US20120076405A1 - Automatic detection of calibration charts in images - Google Patents

Abstract

Methods and apparatuses for locating an embedded color chart in an image are described. In one exemplary method, an image that includes an embedded color chart is located without the intervention of the user. The embedded color chart is verified and used to create a color profile of the image. Furthermore, the orientation angle of the color chart is determined and the image orientation is fixed based on this angle.

Description

• This application is a continuation of co-pending U.S. patent application Ser. No. 11/811,214, filed on Jun. 8, 2007, entitled “Automatic Detection of Calibration Charts in Images.”
FIELD OF THE INVENTION
• This invention relates generally to image processing and more particularly to automatically detecting a color calibration charts embedded in a digital image.
BACKGROUND OF THE INVENTION
• A color calibration chart (“color chart”) is an array of several blocks of known color values that is used to calibrate and evaluate the color in cameras and other systems capable of color reproduction. Each of the squares represent different colors that are typically used in color images, such as white, black, different levels of gray, as well as colors representing human skin, foliage, and blue sky. Color charts are typically used photography, graphic arts, electronic publishing, and video production to check cameras (still and video), printers, scanners, monitors, or any other equipment used in the color reproductions system.
• A photographer will typically take a picture of a scene that includes the color chart. The photographer can do this for every picture, or for a representative picture in a sequence of pictures. In the post-processing of the image, in one embodiment, a user would manually check the color of the some or all of the color squares in the reproduced color chart and adjust the reproduced color until the color of the square matched or closely approximated the known color. In an alternate embodiment, the user would select the color chart in the image and a computer would detect the selected color chart and use this chart to calibrate the image.
• However, this process requires the user to manually select the color chart, or manually check each of the squares to calibrate the image. In addition, these methods known in the art require the color chart be horizontal with the image, which means that the color chart cannot be oriented at an angle other than zero to the image.
SUMMARY OF THE DESCRIPTION
• Methods and apparatuses for locating an embedded color chart in an image are described. In one exemplary method, an image that includes an embedded color chart is located without the intervention of the user. The embedded color chart is verified and used to create a color profile of the image. Furthermore, the orientation angle of the color chart is determined and the image orientation is fixed based on this angle.
BRIEF DESCRIPTION OF THE DRAWINGS
• The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.
• The present invention is illustrated by way of example and not limitation in the figures of the accompanying drawings in which like references indicate similar elements.
• FIG. 1 is an image with an embedded color chart.
• FIG. 2 is a flow chart of one embodiment of a method to detect an embedded color chart in an image and create a color profile for that image.
• FIG. 3 is a flow chart of one embodiment of a method to convert the image to grayscale based on the maximum luminance for pixel.
• FIG. 4 illustrates one embodiment of a conversion of an image to grayscale based on the maximum luminance of each pixel.
• FIG. 5 is a flow chart of one embodiment of a method to locate a color chart embedded in an image.
• FIG. 6A is a flow chart of one embodiment of a method to measure the fit of M pulses onto a vertical generated signal.
• FIG. 6B is a flow chart of one embodiment of a method to measure the fit of N pulses onto a horizontal generated signal.
• FIG. 7A is a graph of one embodiment illustrating a plot of an average horizontal scan lines comprising M pulses.
• FIG. 7B is a graph of one embodiment illustrating a plot of an average horizontal scan lines comprising N pulses.
• FIG. 8 is a flow chart of one embodiment of a method to fix the orientation of the image.
• FIG. 9 illustrates one embodiment of converted image illustrating edges.
• FIG. 10 illustrates one embodiment of an angle histogram overlaid on an image with an embedded color chart.
• FIG. 11 is a block diagram illustrating a color chart location system according to one embodiment of the invention.
• FIG. 12 is a diagram of one embodiment of an operating environment suitable for practicing the present invention.
• FIG. 13 a diagram of one embodiment of a data processing system, such as a general purpose computer system, suitable for use in the operating environment ofFIG. 2.
DETAILED DESCRIPTION
• In the following detailed description of embodiments of the invention, reference is made to the accompanying drawings in which like references indicate similar elements, and in which is shown by way of illustration specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention, and it is to be understood that other embodiments may be utilized and that logical, mechanical, electrical, functional, and other changes may be made without departing from the scope of the present invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is defined only by the appended claims.
• FIG. 2 illustrates an embodiment of a method to locate a color chart in an image. Furthermore, the method converts the image based on the maximum luminance of each pixel and orients the image in order to aid in the location of the color chart.FIG. 3 illustrates one embodiment of a method to convert the image based on the maximum luminance of each pixel.FIG. 5 illustrates one embodiment of a method to locate the color chart in an image based on average horizontal and vertical scan lines. FIG.6AB illustrate fitting generated signals for a particular reference color chart to the horizontal and vertical scan lines.FIG. 8 illustrates orienting the image so that the color chart is horizontal.FIG. 11 illustrates one embodiment of the color chart location system that implementsFIGS. 2,3,5,6AB, and8.
• FIG. 1 is an image with an embedded color chart. InFIG. 1,image100 comprises acolor chart102 andimage subject matter104. In one embodiment, an image is a digital image taken by a digital still camera. The image can be any one of the digital formats known in the art, such Graphics Interchange Format (GIF), Joint Photographics Experts Group (JPEG), RAW, etc. In an alternate embodiment, an image is a video frame. The video frame can be any digital video format known in the art, such as Moving Pictures Experts Group (MPEG), MPEG-4, etc. In a further embodiment, an image can be can be directly acquired from the camera, where there is no file format at all because the image is not written to a file.Image subject matter104 is a music player, block objects and a tool. In alternate embodiment, image subject matter can be any type of subject matter typically taken by a camera or other color reproduction system.Color chart102 comprises a grid of color squares used to calibrate the captured image. Each square is a known color. In one embodiment, the known color for each color square is represented by Red Green Blue (RGB) value. In alternate embodiments, the known color is represented by other color schemes known in the art, e.g. Cyan, Magenta, Yellow, and Black (CMYK), Cyan, Magenta, Yellow, Green (CMYG), etc.
• In the embodiment illustrated inFIG. 1, color chart comprises ten by fourteen color squares. In alternate embodiments, color charts can have differing numbers of color squares, such six by eight, twenty by twelve, etc. Furthermore,color chart102 can be oriented horizontal with the image border or be tilted at an angle to the image border.
• FIG. 2 is a flow chart of one embodiment of amethod200 to detect an embedded color chart in an image and create a color profile for that image. Locating a color chart can be a five dimensional search because of the need to search in the x and y image dimension, chart size (width and height) and chart angle.Method200 reduces the search to two dimensional search by fixing the orientation of the color chart to be horizontal and locating the color chart using horizontal and vertical average scan lines. The new search space is all angles, all x-start positions and widths and all y-positions and heights, which is a two dimensional search. Reducing the search to a two dimensional search enables the search to be done by a modern personal computer is a matter of seconds using the central processing unit (CPU) or graphics processing unit (GPU) of that computer. In one embodiment, color charts are located in the images as the images are being loaded onto the personal computer.
• InFIG. 2, atblock202,method200 converts that image to grayscale. In one embodiment,method200 converts the image to grayscale by selecting the maximum RGB value for the each pixel. This increases the contrast between the background of the color chart and the squares of the color chart. A greater contrast, as shown below, enables easier detection of the color squares in the color chart. Because color charts typically have a black background, selecting the maximum RGB value gives the greatest luminance value for that pixel. A lager luminance value leads to a greater contrast between the black background and the pixel of the color square. Converting an image using the maximum RGB value is further described inFIG. 3, below. In an alternative embodiment,method200 converts the image to grayscale based on the average luminance value for each pixel.
• Atblock204,method200 fixes the orientation of the image such that the color chart is spatially horizontal, such that the sides of the color chart are parallel to the image frame. The color chart may not be in a perfect horizontal orientation relative to the borders of the pictures. In one embodiment,method200 determines the orientation angle of the color chart by plotting a histogram of the edge angles in the image. The orientation angle can be a small angle such that the color chart is tilted slightly or large in the case where the color chart is heavily tilted.Method200 rotates the image by the orientation angle to fix the orientation. Fixing the orientation results in the color chart being right side up or upside down. Fixing the orientation of the image is further described inFIG. 8, below.
• Method200 further executes a processing loop (blocks206-212) to locate a particular reference color chart (N×M color chart) in the image. Atblock208,method200 searches for a particular N×M chart in the image. N refers to the number of color square columns in the color chart and M is the number of color square rows. As stated above, color charts are typically industry standard charts, comprising known dimensions, and number and type of color squares.
• Atblock210,method200 determines if the N×M color chart is located. Locating a color chart is further described inFIG. 5, below. In one embodiment, method locates the color chart that is horizontal. In another embodiment,method200 locates the color chart if the color chart is upside down. Ifmethod200 does not locate the N×M color chart,method200 selects another reference color chart to search for. The processing loop ends atblock212. If no chart is found or the located chart is too small,method200 ends the search for an embedded color chart in the image at block214. Alternatively, if the located chart is too small,method200 can reject the color chart and search for the chart in part of the image. In one embodiment,method200 searches for the color chart in overlapping chunks of the image if the color chart is less than one-eighth the area of the image.
• Ifmethod200 has located the N×M color chart,method200 verifies this chart atblock216. In one embodiment, verification consists of checking the located color chart for the correct number, arrangement and type of color squares. Alternatively,method200 is to build a color profile using the found chart and check if the color matrix is roughly diagonal.Method200 optionally prompts the user to calibrate this image using the found color chart at block218. Atblock220,method200 uses the located color chart to create a color profile for the image. In one embodiment, a color profile, as is known in the art, can be used to calibrate a sensor such as one typically found in a camera, video camera, scanner, printer, etc. Alternatively, the color profile is used to calibrate the sensor for specific lighting conditions (for example, as during a photo shoot). In an alternate embodiment, the color profile is used to calibrate a sequence of images, such as a group of photos taken of the same scene or photo session. In another embodiment, the color profile is used to calibrate a series of video frames. The video frames can be from the same or different scene. In a further embodiment, the color profile can be used to calibrate color reproduction equipment, such as cameras, video cameras, printers, scanners, copiers, etc.
• FIG. 3 is a flow chart of one embodiment ofmethod300 to convert the image to grayscale based on the maximum luminance for pixel.Method300 further executes a processing loop (blocks302-308) to set each pixel to the maximum luminance value. Atblock304,method300 finds the maximum RGB value. In one embodiment,method300 selects the largest pixel value of the three RGB components.Method300 sets all three components to the found maximum at block306. The processing loop ends atblock308.
• FIG. 4 illustrates one embodiment of a conversion of image to grayscale based the maximum luminance. As stated above,method300 converts the image to grayscale using two embodiments: one embodiment selects the luminance based on the average RGB value, whereas the other embodiment selects the luminance based on the maximum RGB value. InFIG. 4, the twograyscale images404A-B are generated fromcolor image402 using the two embodiments.Image404B exhibits greater contrast in the color chart between the color chart's black background and the square. For example, color square406B is lighter than square406A, which gives a greater contrast between the color square and the black background. On other words, color square406A has less luminance than color square406B. A greater luminance for color square406B facilitates easier detection of the color square406B, and thus, making it easier to locate the color chart embedded in the image.
• FIG. 5 is a flow chart of one embodiment of amethod500 to locate a color chart embedded in an image. InFIG. 5, atblock502,method500 computes an average horizontal scan line. In one embodiment, each point on the horizontal scan line is the average luminance of a horizontal scan line for the whole image. On one hand, because the background of the color chart is black, an average luminance of a horizontal scan line across the black background is small. On the other hand, since the most of the color squares in a row of a typical color chart are not black, the average luminance value for a scan line across a row of color squares is larger than the luminance for the black background. Thus, the average horizontal scan line will have peaks at position associated with the color squares and valleys associated with the color chart background. A higher contrast produces sharper peaks.
• Method500 fits a known pulse signal of the N×M color chart to the average horizontal and vertical scan lines by locating the horizontal and vertical positions of the color chart and fitting the pulses sequences of peaks and valleys from the average horizontal and vertical scan lines with generated pulse signals corresponding to a reference color chart.Method500 further executes a first processing loop (blocks504-522) to determine if there is a pulse representing rows of color squares in an embedded color chart in the image. Atblock506,method500 finds the next start position. In one embodiment, the next start position is the next pixel on the average horizontal scan line. In an alternate embodiment, a suitable scheme to known in the art to locate another point on a line can be employed.
• Atblock508,method500 attempts to fit M pulses of the average horizontal scan line onto a generated signal. The M pulses represent M rows of the reference color chart and the generated signal is a signal that represents average horizontal scan line for the reference color chart. In one embodiment,method500 fits the M pulses onto the generate signal by matching the number of pulses in generated signal with the number of pulses in the average horizontal scan line. In an alternate embodiment,method500 fits M pulses onto a generated signal as further described inFIG. 6A below.
• Atblock510,method500 determines if the vertical fit is successful. In one embodiment,method500 compares the sum of the goodness values is greater than a threshold. In one embodiment, the threshold is an empirical threshold. The determination of the goodness values for the average horizontal scan lines is further described atFIG. 6A below. If the vertical fit was not successful,method500 proceeds to the end of the loop at522.
• It the vertical fit was successful, the location of the fit sets the top and bottom horizontal position of the color chart in the image. Locating the left and right vertical positions of the color chart can be accomplished by searching a reduced image bounded by the top and bottom horizontal positions determined above.Method500 computes a reduced average vertical scan line atblock512. In one embodiment, the reduced average vertical scan line is determined by computing the average luminance along a vertical scan line of the image in between the top and bottom horizontal determined above. By computing the reduce average vertical scan line, the difference between the pulse peaks and valleys in the reduced average vertical scan lines can be more pronounced that for the average horizontal scan lines because there is less luminance contribution due to pixels that are not part of the color chart in the reduced image. Thus, the area above and below the chart can be excluded from computing the average vertical scan lines.
• Method500 further executes a second processing loop (blocks514-522) to determine if there is a pulse representing rows of color squares in an embedded color chart in the image. Atblock514,method500 finds the next start position. In one embodiment, the next start position is the next pixel on the average horizontal scan line. In an alternate embodiment, a suitable scheme to known in the art to locate another point on a line can be employed. Furthermore,method500 does not need to search over all possible pulse widths. In one embodiment, the height of the color chart and thepeaks method500 is searching for are roughly square. In this embodiment,method500 searches for pulse widths that roughly comparable to the determined pulse height of the color chart.
• Atblock518,method500 attempts to fit N pulses of the average vertical scan line onto a generated signal. The N pulses represent N columns of the reference color chart. The generated signal is a signal that represents average vertical scan line for the reference color chart. In one embodiment,method500 fits the N pulses onto the generated signal by matching the number of pulses in generated signal with the number of pulses in the average vertical scan line. In an alternate embodiment,method500 fits N pulses onto a generate signal as further described inFIG. 6B below.
• Asblock520,method500 determines if the horizontal fit is successful. In one embodiment,method500 compares if the sum of the goodness values is greater than a threshold. The determination of the goodness values for the average horizontal scan lines is further described atFIG. 6B below. If the horizontal fit was not successful,method500 proceeds to the end of the loop at522. The second processing loop ends atblock522.
• If the horizontal fit was successful, a color chart was found and control proceeds to block216. If no color chart is found, control proceeds to block212.
• FIG. 6A is a flow chart of one embodiment of amethod600 to measure the fit of M pulses from the average horizontal scan line onto a vertical generated signal. InFIG. 6A,method600 executes a processing loop (blocks602-608) to fit M pulses onto the vertical generated signal. At block604,method600 scales the generated signal to a mean value of zero and a standard deviation of one.Method600 derives goodness values for each pulse to measure the fit of the M pulses to the generated signal. In one embodiment, the goodness value is the average of the side form the average of the top of the peak. A difference between the top of the peak and the side of the peak measures the contrast between the areas that are supposed to be dark (low contrast) with the areas that are supposed to be bright (the color square). The processing loop ends atblock608. Atblock610,method600 sums the M pulse goodness values. The sum of the goodness values is used to measure the fit of the M pulses to the vertical generated signal. This sum is used, inFIG. 5, atblock510, to determine if there is a proper fit of the M pulses onto the generated signal.
• FIG. 6B is a flow chart of one embodiment of amethod650 to measure the fit of N pulses from the average vertical scan line onto a horizontal generated signal. InFIG. 6B,method650 executes a processing loop (blocks652-658) to fit N pulses onto the horizontal generated signal. At block654,method650 scales the generated signal to a mean value of zero and a standard deviation of one.Method650 derives goodness values for each pulse to measure the fit of the N pulses to the generated signal. In one embodiment, the goodness value is the average of the side form the average of the top of the peak. A difference between the top of the peak and the side of the peak measures the contrast between the areas that are supposed to be dark (low contrast) with the areas that are supposed to be bright (the color square) The processing loop ends atblock658. Atblock660,method650 sums the N pulse goodness values. The sum of the goodness values is used to measure the fit of the M pulses to the vertical generated signal. This sum is used, inFIG. 5, atblock520, to determine if there is a proper fit of the N pulses onto the generated signal.
• FIG. 7A is agraph700 of one embodiment illustrating a plot of an average horizontal scan lines comprising M pulses. InFIG. 7,graph700 the average horizontal scan line plotted alongX-axis702A and Y-axis702B. On theX-axis702A,graph700 plots the luminance value. On the Y-axis702B,graph700 plots the horizontal scan line position.Graph700 illustrates tenpulses704 in the middle of the graph. These ten pulses represent the ten rows of the color chart embedded in the image. As described inFIG. 5 above,method500 locates the pulses in the average horizontal scan line.
• FIG. 7B is agraph750 of one embodiment illustrating a plot an average vertical scan lines comprising N pulses. InFIG. 7,graph750 is an example of an average vertical scan line plotted alongX-axis752A and Y-axis752B. On theX-axis752A,graph750 plots the luminance value. On the Y-axis752B,graph750 plots the vertical scan line position.Graph750 illustrates fourteenpulses754 in the middle of the graph. These ten pulses represent the fourteen columns of the color chart embedded in the image. As described inFIG. 5 above,method500 locates the pulses in the average vertical scan line.
• FIG. 8 is a flow chart of one embodiment of a method to fix the orientation of the image. While this embodiment ofmethod800 describes fixing the orientation of an image based on an embedded color chart, in alternate embodiments,method800 can be used to fix the orientation of an image that has strong horizontal and/or vertical edges (e.g., scanned text, etc.). InFIG. 8, atblock802,method800 performs edge detection in the image according to one several schemes known in the art. While in oneembodiment method800 performs Sobel edge detection, in alternate embodiments,method800 performs different edge detections as know in the art (Abdou, Prewitt, etc.).FIG. 9 illustrates one embodiment of converted image illustrating edges. InFIG. 9,image900 comprises a color chart, as illustrated by the edges of the color squares in the color chart.
• Returning toFIG. 8, atblock804,method800 finds the edges in the image and measures the angle of the gradient vector for the each edge. The gradient vector comes from the chosengradient operator method800 uses as described atblock802. In one embodiment, if the vector is small,method800 ignores this edge for the analysis.Method800 measures the angle of the vector. In one embodiment,method800 measures the angle of the vector to the horizontal of the image.Method800 creates an image of the vector angles atblock806.
• Atblock808,method800 creates a histogram of the vector angle image. The histogram clusters vector angles along peaks of the histogram that are related to the orientation angle of the color chart.FIG. 10 illustrates one embodiment of an angle histogram overlaid on an image with an embedded color chart. InFIG. 10,images1000 comprisescolor chart1002 oriented at an angle to the horizontal of the image. Overlaid onimage1000 is thehistogram1004 that shows four spikes of the histogram correlating to the angle of the color chart.
• Returning toFIG. 8, atblock810,method800 reduces the histogram to one spike. In one embodiment,method800 reduces the histogram to one spike by taking, for each angle α in the histogram between 0 and π/4, the minimum value of the histogram at α, α+N/4, α+2π/4, α+3π/4. If there is noise in the histogram,method800 blurs the histogram to smooth out the noisy signal. At block812,method800 selects the angle where the reduced histogram has the maximal value. This angle represents the orientation angle of the color chart in reference to the horizontal of the image.
• FIG. 11 is a block diagram illustrating a colorchart location system1100 according to one embodiment of the invention. InFIG. 11,system1100 comprisesgrayscale module1102,orientation module1104, chart location module1106, verifymodule1108,color profile1110, and chartlocation control module1112.Grayscale module1102 couples to chart location module1106 and converts the original image into a grayscale based on the maximum luminance of each image pixel as described atFIG. 2, block202 andFIG. 3 above.Orientation module1104 couples to chart location module1106 and determines the orientation angle of the embedded color chart as described atFIG. 2, block204 andFIG. 8. Orientation module further fixes the orientation of the color chart as described atFIG. 2, block204 andFIG. 8. Chart location module1106 further couples to chartlocation control module1112 and locates the color chart in the image using average horizontal and vertical scan lines as described atFIG. 2, blocks208-210 andFIG. 5. Chartlocation control module1112 couples to the verify module and controls thechart location system1100, in part, by selecting which reference color chart location module1106 searches for as described atFIG. 2, block206. Verifymodule1108 further couples tocolor profile module1110 and verifies the located color chart as described atFIG. 2, block216.Color profile module1110 develops a color profile based on the located color chart as described atFIG. 2,bock220.
• In practice, the methods described herein may constitute one or more programs made up of machine-executable instructions. Describing the method with reference to the flowchart inFIGS. 2,3,5,6AB, and8 enables one skilled in the art to develop such programs, including such instructions to carry out the operations (acts) represented by logical blocks on suitably configured machines (the processor of the machine executing the instructions from machine-readable media, such as RAM (e.g. DRAM), ROM, nonvolatile storage media (e.g. hard drive or CD-ROM), etc.). The machine-executable instructions may be written in a computer programming language or may be embodied in firmware logic or in hardware circuitry. If written in a programming language conforming to a recognized standard, such instructions can be executed on a variety of hardware platforms and for interface to a variety of operating systems. In addition, the present invention is not described with reference to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the invention as described herein. Furthermore, it is common in the art to speak of software, in one form or another (e.g., program, procedure, process, application, module, logic . . . ), as taking an action or causing a result. Such expressions are merely a shorthand way of saying that execution of the software by a machine causes the processor of the machine to perform an action or produce a result. It will be further appreciated that more or fewer processes may be incorporated into the methods illustrated in the flow diagrams without departing from the scope of the invention and that no particular order is implied by the arrangement of blocks shown and described herein.
• FIG. 12 showsseveral computer systems1200 that are coupled together through anetwork1202, such as the Internet. The term “Internet” as used herein refers to a network of networks which uses certain protocols, such as the TCP/IP protocol, and possibly other protocols such as the hypertext transfer protocol (HTTP) for hypertext markup language (HTML) documents that make up the World Wide Web (web). The physical connections of the Internet and the protocols and communication procedures of the Internet are well known to those of skill in the art. Access to theInternet1202 is typically provided by Internet service providers (ISP), such as theISPs1204 and1206. Users on client systems, such asclient computer systems1212,1216,1224, and12212 obtain access to the Internet through the Internet service providers, such asISPs1204 and1206. Access to the Internet allows users of the client computer systems to exchange information, receive and send e-mails, and view documents, such as documents which have been prepared in the HTML format. These documents are often provided by web servers, such asweb server1208 which is considered to be “on” the Internet. Often these web servers are provided by the ISPs, such asISP1204, although a computer system can be set up and connected to the Internet without that system being also an ISP as is well known in the art.
• Theweb server1208 is typically at least one computer system which operates as a server computer system and is configured to operate with the protocols of the World Wide Web and is coupled to the Internet. Optionally, theweb server1208 can be part of an ISP which provides access to the Internet for client systems. Theweb server1208 is shown coupled to theserver computer system1210 which itself is coupled toweb content1212, which can be considered a form of a media database. It will be appreciated that while twocomputer systems1208 and1210 are shown inFIG. 12, theweb server system1208 and theserver computer system1210 can be one computer system having different software components providing the web server functionality and the server functionality provided by theserver computer system1210 which will be described further below.
• Client computer systems1212,1216,1224, and12212 can each, with the appropriate web browsing software, view HTML pages provided by theweb server1208. TheISP1204 provides Internet connectivity to theclient computer system1212 through themodem interface1214 which can be considered part of theclient computer system1212. The client computer system can be a personal computer system, a network computer, a Web TV system, a handheld device, or other such computer system. Similarly, theISP1206 provides Internet connectivity forclient systems1216,1224, and1226, although as shown inFIG. 12, the connections are not the same for these three computer systems.Client computer system1216 is coupled through amodem interface1218 whileclient computer systems1224 and1226 are part of a LAN. WhileFIG. 12 shows theinterfaces1214 and1218 as generically as a “modem,” it will be appreciated that each of these interfaces can be an analog modem, ISDN modem, cable modem, satellite transmission interface, or other interfaces for coupling a computer system to other computer systems.Client computer systems1224 and1216 are coupled to aLAN1222 throughnetwork interfaces1230 and1232, which can be Ethernet network or other network interfaces. TheLAN1222 is also coupled to agateway computer system1220 which can provide firewall and other Internet related services for the local area network. Thisgateway computer system1220 is coupled to the ISP12012 to provide Internet connectivity to theclient computer systems1224 and12212. Thegateway computer system1220 can be a conventional server computer system. Also, theweb server system1208 can be a conventional server computer system.
• Alternatively, as well-known, aserver computer system1228 can be directly coupled to theLAN1222 through anetwork interface1234 to provide files12312 and other services to theclients1224,1226, without the need to connect to the Internet through thegateway system1220. Furthermore, any combination ofclient systems1212,1216,1224,1226 may be connected together in a peer-to-peernetwork using LAN1222,Internet1202 or a combination as a communications medium. Generally, a peer-to-peer network distributes data across a network of multiple machines for storage and retrieval without the use of a central server or servers. Thus, each peer network node may incorporate the functions of both the client and the server described above.
• The following description ofFIG. 13 is intended to provide an overview of computer hardware and other operating components suitable for performing the methods of the invention described above, but is not intended to limit the applicable environments. One of skill in the art will immediately appreciate that the embodiments of the invention can be practiced with other computer system configurations, including set-top boxes, hand-held devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, and the like. The embodiments of the invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network, such as peer-to-peer network infrastructure.
• FIG. 13 shows one example of a conventional computer system that can be used in one or more aspects of the invention. Thecomputer system1300 interfaces to external systems through the modem ornetwork interface1302. It will be appreciated that the modem ornetwork interface1302 can be considered to be part of thecomputer system1300. Thisinterface1302 can be an analog modem, ISDN modem, cable modem, token ring interface, satellite transmission interface, or other interfaces for coupling a computer system to other computer systems. Thecomputer system1302 includes aprocessing unit1304, which can be a conventional microprocessor such as an Intel Pentium microprocessor or Motorola Power PC microprocessor.Memory1308 is coupled to theprocessor1304 by abus1306.Memory1308 can be dynamic random access memory (DRAM) and can also include static RAM (SRAM). Thebus1306 couples theprocessor1304 to thememory1308 and also tonon-volatile storage1314 and to displaycontroller1310 and to the input/output (I/O)controller1316. Thedisplay controller1310 controls in the conventional manner a display on adisplay device1312 which can be a cathode ray tube (CRT) or liquid crystal display (LCD). The input/output devices1318 can include a keyboard, disk drives, printers, a scanner, and other input and output devices, including a mouse or other pointing device. Thedisplay controller1310 and the I/O controller1316 can be implemented with conventional well known technology. A digitalimage input device1320 can be a digital camera which is coupled to an I/O controller1316 in order to allow images from the digital camera to be input into thecomputer system1300. Thenon-volatile storage1314 is often a magnetic hard disk, an optical disk, or another form of storage for large amounts of data. Some of this data is often written, by a direct memory access process, intomemory1308 during execution of software in thecomputer system1300. One of skill in the art will immediately recognize that the terms “computer-readable medium” and “machine-readable medium” include any type of storage device that is accessible by theprocessor1304 or by other data processing systems such as cellular telephones or personal digital assistants or MP3 players, etc. and also encompass a carrier wave that encodes a data signal.
• Network computers are another type of computer system that can be used with the embodiments of the present invention. Network computers do not usually include a hard disk or other mass storage, and the executable programs are loaded from a network connection into thememory1308 for execution by theprocessor1304. A Web TV system, which is known in the art, is also considered to be a computer system according to the embodiments of the present invention, but it may lack some of the features shown inFIG. 13, such as certain input or output devices. A typical computer system will usually include at least a processor, memory, and a bus coupling the memory to the processor.
• It will be appreciated that thecomputer system1300 is one example of many possible computer systems, which have different architectures. For example, personal computers based on an Intel microprocessor often have multiple buses, one of which can be an input/output (I/O) bus for the peripherals and one that directly connects theprocessor1304 and the memory1308 (often referred to as a memory bus). The buses are connected together through bridge components that perform any necessary translation due to differing bus protocols.
• It will also be appreciated that thecomputer system1300 is controlled by operating system software, which includes a file management system, such as a disk operating system, which is part of the operating system software. One example of an operating system software with its associated file management system software is the family of operating systems known as MAC OS X from Apple Corporation in Cupertino, Calif., and their associated file management systems. The file management system is typically stored in thenon-volatile storage1314 and causes theprocessor1304 to execute the various acts required by the operating system to input and output data and to store data in memory, including storing files on thenon-volatile storage1314.
• It will be appreciated thatcomputer system1300 could be a camera, video camera, scanner, or any other type image acquisition system. In one embodiment, image acquisition system comprises a lens, image sensor or other hardware typically associated with a camera, video camera, or other type if image acquisition system.
• In the foregoing specification, the invention has been described with reference to specific exemplary embodiments thereof. It will be evident that various modifications may be made thereto without departing from the broader spirit and scope of the invention as set forth in the following claims. The specification and drawings are, accordingly, to be regarded in an illustrative sense rather than a restrictive sense.

Claims (21)

1. A computerized method comprising:

receiving an image, wherein the image comprises an embedded color chart;

locating the embedded color chart without intervention of a user;

verifying the embedded color chart; and

creating a color profile for the image based on the embedded color chart.

2. The computerized method ofclaim 1, wherein the locating comprises:

computing an average horizontal scan line comprising a first set of pulses;

fitting a second set of generated pulses corresponding to a reference color chart to the first set of pulses;

determining if the first set of pulses matches the second set of generated pulses;

computing an average vertical scan line comprising a third set of pulses;

fitting a fourth set of generated pulses corresponding to a reference color chart to the third set of pulses; and

determining if the third set of pulses matches the second set of generated pulses; and

determining the location of the embedded color chart in the image based on the first and third set of pulses.

3. The computerized method ofclaim 2, wherein said fitting a second set of generated pulses to a first set of pulses comprises matching the number pulses in the second set of generated pulses to the first set of pulses.

4. The computerized method ofclaim 1, further comprising:

determining an orientation angle of the embedded color chart; and

fixing the orientation of the image based on the orientation angle.

5. The computerized method ofclaim 4, wherein the determining the orientation angle comprises:

performing edge detection on the image;

measuring an set of vector angles, wherein each angle in the set of vector angles is an angle of the gradient vector for each edge in the image;

creating an angle image from the set of vector angles;

creating a histogram from the angle image;

reducing the histogram to one spike; and

determining the orientation angle by selecting the maximum value in the reduced histogram.

6. The computerized method ofclaim 1, further comprising:

calibrating the image with the color profile.

7. The computerized method ofclaim 6, further comprising:

receiving a set of other images; and

calibrating the set of other images with the color profile.

8. A computerized method comprising:

locating automatically an embedded color chart in an image;

determining an orientation angle of the embedded color chart in the image; and

fixing the orientation of the image based on the orientation angle.

9. The computerized method ofclaim 8, wherein the determining the orientation angle comprises:

performing edge detection on the image;

measuring a set of vector angles, wherein each angle in the set of vector angles is an angle of the gradient vector for each edge in the image;

creating an angle image from the set of vector angles;

creating a histogram from the angle image;

reducing the histogram to one spike; and

determining the orientation angle by selecting the maximum value in the reduced histogram.

10. The computerized method ofclaim 9, further comprising:

calibrating the image with the color profile.

11. The computerized method ofclaim 10, further comprising:

receiving a set of other images; and

calibrating the set of other images with the color profile.

12. A machine-readable medium having executable instructions to cause a processing system to perform a method comprising:

receiving an image, wherein the image comprises an embedded color chart;

locating the embedded color chart without intervention of a user;

verifying the embedded color chart; and

creating a color profile for the image based on the embedded color chart.

13. The machine-readable medium ofclaim 12, the method further comprising:

computing an average horizontal scan line comprising a first set of pulses;

fitting a second set of generated pulses corresponding to a reference color chart to the first set of pulses;

determining if the first set of pulses matches the second set of generated pulses;

computing an average vertical scan line comprising a third set of pulses;

fitting a fourth set of generated pulses corresponding to a reference color chart to the third set of pulses; and

determining if the third set of pulses matches the second set of generated pulses; and

determining the location of the embedded color chart in the image based on the first and third set of pulses.

14. The medium ofclaim 12, the method further comprising:

determining an orientation angle of the embedded color chart; and

fixing the orientation of the image based on the orientation angle.

15. The medium ofclaim 14, wherein the determining the orientation angle comprises:

performing edge detection on the image;

measuring a set of vector angles, wherein each angle in the set of vector angles is an angle of the gradient vector for each edge in the image;

creating an angle image from the set of vector angles;

creating a histogram from the angle image;

reducing the histogram to one spike; and

determining the orientation angle by selecting the maximum value in the reduced histogram.

16. The medium ofclaim 14, the method further comprising:

calibrating the image with the color profile.

17. The medium ofclaim 16, further comprising:

receiving a set of other images; and

calibrating the set of other images with the color profile.

18. A machine readable medium having executable instructions to cause a processing system to perform a method comprising:

locating automatically an embedded color chart in an image;

determining an orientation angle of the embedded color chart in the image; and

fixing the orientation of the image based on the orientation angle.

19. The medium ofclaim 18, wherein the determining the orientation angle comprises:

performing edge detection on the image;

measuring a set of vector angles, wherein each angle in the set of vector angles is an angle of the gradient vector for each edge in the image;

creating an angle image from the set of vector angles;

creating a histogram from the angle image;

reducing the histogram to one spike; and

determining the orientation angle by selecting the maximum value in the reduced histogram.

20. The medium ofclaim 19, the method further comprising:

calibrating the image with the color profile.

21. The medium ofclaim 20, the method further comprising:

receiving a set of other images; and

calibrating the set of other images with the color profile.

Images