBR | Date of receipt of statement of grounds of appeal recorded |
Free format text: ORIGINAL CODE: EPIDOSNNOA3E |
|
| APAV | Appeal reference deleted |
Free format text: ORIGINAL CODE: EPIDOSDREFNE |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R003 |
|
| APBT | Appeal procedure closed |
Free format text: ORIGINAL CODE: EPIDOSNNOA9E |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED |
|
| 18R | Application refused |
Effective date: 20230308 |
|
| P01 | Opt-out of the competence of the unified patent court (upc) registered |
Effective date: 20230526 |