WO2021155153A1

WO2021155153A1 - Computer-based systems configured for reference-free color correction and methods thereof

Info

Publication number: WO2021155153A1
Application number: PCT/US2021/015716
Authority: WO
Inventors: Kristian Sandberg; JR. L. Dean RISINGER
Original assignee: Reliant Immune Diagnostics, Inc.
Priority date: 2020-01-31
Filing date: 2021-01-29
Publication date: 2021-08-05

Abstract

Systems and methods of present disclosure enable reference free color correction with a processing system (110) by receiving a digital image depicting a color-coded subject and determining color-space values associated with color-space channels for each pixel. An area-of-interest (AoI) is determined in a subject depicted in the digital image based on extracted features. A color patch is determined within each AoI based on a subregion of each AoI having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each AoI. A patch of a known color within the color-coded subject having a similar size as each color patch is determined. A color-based analysis model is used to determine a color-based result associated with the AoI based on a difference between each color patch and the calibration patch.

Description

COMPUTER-BASED SYSTEMS CONFIGURED FOR REFERENCE-FREE COLOR CORRECTION AND METHODS THEREOF

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to United States Provisional Patent Application number 62/968,455 filed on 31 January 2020, which is herein incorporated by reference in its entirety.

COPYRIGHT NOTICE

[0002] A portion of the disclosure of this patent document contains material that is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all copyright rights whatsoever. The following notice applies to the software and data as described below and in drawings that form a part of this document: Copyright, Reliant Immune Diagnostics, All Rights Reserved.

FIELD OF TECHNOLOGY

[0003] The present disclosure generally relates to improved computer-based platforms, systems, devices, components and/or objects configured for reference-free color correction, e.g., in digital imagery, for accurate color measurements, image analysis, or other applications, and methods thereof.

BACKGROUND OF TECHNOLOGY

[0004] Analysis of imagery via automated methods can be very difficult due to inaccuracies in representations of the colors in a captured scene, such as due to lighting variations, glare and reflections, dust and other interferences. In some applications, reducing inaccuracies can facilitate improved analysis of the imagery. However, color correction can often require the use of various color reference charts that must be included with the image and objects being measure. However, such color reference charts can be large, making them difficult to include with the objects of the image. Moreover, the color reference charts are subject to the same interferences, including glare, shadows, reflections, among others, thus reducing the accuracy and usefulness. SUMMARY OF DESCRIBED SUBJECT MATTER

[0005] In some embodiments, the present disclosure provides an illustrative technically improved computer-based method that includes at least the following steps of receiving, by at least one processor, a digital image depicting a color-coded subject; determining, by the at least one processor, at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determining, by the at least one processor, at least one area- of-interest in a subject depicted in the digital image based on extracted features using edge detection; determining, by the at least one processor, a color patch within each area-of-interest of the at least one area-of-interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each area-of-interest; determining, by the at least one processor, a calibration patch of a known color within the color-coded subject having a same size as each color patch; utilizing, by the at least one processor, a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color; and causing to compute, by the at least one processor, the color-based result associated with the at least one area-of-interest for use in further analysis.

[0006] In some embodiments, the present disclosure provides an illustrative technically improved computer-based system that includes at least the following components of at least one processor in communication with a non-transitory memory having instructions stored thereon, the at least one processor configured to execute the instructions to perform steps. The steps comprise: receive a digital image depicting a color-coded subject; determine at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determine at least one area-of-interest in a subject depicted in the digital image based on extracted features; determine a color patch within each area-of-interest of the at least one area-of-interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each area-of-interest; determine a calibration patch of a known color within the color-coded subject having a same size as each color patch; and utilize a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color. [0007] In some embodiments, the present disclosure provides an illustrative technically improved computer-based product that includes at least the following components of a non- transitory computer-readable storage medium with an executable program stored thereon, wherein the program instructs at least one processor to perform the following steps: receiving a digital image depicting a color-coded subject; determining at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determining at least one area-of-interest in a subject depicted in the digital image based on extracted features; determining a color patch within each area-of-interest of the at least one area-of- interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each area-of-interest; determining a calibration patch of a known color within the color-coded subject having a similar size as each color patch; utilizing a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color; and causing to display the color-based result associated with the at least one area-of-interest on a screen of at least one computing device associated with at least one user.

BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Various embodiments of the present disclosure can be further explained with reference to the attached drawings, wherein like structures are referred to by like numerals throughout the several views. The drawings shown are not necessarily to scale, with emphasis instead generally being placed upon illustrating the principles of the present disclosure. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ one or more illustrative embodiments.

[0009] FIGS. 1-11 show one or more schematic flow diagrams, certain computer-based architectures, and/or screenshots of various specialized graphical user interfaces which are illustrative of some illustrative aspects of at least some embodiments of the present disclosure.

DETAILED DESCRIPTION

[0010] Various detailed embodiments of the present disclosure, taken in conjunction with the accompanying figures, are disclosed herein; however, it is to be understood that the disclosed embodiments are merely illustrative. In addition, each of the examples given in connection with the various embodiments of the present disclosure is intended to be illustrative, and not restrictive.

[0011] Throughout the specification, the following terms take the meanings explicitly associated herein, unless the context clearly dictates otherwise. The phrases “in one embodiment” and “in some embodiments” as used herein do not necessarily refer to the same embodiment(s), though it may. Furthermore, the phrases “in another embodiment” and “in some other embodiments” as used herein do not necessarily refer to a different embodiment, although it may. Thus, as described below, various embodiments may be readily combined, without departing from the scope or spirit of the present disclosure.

[0012] In addition, the term "based on" is not exclusive and allows for being based on additional factors not described, unless the context clearly dictates otherwise. In addition, throughout the specification, the meaning of "a," "an," and "the" include plural references. The meaning of "in" includes "in" and "on."

[0013] Figures 1 through 11 illustrate systems and methods of reference-free color correction in automated systems. The following embodiments provide technical solutions and technical improvements that overcome technical problems, drawbacks and/or deficiencies in the technical fields involving color measurement for image representation, image recognition, and other tasks associated with applications such as color-based tests. As explained in more detail below, technical solutions and technical improvements herein include aspects of improved color correction algorithms and color-based test devices that facilitate accurate color measurements in lower quality images influenced by imperfections associated with mobile cameras, mobile software, ambient lighting, shadows, and other interferences and sources of color inaccuracies in images. Based on such technical features, further technical benefits become available to users and operators of these systems and methods. Moreover, various practical applications of the disclosed technology are also described, which provide further practical benefits to users and operators that are also new and useful improvements in the art.

[0014] FIG. 1 is a block diagram of another illustrative computer-based testing system and platform configured for reference-free color correction for color-based analysis in accordance with one or more embodiments of the present disclosure.

[0015] Quantitative color-based analyses (such as medical tests including urinary tract infection (UTI) tests, among others) may be based on accurate measurements of color. To achieve accurate color-based analysis results, therefore, a color correction step is often necessary to account for differences in mobile cameras, software, and ambient lighting that may affect the true colors in the image.

[0016] In some embodiments, a color correction algorithm is employed that uses a patch of the subject (or other white element) from the image to determine the appropriate correction to apply to the areas-of-interest in the image. In some embodiments, the correction is computed by computing a difference measure between the areas-of-interest and the calibration patch of the known color in an appropriate color space and then applying that difference to the areas- of-interest to obtain their true colors. The difference measure itself can also be used directly for further computation, e.g. as input to a Support Vector Machine (SVM) classifier to determine the quantified result of a medical test.

[0017] In some embodiments, to better counteract the effects of ambient lighting, camera sensor artifacts and noise, and camera or mobile device 102 image processing effects on an image 101, a color testing platform 100 may employ a color analysis system 110 that automatically corrects for color imperfects in the received image 101 without a need for a reference color chart or other device. Rather, in some embodiments, the color analysis system 110 may utilize calibration patches of the known colors within the image 101 itself as reference points for characterizing colors of colored patches, such as diagnostic areas-of-interest, of the image 101.

[0018] In some embodiments, the color analysis system 110 includes components for receiving the image 101 from the camera sensor 102, converting the image to a signal, e.g., according to a color space, identifying and extracting patches representative of areas-of-interest depicted in the image 101, and classifying the patches based on color. In some embodiments, the classification may include a color-based recommendation associated with a color of each patch. In some embodiments, the color analysis system 110 may represent the color of each area-of- interest using an appropriate color space, such as, e.g., YUV color space, YPbPr color space, YCbCr color space, Adobe RGB™ color space, sRGB color space, CIELAB color space, CIEXYZ color space, CIELUV color space, CIEUVW color space, CIE 1931 XYZ color space, CMYK color space, YIQ color space, xvYCC color space, HSV color space, HSL color space, TSL color space, ICtCp color space, or any other suitable color space for representing pixels of the image 101.

[0019] For example, the image 101 may depict a subject including a diagnostic test strip having areas-of-interest including test pads with reagents to react with target compounds and change color according to a concentration of the target compound in, e.g., a solution. In some embodiments, the diagnostic test strip may include, e.g., a urine-based test strip for a urinary tract infection including, e.g., two test pads: a test pad with a reagent for detecting leukocytes and a test pad with a reagent for detecting nitrites. In such an example of a diagnostic test strip, the color of each test pad indicates a concentration of, e.g., leukocytes and nitrites. However, the test strip may be for diagnosis of any condition suitable for testing with test strips including urine, blood, saliva and other fluids. For example, the test strip may include test pads for, e.g., blood glucose, hemoglobin, ketones, proteins, pH of the fluid, among others based on the condition being tested for.

[0020] Based on the color, the color analysis system 110 may identify color-based analysis results of the subject based on the color of the areas-of-interest in the image 101. These color- based analysis results may then be provided as a recommendation. For example, in the above example regarding a diagnostic test strip, the color-based analysis results can include a diagnosis based on the color of the test pads, which may be provided as a recommendation for a diagnosis to, e.g., a user, patient care provider, electronic medical record, administrator, or among others by, e.g., communicating data representative of the diagnosis recommendation to a computing device.

[0021] In some embodiments, the computing device may include, e.g., a mobile device 104, such as a smartphone, tablet, personal digital assistance (PDA), a smartwatch or other mobile device, a user computing device 105 such as a desktop computer, a laptop computer, or other computing device, or a data storage system 103, such as a database, a hard-drive, a solid-state drive, a cloud storage platform, a server storage system, or other suitable data storage system. Thus, the color analysis system 110 may automatically facilitate quick and accurate analysis of a subject color.

[0022] In some embodiments, to formulate the color-based analysis, as described above, the color analysis system 110 may perform tasks including converting the image to a signal, e.g., according to a color space, identifying and extracting patches representative of areas-of-interest depicted in the image 101, and classifying the patches based on color. As such, the color analysis system 110 may include a processing system 112 to implement instructions associated with algorithms, models, engines and other hardware and software components for performing each of the above tasks. [0023] In some embodiments, the processing system 112 may include one or more computing processing devices, such as, e.g., a hardware logic circuit, for example an application specific integrated circuit (ASIC) and a programmable logic, or such as a computing device, for example, a microcomputer or microcontroller that include a programmable microprocessor. In some embodiments, the processing device may include data-processing capacity provided by the microprocessor. In some embodiments, the microprocessor may include memory, processing, interface resources, controllers, and counters. In some embodiments, the microprocessor may also include one or more programs stored in memory.

[0024] In some embodiments, the processing system 112 may be configured to implement an image-to-signal engine 114, a feature extraction engine 116 and a color analysis engine 118. As used herein, the terms “computer engine” and “engine”, and “model” identify at least one software component and/or a combination of at least one software component and at least one hardware component which are designed/programmed/configured to manage/control other software and/or hardware components (such as the libraries, software development kits (SDKs), objects, etc.). Each of the image-to-signal engine 114, the feature extraction engine 116 and the color analysis engine 118 may therefore be formed of software components (e.g., logic, algorithms, machine learning models, or other software components), hardware components (e.g., processors, memory, buffers, storage, cache, etc.), or combinations thereof.

[0025] In some embodiments, the image-to-signal engine 114 is configured to analyze the image 101 using the processing system 112 to convert an image file storing a representation of the image 101 into an image signal. For example, the image file may be in a lossy or lossless raster format such as, e.g., Joint Photographic Experts Group (JPEG), Tagged Image File Format (TIFF), Portable Network Graphics (PNG), Exchangeable image file format (Exif), Graphics Interchange Format (GIF), Windows bitmap (BMP), portable pixmap (PPM) or other formats from the Netpbm format family, WebP, High Efficiency Image File Format (HEIF), BAT, Better Portable Graphics (BPG), or a lossy or lossless vector format such as, Computer Graphics Metafile (CGM), Gerber (RS-274X), Scalable Vector Graphics (SVG), or other formats and combinations thereof. The file format of the image 101 may depend on the image capture device 102, such as the format used by a digital camera or smartphone, which can vary from device to device.

[0026] In some embodiments, the image-to-signal engine 114 ingests the file of the image 101 and generates a signal using a selected color space. In some embodiments, the color space is predefined according to the configuration of the color analysis system 110. However, in some embodiments, the color space can be selected by, e.g., a user or selected automatically based on the format of the file for the image 101. The image-to-signal engine 114 creates the color- space signal by analyzing each pixel of the image 101 and measuring values for the pixel for each channel of the color space. For example, in some embodiments, the color space is the YUV color space. The YUV color space refers to a color space having a luminance channel (Y) or luma channel (Y’), a blue projection channel (U) and a red projection channel (V). In some embodiments, the YUV color space takes the form of YCbCr, where Cb is a blue- difference chroma channel and Cr and red-difference chroma channel. The YUV color space may alternatively take the form of YPbPr, where Pb is the difference between the blue projection and the luma and Pr is the difference between the red projection and the luma. Thus, in some embodiments, the image-to-signal engine 114 generates a three-channel color space measurement for each pixel in the image 101. However, other color spaces are also contemplated, such as those described above, that may have more, less or the same number of channels as YUV.

[0027] In some embodiments, the signal associated with the color-space measurements of the image 101 may then be ingested by the feature extraction engine 116 via the processing system 112. In some embodiments, the feature extraction engine 116 identifies and extracts portions of the image 101 that represent the areas-of-interest. The color space values of the extracted portions, or patches, of the areas-of-interest can then be used to represent the color of the areas- of-interest in general.

[0028] In some embodiments, to extract the portions of the areas-of-interest, the feature extraction engine 116 first identifies the areas-of-interest on the subject. In some embodiments, the areas-of-interest are identified using a suitable image recognition technique, including, e.g., logic based algorithms, machine learning algorithms (e.g., a neural network, or other machine learning algorithms and combinations thereof), predetermined locations within the image, or other image recognition technique and combinations thereof.

[0029] In some embodiments, the present invention employs a feature detection algorithm with matching of geometric feature configurations to predetermined shapes. For example, the feature extraction engine 116 may identify edges, key-points, contours, or other geometric features formed in the digital image. For example, edge detection techniques may be utilized, such as, e.g., a Sobel edge detector, a Radon transform, orientation fields utilizing transitions between colors pixels or between light and dark pixels or others and combinations thereof. In some embodiments, the geometric features are compared against a predetermined library of shapes of areas-of-interest and of the subject (e.g., square and rectangle pads within a range of scale sizes, or other shapes and orientations). However, any suitable type of feature detection may be employed to identify the areas-of-interest, including shape-based, key-point based, semantic analysis-based or any other suitable technique.

[0030] In some embodiments, using the identified areas-of-interest and subject, the feature extraction engine 116 can extract area-of-interest patches from within the area of the areas-of- interest in the image signal to represent the color of each area-of-interest. For example, in some embodiments, the feature extraction engine 116 may determine the mean or median value for each channel of the color space for the pixels within the area-of-interest area identified above. However, in some embodiments, the area-of-interest patch is smaller the size of the corresponding area-of-interest to reduce the risk of color variations caused by, e.g., shadows, glare, dust, or other artifacts. Thus, the feature extraction engine 116 may extract an area-of- interest patch from within the area-of-interest area that includes a portion of the area-of-interest having a particular size or proportion of the area-of-interest, such as, e.g., two thirds of the size of the area-of-interest area, one half of the size of the area-of-interest area, one third of the size of the area-of-interest area, one quarter of the size of the area-of-interest area, or other proportion.

[0031] In some embodiments, the area-of-interest patch may be selected according to a portion having the particular size or proportion with the most uniform color according to the channel values of the color space of the image signal. For example, the most uniform color portion may be determined according to a minimum difference between the means or medians of the maxima and minima of the color space values for pixels within the area-of-interest patch relative to any other portion within the area of the area-of-interest. To do so, the maxima and minima of the color space values for pixels within the area-of-interest patch may be determined, and the mean and/or median of each maxima and minima may then be computed. By finding a portion of the area-of-interest having a minimum of the difference of the means and/or medians of the maxima and minima of the color space values between the portion and any other portion of the area-of-interest, the portion may be identified as the most uniform in color.

[0032] In some embodiments, even when identifying area-of-interest patches with the most uniform color, the image 101 and resulting image signal may nevertheless include more global artifacts effect the areas-of-interest and subj ect on the whole, such as, e.g., glare, shadow, noise, image processing alterations, among other artifacts that cause the representation of the color of the subject in the image 101 and the image signal to deviate from the true colors. These inaccuracies make color measurements based on the image 101 difficult and inaccurate. However, in some embodiments, to mitigate the inaccuracies in the image 101 and resulting image signal, the feature extraction engine 116 may also extract a reference feature from the image signal. For example, the subject may be formed of a known color, such as, e.g., white, though other colors are also contemplated. Accordingly, the feature extraction engine 116 may identify a subject patch including a portion of the subject outside of the area-of-interest area or area-of-interest areas. In some embodiments, the subject patch may form a patch of the predetermined color that provides a point of reference with which to compare the area-of- interest patches. In some embodiments, the subject patch may have a same size as the area-of- interest patches, however other sizes are also contemplated.

[0033] In some embodiments, the color analysis engine 118 may ingest the extracted features including the area-of-interest patches and the subject patch to determine a diagnostic recommendation including an analysis of the colors of the areas-of-interest in the subject. In some embodiments, the color analysis engine 118 uses the subject patch in conjunction with the area-of-interest patches to recharacterize the color space values of each area-of-interest patch. For example, the color analysis engine 118 may determine a difference between the color space values (e.g., the value of each channel of the color space) between each area-of- interest patch and the subject patch. In some embodiments, the difference is between the average color space values across each of the area-of-interest patches and the mean and/or median color space values of the subject patch. However, the color analysis engine 118 may modify the area-of-interest patches with the subject patch in other ways as well, including using, e.g., a weighted sum, a weighted division, a division, a weighted product, a product, among others and combinations thereof.

[0034] In some embodiments, the color analysis engine 118 determined the difference between each area-of-interest patch and the subject patch by first determining the mean and/or median color space values for each patch. In particular, for each patch, the color analysis engine 118 extracts the values for each channel of the color space and then averages each channel across all pixels in the patch. Thus, the color analysis engine 118 generates color space values that include a mean and/or median of each color space channel for each patch. The mean and/or median color space values of the subject patch are then subtracted from the mean and/or median color space values of each area-of-interest to determine a color difference for each area-of- interest patch. [0035] In some embodiments, the color analysis engine 118 may first subtract from each pixel in each area-of-interest patch the color space values of a corresponding pixel in the subject patch to form pixel-wise color difference values for each color space channel for each pixel of each area-of-interest patch. Then, for each area-of-interest patch, the color analysis engine 118 may determine the mean and/or median color across all pixels in the patch by averaging the channel values of each pixel in the patch to determine the color difference for the patch.

[0036] Using either technique to determine the color difference for each patch, the color analysis engine 118 may then analyze the color difference to assess the color-based results. For example, where the subject is the diagnostic test strip, the color analysis engine 118 may analyze the color difference between patches of the test pads and a calibration patch of a known color (e.g., white or any other suitable color) of the test strip to identify a matching test result (e.g., positive or negative). In some embodiments, the color analysis engine 118 may match the color difference for each patch to predetermined color difference profiles for each possible result of the color-based analysis. For example, channel values of the color difference may be compared to color difference channel values of a diagnostic test strip positive result, and the test result may be determined based on whether there is a match.

[0037] However, matching to predetermined profiles assumes no or little error in the color differences. In some embodiments, to better account for potential error, the color analysis engine 118 may utilize a machine learning model to, e.g., classify or cluster the color differences based on prior training. Thus, the color analysis engine 118 may recognize a similarity to prior or ground-truth outcomes rather than an explicit match, facilitating accurate results even where the color in the image 101 is not a perfect match to channel values or a range of channel values of a particular outcome.

[0038] In some embodiments, by using the color difference channel values rather than absolute channel values, the color analysis engine 118 can remove global artifacts and inaccuracies that effect the color representation of a large portion of the subject. This is because the global artifacts and inaccuracies are present in the subject patch as well as the area-of-interest patches. Thus, by subtracting subject patch channel values from area-of-interest patch channel values, the influence on those channel values by the global artifacts and inaccuracies are also subtracted from the area-of-interest patch channel values. Accordingly, measurement of the color of the areas-of-interest can be more accurately and reliably performed. [0039] While the above description uses diagnostic subjects as an example for the color analysis system 110, the color analysis system 110 or other system employing the image-to- signal engine 114, feature extraction engine 116 and color analysis engine 118 may be utilized to perform color measurement in any suitable application where analysis based on the color of an area of an image is beneficial. For example, chromatography tests may utilize the color analysis system 110 to better analyze the chromatograph results. Other applications are also contemplated.

[0040] FIG. 2 is a block diagram of another illustrative computer-based system and platform including a test analysis system utilizing reference-free color correction in accordance with one or more embodiments of the present disclosure.

[0041] In some embodiments, a color analysis system 210 utilizes an image signal 202 representing a color measurement subject for which color measurement is to be performed. For example, the subject may be a diagnostic test strip having, e.g., test pads including a reagent that reacts to compounds in a fluid causing the pads to change colors in accordance with a concentration of the compounds.

[0042] Similar to the signal described above, the image signal 202 may represent the subject using pixel-level values for each channel of a color space. For example, each pixel in an image of the subject is represented in the image signal 202 with a set of color channel values of a color space, including a color space such as those described above. However, the channel values of the image signal 202 may result from an image having inaccuracies due to, e.g., image processing color modifications, compression artifacts, lens tint, shadows, glare, ambient lighting variation, white balance and metering errors of the image capture device, among other color inaccuracies. Such inaccuracies reduce the accuracy and usefulness of color measurement to generate the image signal 202. As a result, in situations where color accuracy is important to analysis of an image, such as measuring the color of a subject of the image. For example, measurement may include interpreting subject results in accordance with the color of the areas- of-interest, where the color inaccuracy can lead to inaccurate color-based analysis. In some embodiments, the color analysis system 210 may compensate for channel value inaccuracies relative to the true color of the subject with a reference free color correction by employing a feature extraction engine 220 and a color analysis engine 250 to determine color results 203 without, e.g., any color reference chart or other color correction tools. [0043] In some embodiments, the feature extraction engine 220 includes a subject extraction model 230 and a patch extraction model 240 to identify and isolate a subject represented in the image signal 202 and the areas-of-interest of the subject, respectively.

[0044] In some embodiments, the subject extraction model 230 utilizes a series of algorithmic steps to identify the portions of the image, as represented in the image signal 202 by the channel values of the color space, that correspond with a subject. In some embodiments, the subject extraction model 230 includes an image segmentation algorithm for segmenting the image signal 202 according to structures represented therein based on the channel values of each pixel. In some embodiments, the image segmentation algorithm may include, e.g., Active Contours, Level Set methods, and the Watershed Transform, Orientation Field Transforms, the Hough Transform, or other image segmentation techniques and combinations thereof. For example, the subject extraction model 230 can perform, e.g., a per-pixel analysis of variations in channel values with respect to neighboring pixels, to leverage contrast in the image signal 202 and identify light versus dark colored shapes. The shapes can then be matched to a library of shapes- of-interest corresponding to the subject and the areas-of-interest.

[0045] In some embodiments, upon image segmentation, the feature extraction model 230 can extract the pixels of the image signal 202 associated with the shapes-of-interest including the subject and the areas-of-interest. For example, the subject extraction model 230 may discard pixels that not part of the subject or the areas-of-interest. The subject extraction model 230 may then assign each pixel a label as subject pixel or area-of-interest pixel based on its location in the image signal 202 relative to the extracted shapes. As a result, the extracted subject and areas-of-interest, or any other shapes-of-interest in the subject and represented in the image signal 202 may be analyzed in isolation from the remainder of the image signal 202.

[0046] In some embodiments, the extracted subject and area-of-interest pixels of the image signal 202 can be analyzed to identify and extract a patch of representative pixels that are representative of the color of each of the subject and areas-of-interest. For example, the image signal 202 may be affected by color variations due to, e.g., environmental noise (e.g., shadows, glare, occlusions, etc.), and signal noise (e.g., processing noise, compression artifacts, banding, etc.), among other factors. Thus, each feature of the image signal 202, such as the subject, the areas-of-interest, and other features, may vary in channel values across each feature in ways that do not match the real life colors of the features on the subject. For example, a shadow may result in darker colors in the image signal 202 for a portion of one of the areas-of-interest, while the remainder of that area-of-interest may be unshadowed, and thus have channel values representing lighter coloring. Thus, the patch extraction model 240 extracts a portion of each feature, such as the subject and the areas-of-interest, having a uniform color that most closely matches a true-to4ife color of the subject without the color variations.

[0047] In some embodiments, for each feature of the image signal 202, the patch extraction model 240 may identify every possible patch of pixels. The patch extraction model 240 may then compare the channel values of the pixels in each patch to each other patch of the feature. However, comparing each pixel of each patch to each pixel of every other patch may result in inefficient processing and long processing times. To reduce the time and resources of identifying the representative patch for each feature, the channel values for each pixel in each patch may be combined to represent the overall color of each patch. For example, the patch extraction model 240 may determine, e.g., the sum, the product, the mean, the median, the standard deviation, the variability, etc. of each channel value of the pixels in each patch to generate a single set of channel values representing the patch. The channel values representing each patch may then be used to identify the patch least influenced by color variations in the image signal 202. For example, the patch in which, e.g., the difference between the mean and/or median of the of the maxima and minima of each of the color channels is minimized, the variability of each of the color channels is minimized, the standard deviation of each of the color channels is minimized, the sum of each of the color channels is minimized, the product of each of the color channels is minimized, etc. to identify a sub-region of the feature that is most uniform in color.

[0048] In some embodiments, for each feature (e.g., the subject and each area-of-interest), the patch extraction model 240 may identify and label the pixels associated with the most uniform patch of pixels. In some embodiments, the patch extraction model 240 may then determine, e.g., a mean and/or median color space coordinate formed of the mean and/or median of each channel value of the pixels within the most uniform patch of each feature. However, where the channel values representing the most uniform patch was previously determined, as described above, as the mean and/or median of channel values, the patch extraction model 240 may collect the channel values representing the most uniform patch to form the color space coordinates representative of the color of the corresponding feature. In some embodiments, the color space coordinates of each feature may then be passed to the color analysis engine 250 to determine the color results 203 according to the color of each area-of-interest.

[0049] In some embodiments, the color analysis engine 250 includes a normalization model 260 and a color-based measurement model 270 to, respectively, normalize the color space coordinates representing each area-of-interest and classify the normalized color space coordinates as a diagnostic test result 203.

[0050] In some embodiments, the normalization model 260 compensates for color inaccuracies of the image signal 202 to normalize or correct the color space coordinates representing each area-of-interest without any reference to additional tools or devices such as color reference charts. Rather, the normalization model 260 may use the subject and area-of-interest patches themselves to self-referentially compensate for color inaccuracies. For example, the subject may be configured with a known or predetermined color, such as, e.g., white, although other colors are contemplated. The subject patch may, therefore, be used to compensate for inaccuracies in the color space coordinates of the area-of-interest patches based on deviation from the known or predetermined color. For example, where the subject is e.g., white, blue, green, red or any other suitable color, the channel values representing the colors of an area-of- interest are proportional to the difference in channel values between the area-of-interest and the subject. Accordingly, in some embodiments, the normalization model 260 utilizes the subject patch as a common, known reference point with which to characterize the color of each area-of-interest patch.

[0051] In some embodiments, this characterization takes the form of the difference between each area-of-interest patch and the subject patch to generate for each area-of-interest patch normalized or corrected color space coordinates. Because the predetermined color of the subject patch is represented by the image signal 202 to include any color inaccuracies due to the imaging device, image processing or environment, by subtracting the subject patch color space coordinates from the area-of-interest patch color space coordinates, those inaccuracies are also removed. Thus, the resulting coordinates may be proportional to an accurate color of each area-of-interest, even if the resulting coordinates are not exactly equivalent to the area-of- interest color.

[0052] In some embodiments, the normalized or corrected color coordinates for each area-of- interest patch may then be classified to indicate a particular result of associated color-based analysis using the color-based measurement model 270. In some embodiments, the color-based measurement model 270 includes a machine learning classification model, however, logic or mathematical formula-based and matching-based algorithms are also contemplated.

[0053] In some embodiments, the machine learning classification model may be chosen from, but not limited to, decision trees, boosting (e.g., Xgboost), support-vector machines, neural networks, nearest neighbor algorithms, Naive Bayes, bagging, random forests, and the like. In some embodiments and, optionally, in combination of any embodiment described above or below, an illustrative neutral network technique may be one of, without limitation, feedforward neural network, radial basis function network, recurrent neural network, convolutional network (e.g., U-net) or other suitable network. In some embodiments and, optionally, in combination of any embodiment described above or below, an illustrative implementation of Neural Network may be executed as follows: i) Define Neural Network architecture/model, ii) Transfer the input data to the illustrative neural network model, iii) Train the illustrative model incrementally, iv) determine the accuracy for a specific number of timesteps, v) apply the illustrative trained model to process the newly-received input data, vi) optionally and in parallel, continue to train the illustrative trained model with a predetermined periodicity.

[0054] In some embodiments and, optionally, in combination of any embodiment described above or below, the illustrative trained neural network model may specify a neural network by at least a neural network topology, a series of activation functions, and connection weights. For example, the topology of a neural network may include a configuration of nodes of the neural network and connections between such nodes. In some embodiments and, optionally, in combination of any embodiment described above or below, the illustrative trained neural network model may also be specified to include other parameters, including but not limited to, bias values, functions and aggregation functions. For example, an activation function of a node may be a step function, sine function, continuous or piecewise linear function, sigmoid function, hyperbolic tangent function, or other type of mathematical function that represents a threshold at which the node is activated. In some embodiments and, optionally, in combination of any embodiment described above or below, the illustrative aggregation function may be a mathematical function that combines (e.g., sum, product, etc.) input signals to the node. In some embodiments and, optionally, in combination of any embodiment described above or below, an output of the illustrative aggregation function may be used as input to the illustrative activation function. In some embodiments and, optionally, in combination of any embodiment described above or below, the bias may be a constant value or function that may be used by the aggregation function and/or the activation function to make the node more or less likely to be activated. [0055] In some embodiments, each area-of-interest is associated with a particular color-based test. For example, the color-based test may leverage a color changing reagent based on the presence of a particular compound, where the color of the area-of-interest indicates the concentration of the compound present in a sample. Depending on the substance being tested for, color result 203 may include a classification selected from a set of possible result classifications. For example, a nitrite test may have two possible result classifications, such as positive (N+) or negative (N-). Leukocyte tests on the other hand, may have up to five or more possible result classifications, such as, negative (L-), trace (L+-), and three degrees of positive (L+, L++ or L+++).

[0056] In some embodiments, the color-based measurement model 270 is trained to predict a result classification for each area-of-interest based on the normalized color space coordinates of the associated area-of-interest patch. Accordingly, the color-based measurement model 270 may be trained for each test type to receive as input features each channel value of the normalized color space coordinates for an area-of-interest patch associated with the test type and generate a label classifying a result classification of the possible result classifications for the test type.

[0057] In some embodiments, the color-based measurement model 270 may include a different classifier for each test type, and each area-of-interest may correspond to a test type. Thus, the color-based measurement model 270 may select and implement a classifier for each area-of- interest based on each area-of-interest’ s associated test type. In some embodiments, the test types associated with each area-of-interest may be, e.g., automatically recognized using, e.g., indicia on the subject or areas-of-interest, user selected, or automatically selected.

[0058] As a result, in some embodiments, the color-based measurement model 270 receives the normalized color space coordinates for each area-of-interest and applies a particular classifier associated with the color-based analysis for each area-of-interest. The color-based measurement model 270 may then automatically classify the normalized color space coordinates according to a selection of possible result classifications. The color-based measurement model 270 and color analysis system 210 may then output, e.g., to a user, data storage, or combination thereof, a color result 203 indicating the result classifications for each area-of-interest on the subject represented by the image signal 202. [0059] FIG. 3 is a block diagram of another illustrative computer-based system and platform including a feature extraction engine for reference-free color correction and image analysis in accordance with one or more embodiments of the present disclosure.

[0060] In some embodiments, an image signal 302 including channel values of a color space for each pixel of an image may be analyzed by a feature extraction engine 320 to identify and extract color patches 322 associated with each area-of-interest of a subject. In some embodiments, the feature extraction engine 320 utilizes a subject extraction model 330 and patch extraction model 340 to identify and extract the patches 322.

[0061] In some embodiments, the subject extraction model 330 ingests the image signal 302 and applies a geometry detection engine 332 to identify matching geometry. In some embodiments, the subject extraction model 330 searches for geometric features, such as, e.g., edges and lines, key-points (e.g., comers), shapes, patterns, or other features of the image. For example, using color differences between nearby pixels, gradients, step-changes, and other color and contrast relationships may be determined and used to identify shapes or parts of shapes. In some embodiments, the geometry detection engine 332 may identify where regions of the image change from light to dark and dark to light, one color to another color, or other variations in the color-space of regions of the image. The locations of these variations facilitate identifying a rough estimate of the location of the areas-of-interest. These variations may be used by the geometry detection engine 332 to determine geometries represented in the image using, e.g., shape-based techniques, key-point based techniques, semantic analysis-based techniques or any other suitable of technique.

[0062] In some embodiments, the pixels for the geometric features identified by the geometry detection engine 332 are passed to a recognition algorithm 334. In some embodiments, the subject has a known geometry. Thus, the areas-of-interest can be identified using a matching of the features to a known library of features identifying the areas-of-interest. For example, the two areas-of-interest may be squares, and thus generate four lines of known separation distance. Thus, the areas-of-interest may be identified by looking for the four lines. Thus, the recognition algorithm 334 can match shapes formed by the geometric features to the known shapes of the subject and recognize the areas-of-interest and the subject. Pixels may then be assigned with labels identifying whether they are within an area-of-interest or the subject. The areas-of- interest and subject may then each be extracted from the image signal 302. [0063] In some embodiments, the extracted areas-of-interest and subject are ingested by the patch extraction model 340 to identify and extract a sub-region of each area-of-interest and the subject that is representative of the most uniform color.

[0064] In some embodiments, the patch extraction model 340 utilizes a patch extractor 342 to identify the patch of each area-of-interest having the most uniform color. Within each area-of- interest, the patch extractor 342 identifies a sub-region within which the difference between the mean and/or median, or a weighted combination thereof of the maxima and minima across the color channels is minimized. In some embodiments, the sub-region is predetermined to have a diameter of about two thirds of the full diameter of the area-of-interest. As a result, the sub-region is most likely to be a region of the area-of-interest with the most uniform color. In some embodiments, the patch extractor 342 may then extract the sub-region as an area-of- interest patch by discarding the remainder of the area-of-interest pixels outside of the sub- region.

[0065] In some embodiments, the patch extraction model 340 utilizes a calibration patch extractor 344 to identify the patch of a white portion of the subject having the most uniform color. In some embodiments, once the locations of the two areas-of-interest are identified and the area-of-interest patches extracted, a square region of the white portion of the strip is extracted, e.g., next to one of areas-of-interest. This region is chosen to have the same or similar size as the area-of-interest patches.

[0066] In some embodiments, each patch 322, including the area-of-interest patches and the calibration patch, may be output by the patch extraction model 340, including the pixels and associated channel values within the sub-regions corresponding the patches. Depending on the subject, the feature extraction engine 320 may generate a number of patches, include a calibration patch 323 for the sub-region of the subject, and area-of-interest patches 324 through 325 corresponding to the number of areas-of-interest for color-based analysis present on the subject.

[0067] FIG. 4 is a block diagram of another illustrative computer-based system and platform including a color normalization engine for reference-free color correction in accordance with one or more embodiments of the present disclosure.

[0068] In some embodiments, patches 322 extracted from an image signal 302 representing a subject, as described above, may be ingested by a normalization model 460. In some embodiments, the normalization model 460 determines an areas-of-interest color using a patch color algorithm 1 through N (462 through 464) using each patch 323 through 325, respectively. In some embodiments, each patch color algorithm 462 through 464 uses the channel values of a corresponding patch 322 to determine the mean of each channel value. For example, patch color algorithm 1 463 receives patch 1 324 and averages each channel value across all pixels in patch 1 324 to represent the color of a first area-of-interest. Similarly, a calibration color algorithm 462 receives the calibration patch 323 and averages each channel value across all pixels in the calibration patch 323 to represent the color of the subject. Because the patches 322 are the most uniform sub-region of the subject and each area-of-interest, the means of the channel values represents a most accurate color space coordinate for the subject and each area- of-interest.

[0069] In some embodiments, the mean channel values for each patch are then provided to a corresponding patch color difference algorithm 465 through 466 to determine the normalized color space coordinates representing a corrected color for each area-of-interest. To do so, the patch color difference algorithms 465 through 466 correct the mean channel values associated with area-of-interest patch against mean channel values of the calibration patch 323. In some embodiments, the normalization is performed according to, e.g., equation 1 below:

[0070] where m denotes a mean value for a color channel of a patch, the indices 1, 2, and 3 refer to a first, second and third color channel, respectively, patch denotes a patch formed by at least a portion of an area-of-interest, and calibration refers to the calibration patch. correctedpatchcoordinate refers to a point within at least a portion of spaces of known color on the subject. As a result, the color normalization model 460 produces patch coordinates 467 through 468 that represent the normalized color space coordinates for each area-of-interest on the subject.

[0071] FIG. 5 is a block diagram of another illustrative computer-based system and platform color analysis engine for reference-free color correction in color-based image analysis in accordance with one or more embodiments of the present disclosure.

[0072] In some embodiments, a color-based measurement model 570 receives the patch coordinates 567 through 568 and classifies each patch coordinate according to possible result classifications. In some embodiments, the color-based measurement model 570 includes patch support vector machines 572 through 573 trained to classify the patch coordinates for each area-of-interest type (e.g., the substance or compound for a test pad is configured to test using, e.g., a suitable reagent) using the calibration patch 323.

[0073] In some embodiments, each patch support vector machine 572 through 573 receives the normalized channel values included in a set of normalized subject coordinates and maps the coordinates to a three-dimensional space. In some embodiments, the patch support vector machines 572 through 573 include support vector machine classifiers. A support vector machine classifier is a machine learning algorithm that takes labeled clusters in a dataset and partitions an associated space into disjoint subsets where each subset contains exactly one cluster or a majority of a cluster’ s points. Once the algorithm is trained on a dataset, it can then map new data points, e.g., the patch coordinates 567 or the patch coordinates 568, into the associated space and identify the cluster to which they belong to produce patch 1 result 574 through patch N result 575 and generate color results 578. This mapping is called a model. The associated space is created by hyperplanes generated by the algorithm, each with a distance that maximizes the space between clusters so that new points have a better chance of being classified correctly by the model into their matching cluster.

[0074] FIG. 6 is a block diagram of another illustrative computer-based system and platform: a color classifier for reference-free color correction in color-based image analysis in accordance with one or more embodiments of the present disclosure.

[0075] In some embodiments, patch coordinates 666 is classified by a patch support vector machine 672 according to a mapping by a mapping engine 682. In some embodiments, the mapping engine 682 maps the patch coordinates 666 to, e.g., a three-dimensional space, where each dimension corresponds to a channel of a color space, such as, e.g., the YUV color space. In some embodiments, the channel values of the patch coordinates 666 directly dictate the mapping, e.g., the channel value is used as the coordinate value in the space to which the patch coordinates 666 are being mapped. However, in some embodiments, the mapping engine 682 may weight the patch coordinates 666 or convert the patch coordinates 666 into another coordinate system through, e.g., parameterization of the patch coordinates 666.

[0076] In some embodiments, the mapped patch coordinates 666 may then be classified according to a hyperplane engine 684. In some embodiments, the hyperplane engine 684 generates learned hyperplanes to segment clusters into multiple subspaces, where each subspace is associated with a classification of the area-of-interest color to produce the color- based analysis results, such as color result 674. In some embodiments, the hyperplanes are created to have a distance that maximizes the space between clusters so that new points have a better chance of being classified correctly by the model into their matching cluster. In some embodiments, the hyperplane engine 684 utilizes a linear hyperplane. However, to better accommodate non-linearities in color representation, in some embodiments, the hyperplane engine 684 employs non-linear surfaces to better maximize the margin between each surface and each cluster.

[0077] In some embodiments, the hyperplane engine 684 is trained according to patch targets 680 (e.g., ground truth-labelled areas-of-interest) using an optimizer 686. The optimizer 686 is configured to ingest a training dataset of the labelled areas-of-interest having known results, and based on the labels, segment each patch target 680 into a cluster associated with its label. To do so, the optimizer 686 may generate a hyperplane with a maximized margin such that the distance between the hyperplane and patch targets 680 of each cluster is maximized. In some embodiments, the optimizer 686 may implement a loss function such as, e.g., a Hinge loss function, to maximize the margin. The parameters of the loss function can then be applied to the hyperplane engine 684 to form a trained model. Once the hyperplane engine 684 is trained on the dataset of patch targets 680, it can then map new data points into the associated space and identify which cluster they belong to.

[0078] In some embodiments, the hyperplane engine 684 compares the mapped patch coordinates 666 to the spaces established by the hyperplanes to determine the result classification of the patch coordinates 666. Thus, the hyperplane engine 684 can identify to which cluster the patch coordinates belong, and label the patch coordinates 666 with the classification associated with the cluster. Thus, the hyperplane engine 684 may produce a color result 674 including the results classification associated with the cluster.

[0079] Referring now to FIG. 7, a flowchart of a method for reference free color correction is depicted according aspects of embodiments.

[0080] In some embodiments, the method includes a step to, at block 701, receive a digital image depicting a color-coded subject.

[0081] At block 702, determine pixel-wise color space values for the image. In some embodiments, determining the pixel -wise color space values may include determining at least one color-space value associated with at least one color-space channel for each pixel in the digital image, where the at least one color-space value comprises a luminance value and two chrominance values and the at least one color-space channel corresponds to channels of a YUV color space.

[0082] At block 703, extract a subject from the image using the color space values. In some embodiments, extracting the subject includes detecting edges by, e.g., generating an orientation field, employing a Sobel detector, applying a Radon transform, or by any other suitable edge detection technique or combinations thereof. In some embodiments, the subject edges represent edges of the color-coded subject in the digital image. The subject edges may then be used to identify area-of-interest edges representing edges of at least one area-of-interest in the digital image based at least in part on the edge detection of each edge.

[0083] In some embodiments, a Hough transform analyzes the detected edges to transform the detected edges to identify the subject edges and area-of-interest edges.

[0084] At block 704, extract patches representing areas-of-interest from the subject using the color space values. In some embodiments, extracting the patches may include determining a color patch within each area-of-interest of the at least one area-of-interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each area-of-interest and determining a calibration patch within the color-coded subject having the same or similar size as each color patch.

[0085] At block 705, calculate mean color space values for each extracted patch. In some embodiments, calculating the mean color space values may include determining a mean color patch value for each color-space channel of the at least one color-space channel of pixels in each color patch, and determining a mean calibration patch value for each color-space channel of the at least one color-space channel of pixels in the calibration patch. In some embodiments, upon determining the mean color space values for each extracted patch, a difference between each color patch and the calibration patch may be determined as a difference between the mean calibration patch value and the mean color patch value for each color patch.

[0086] At block 706, analyze the areas-of-interest with automatic color correction based on the mean color space values. In some embodiments, classifying the areas-of-interest may include utilizing a color-based analysis model to determine a color-based analysis result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch, and mapping the difference between the mean calibration patch value and the mean color patch value for each color patch to a space based at least in part on the at least one color-space channel.

[0087] In some embodiments, the color-based analysis model may include a support vector machine. The support vector machine may include a non-linear support vector machine. In some embodiments, the result classification may include a diagnostic test strip result selected from one of i) negative, ii) trace, or iii) positive.

[0088] In some embodiments, upon classifying the diagnostic results, the result classification may be caused to be displayed on a screen of at least one computing device associated with at least one user.

[0089] FIG. 8 depicts a block diagram of an illustrative computer-based system and platform 800 in accordance with one or more embodiments of the present disclosure. However, not all of these components may be required to practice one or more embodiments, and variations in the arrangement and type of the components may be made without departing from the spirit or scope of various embodiments of the present disclosure. In some embodiments, the illustrative computing devices and the illustrative computing components of the illustrative computer- based system and platform 800 may be configured to manage a large number of members and concurrent transactions, as detailed herein. In some embodiments, the illustrative computer- based system and platform 800 may be based on a scalable computer and network architecture that incorporates varies strategies for assessing the data, caching, searching, and/or database connection pooling. An example of the scalable architecture is an architecture that is capable of operating multiple servers.

[0090] In some embodiments, referring to FIG. 8, members 802-804 (e.g., clients) of the illustrative computer-based system and platform 800 may include virtually any computing device capable of receiving and sending a message over a network (e.g., cloud network), such as network 805, to and from another computing device, such as servers 806 and 807, each other, and the like. In some embodiments, the member devices 802-804 may be personal computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, and the like. In some embodiments, one or more member devices within member devices 802-804 may include computing devices that typically connect using a wireless communications medium such as cell phones, smart phones, pagers, walkie talkies, radio frequency (RF) devices, infrared (IR) devices, CBs, integrated devices combining one or more of the preceding devices, or virtually any mobile computing device, and the like. In some embodiments, one or more member devices within member devices 802-804 may be devices that are capable of connecting using a wired or wireless communication medium such as a PDA, POCKET PC, wearable computer, a laptop, tablet, desktop computer, a netbook, a video game device, a pager, a smart phone, an ultra-mobile personal computer (UMPC), and/or any other device that is equipped to communicate over a wired and/or wireless communication medium (e g., NFC, RFID, NBIOT, 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite, ZigBee, etc.). In some embodiments, one or more member devices within member devices 802- 804 may run one or more applications, such as Internet browsers, mobile applications, voice calls, video games, videoconferencing, and email, among others. In some embodiments, one or more member devices within member devices 802-804 may be configured to receive and to send web pages, and the like. In some embodiments, an illustrative specifically programmed browser application of the present disclosure may be configured to receive and display graphics, text, multimedia, and the like, employing virtually any web based language, including, but not limited to Standard Generalized Markup Language (SMGL), HyperText Markup Language (HTML), a wireless application protocol (WAP), a Handheld Device Markup Language (HDML), such as Wireless Markup Language (WML), WMLScript, XML, JavaScript, and the like. In some embodiments, a member device within member devices 802- 804 may be specifically programmed by either Java, .Net, QT, C, C++ and/or other suitable programming language. In some embodiments, one or more member devices within member devices 802-804 may be specifically programmed to include or execute an application to perform a variety of possible tasks, such as, without limitation, messaging functionality, browsing, searching, playing, streaming or displaying various forms of content, including locally stored or uploaded messages, images and/or video, and/or games.

[0091] In some embodiments, the illustrative network 805 may provide network access, data transport and/or other services to any computing device coupled to it. In some embodiments, the illustrative network 805 may include and implement at least one specialized network architecture that may be based at least in part on one or more standards set by, for example, without limitation, Global System for Mobile communication (GSM) Association, the Internet Engineering Task Force (IETF), and the Worldwide Interoperability for Microwave Access (WiMAX) forum. In some embodiments, the illustrative network 805 may implement one or more of a GSM architecture, a General Packet Radio Service (GPRS) architecture, a Universal Mobile Telecommunications System (UMTS) architecture, and an evolution of UMTS referred to as Long Term Evolution (LTE). In some embodiments, the illustrative network 805 may include and implement, as an alternative or in conjunction with one or more of the above, a WiMAX architecture defined by the WiMAX forum. In some embodiments and, optionally, in combination of any embodiment described above or below, the illustrative network 805 may also include, for instance, at least one of a local area network (LAN), a wide area network (WAN), the Internet, a virtual LAN (VLAN), an enterprise LAN, a layer 3 virtual private network (VPN), an enterprise IP network, or any combination thereof. In some embodiments and, optionally, in combination of any embodiment described above or below, at least one computer network communication over the illustrative network 805 may be transmitted based at least in part on one of more communication modes such as but not limited to: NFC, RFID, Narrow Band Internet of Things (NBIOT), ZigBee, 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite and any combination thereof. In some embodiments, the illustrative network 805 may also include mass storage, such as network attached storage (NAS), a storage area network (SAN), a content delivery network (CDN) or other forms of computer or machine readable media.

[0092] In some embodiments, the illustrative server 806 or the illustrative server 807 may be a web server (or a series of servers) running a network operating system, examples of which may include but are not limited to Microsoft Windows Server, Novell NetWare, or Linux. In some embodiments, the illustrative server 806 or the illustrative server 807 may be used for and/or provide cloud and/or network computing. Although not shown in FIG. 8, in some embodiments, the illustrative server 806 or the illustrative server 807 may have connections to external systems like email, SMS messaging, text messaging, ad content providers, etc. Any of the features of the illustrative server 806 may be also implemented in the illustrative server 807 and vice versa.

[0093] In some embodiments, one or more of the illustrative servers 806 and 807 may be specifically programmed to perform, in non-limiting example, as authentication servers, search servers, email servers, social networking services servers, SMS servers, IM servers, MMS servers, exchange servers, photo-sharing services servers, advertisement providing servers, fmancial/banking-related services servers, travel services servers, or any similarly suitable service-base servers for users of the member computing devices 801-804.

[0094] In some embodiments and, optionally, in combination of any embodiment described above or below, for example, one or more illustrative computing member devices 802-804, the illustrative server 806, and/or the illustrative server 807 may include a specifically programmed software module that may be configured to send, process, and receive information using a scripting language, a remote procedure call, an email, a tweet, Short Message Service (SMS), Multimedia Message Service (MMS), instant messaging (IM), internet relay chat (IRC), mIRC, Jabber, an application programming interface, Simple Object Access Protocol (SOAP) methods, Common Object Request Broker Architecture (CORBA), HTTP (Hypertext Transfer Protocol), REST (Representational State Transfer), or any combination thereof.

[0095] FIG. 9 depicts a block diagram of another illustrative computer-based system and platform 900 in accordance with one or more embodiments of the present disclosure. However, not all of these components may be required to practice one or more embodiments, and variations in the arrangement and type of the components may be made without departing from the spirit or scope of various embodiments of the present disclosure. In some embodiments, the member computing devices 902a, 902b thru 902n shown each at least includes a computer- readable medium, such as a random-access memory (RAM) 908 coupled to a processor 910 or FLASH memory. In some embodiments, the processor 910 may execute computer-executable program instructions stored in memory 908. In some embodiments, the processor 910 may include a microprocessor, an ASIC, and/or a state machine. In some embodiments, the processor 910 may include, or may be in communication with, media, for example computer- readable media, which stores instructions that, when executed by the processor 910, may cause the processor 910 to perform one or more steps described herein. In some embodiments, examples of computer-readable media may include, but are not limited to, an electronic, optical, magnetic, or other storage or transmission device capable of providing a processor, such as the processor 910 of client 902a, with computer-readable instructions. In some embodiments, other examples of suitable media may include, but are not limited to, a floppy disk, CD-ROM, DVD, magnetic disk, memory chip, ROM, RAM, an ASIC, a configured processor, all optical media, all magnetic tape or other magnetic media, or any other medium from which a computer processor can read instructions. Also, various other forms of computer- readable media may transmit or carry instructions to a computer, including a router, private or public network, or other transmission device or channel, both wired and wireless. In some embodiments, the instructions may comprise code from any computer-programming language, including, for example, C, C++, Visual Basic, Java, Python, Perl, JavaScript, and etc.

[0096] In some embodiments, member computing devices 902a through 902n may also comprise a number of external or internal devices such as a mouse, a CD-ROM, DVD, a physical or virtual keyboard, a display, or other input or output devices. In some embodiments, examples of member computing devices 902a through 902n (e.g., clients) may be any type of processor-based platforms that are connected to a network 906 such as, without limitation, personal computers, digital assistants, personal digital assistants, smart phones, pagers, digital tablets, laptop computers, Internet appliances, and other processor-based devices. In some embodiments, member computing devices 902a through 902n may be specifically programmed with one or more application programs in accordance with one or more principles/methodologies detailed herein. In some embodiments, member computing devices 902a through 902n may operate on any operating system capable of supporting a browser or browser-enabled application, such as Microsoft™, Windows™, and/or Linux. In some embodiments, member computing devices 902a through 902n shown may include, for example, personal computers executing a browser application program such as Microsoft Corporation's Internet Explorer™, Apple Computer, Inc.'s Safari™, Mozilla Firefox, and/or Opera. In some embodiments, through the member computing client devices 902a through 902n, users, 912a through 902n, may communicate over the illustrative network 906 with each other and/or with other systems and/or devices coupled to the network 906. As shown in FIG. 9, illustrative server devices 904 and 913 may be also coupled to the network 906. In some embodiments, one or more member computing devices 902a through 902n may be mobile clients.

[0097] In some embodiments, at least one database of illustrative databases 907 and 915 may be any type of database, including a database managed by a database management system (DBMS). In some embodiments, an illustrative DBMS-managed database may be specifically programmed as an engine that controls organization, storage, management, and/or retrieval of data in the respective database. In some embodiments, the illustrative DBMS-managed database may be specifically programmed to provide the ability to query, backup and replicate, enforce rules, provide security, compute, perform change and access logging, and/or automate optimization. In some embodiments, the illustrative DBMS-managed database may be chosen from Oracle database, IBM DB2, Adaptive Server Enterprise, FileMaker, Microsoft Access, Microsoft SQL Server, MySQL, PostgreSQL, and a NoSQL implementation. In some embodiments, the illustrative DBMS-managed database may be specifically programmed to define each respective schema of each database in the illustrative DBMS, according to a particular database model of the present disclosure which may include a hierarchical model, network model, relational model, object model, or some other suitable organization that may result in one or more applicable data structures that may include fields, records, files, and/or objects. In some embodiments, the illustrative DBMS-managed database may be specifically programmed to include metadata about the data that is stored.

[0098] In some embodiments, the illustrative computer-based systems or platforms of the present disclosure may be specifically configured to operate in a cloud computing/architecture such as, but not limiting to: infrastructure a service (IaaS), platform as a service (PaaS), and/or software as a service (SaaS). FIGs. 10 and 11 illustrate schematics of illustrative implementations of the cloud computing/architecture(s) in which the illustrative computer- based systems or platforms of the present disclosure may be specifically configured to operate.

[0099] It is understood that at least one aspect/functionality of various embodiments described herein can be performed in real-time and/or dynamically. As used herein, the term “real-time” is directed to an event/action that can occur instantaneously or almost instantaneously in time when another event/action has occurred. For example, the “real-time processing,” “real-time computation,” and “real-time execution” all pertain to the performance of a computation during the actual time that the related physical process (e.g., a user interacting with an application on a mobile device) occurs, in order that results of the computation can be used in guiding the physical process.

[0100] As used herein, the term “dynamically” and term “automatically,” and their logical and/or linguistic relatives and/or derivatives, mean that certain events and/or actions can be triggered and/or occur without any human intervention. In some embodiments, events and/or actions in accordance with the present disclosure can be in real-time and/or based on a predetermined periodicity of at least one of: nanosecond, several nanoseconds, millisecond, several milliseconds, second, several seconds, minute, several minutes, hourly, several hours, daily, several days, weekly, monthly, etc.

[0101] As used herein, the term “runtime” corresponds to any behavior that is dynamically determined during an execution of a software application or at least a portion of software application.

[0102] In some embodiments, illustrative inventive, specially programmed computing systems and platforms with associated devices are configured to operate in the distributed network environment, communicating with one another over one or more suitable data communication networks (e.g., the Internet, satellite, etc.) and utilizing one or more suitable data communication protocols/modes such as, without limitation, IPX/SPX, X.25, AX.25, AppleTalk(TM), TCP/IP (e.g., HTTP), near-field wireless communication (NFC), RFID, Narrow Band Internet of Things (NBIOT), 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite, ZigBee, and other suitable communication modes. In some embodiments, the NFC can represent a short-range wireless communications technology in which NFC-enabled devices are “swiped,” “bumped,” “tapped” or otherwise moved in close proximity to communicate. In some embodiments, the NFC could include a set of short-range wireless technologies, typically requiring a distance of 10 cm or less. In some embodiments, the NFC may operate at 13.56 MHz on ISO/IEC 18000-3 air interface and at rates ranging from 106 kbit/s to 424 kbit/s. In some embodiments, the NFC can involve an initiator and a target; the initiator actively generates an RF field that can power a passive target. In some embodiment, this can enable NFC targets to take very simple form factors such as tags, stickers, key fobs, or cards that do not require batteries. In some embodiments, the NFC’s peer-to-peer communication can be conducted when a plurality of NFC-enable devices (e.g., smartphones) within close proximity of each other.

[0103] The material disclosed herein may be implemented in software or firmware or a combination of them or as instructions stored on a machine-readable medium, which may be read and executed by one or more processors. A machine-readable medium may include any medium and/or mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device). For example, a machine-readable medium may include read only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory devices; electrical, optical, acoustical or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), and others.

[0104] As used herein, the terms “computer engine” and “engine” identify at least one software component and/or a combination of at least one software component and at least one hardware component which are designed/programmed/configured to manage/control other software and/or hardware components (such as the libraries, software development kits (SDKs), obj ects, etc.).

[0105] Examples of hardware elements may include processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, and so forth), integrated circuits, application specific integrated circuits (ASIC), programmable logic devices (PLD), digital signal processors (DSP), field programmable gate array (FPGA), logic gates, registers, semiconductor device, chips, microchips, chip sets, and so forth. In some embodiments, the one or more processors may be implemented as a Complex Instruction Set Computer (CISC) or Reduced Instruction Set Computer (RISC) processors; x86 instruction set compatible processors, multi-core, or any other microprocessor or central processing unit (CPU). In various implementations, the one or more processors may be dual-core processor(s), dual-core mobile processor(s), and so forth.

[0106] Computer-related systems, computer systems, and systems, as used herein, include any combination of hardware and software. Examples of software may include software components, programs, applications, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application program interfaces (API), instruction sets, computer code, computer code segments, words, values, symbols, or any combination thereof. Determining whether an embodiment is implemented using hardware elements and/or software elements may vary in accordance with any number of factors, such as desired computational rate, power levels, heat tolerances, processing cycle budget, input data rates, output data rates, memory resources, data bus speeds and other design or performance constraints.

[0107] One or more aspects of at least one embodiment may be implemented by representative instructions stored on a machine-readable medium which represents various logic within the processor, which when read by a machine causes the machine to fabricate logic to perform the techniques described herein. Such representations, known as “IP cores” may be stored on a tangible, machine readable medium and supplied to various customers or manufacturing facilities to load into the fabrication machines that make the logic or processor. Of note, various embodiments described herein may, of course, be implemented using any appropriate hardware and/or computing software languages (e.g., C++, Objective-C, Swift, Java, JavaScript, Python, Perl, QT, etc ).

[0108] In some embodiments, one or more of illustrative computer-based systems or platforms of the present disclosure may include or be incorporated, partially or entirely into at least one personal computer (PC), laptop computer, ultra-laptop computer, tablet, touch pad, portable computer, handheld computer, palmtop computer, personal digital assistant (PDA), cellular telephone, combination cellular telephone/PDA, television, smart device (e.g., smart phone, smart tablet or smart television), mobile internet device (MID), messaging device, data communication device, and so forth.

[0109] As used herein, term “server” should be understood to refer to a service point which provides processing, database, and communication facilities. By way of example, and not limitation, the term “server” can refer to a single, physical processor with associated communications and data storage and database facilities, or it can refer to a networked or clustered complex of processors and associated network and storage devices, as well as operating software and one or more database systems and application software that support the services provided by the server. Cloud servers are examples.

[0110] In some embodiments, as detailed herein, one or more of the computer-based systems of the present disclosure may obtain, manipulate, transfer, store, transform, generate, and/or output any digital object and/or data unit (e.g., from inside and/or outside of a particular application) that can be in any suitable form such as, without limitation, a file, a contact, a task, an email, a message, a map, an entire application (e.g., a calculator), data points, and other suitable data. In some embodiments, as detailed herein, one or more of the computer-based systems of the present disclosure may be implemented across one or more of various computer platforms such as, but not limited to: (1) Linux, (2) Microsoft Windows, (3) OS X (Mac OS), (4) Solaris, (5) UNIX (6) VMWare, (7) Android, (8) Java Platforms, (9) Open Web Platform, (10) Kubemetes or other suitable computer platforms. In some embodiments, illustrative computer-based systems or platforms of the present disclosure may be configured to utilize hardwired circuitry that may be used in place of or in combination with software instructions to implement features consistent with principles of the disclosure. Thus, implementations consistent with principles of the disclosure are not limited to any specific combination of hardware circuitry and software. For example, various embodiments may be embodied in many different ways as a software component such as, without limitation, a stand-alone software package, a combination of software packages, or it may be a software package incorporated as a “tool” in a larger software product.

[0111] For example, illustrative software specifically programmed in accordance with one or more principles of the present disclosure may be downloadable from a network, for example, a website, as a stand-alone product or as an add-in package for installation in an existing software application. For example, illustrative software specifically programmed in accordance with one or more principles of the present disclosure may also be available as a client-server software application, or as a web-enabled software application. For example, illustrative software specifically programmed in accordance with one or more principles of the present disclosure may also be embodied as a software package installed on a hardware device.

[0112] In some embodiments, illustrative computer-based systems or platforms of the present disclosure may be configured to handle numerous concurrent users that may be, but is not limited to, at least 100 (e.g., but not limited to, 100-999), at least 1,000 (e.g., but not limited to, 1,000-9,999 ), at least 10,000 (e.g., but not limited to, 10,000-99,999 ), at least 100,000 (e.g., but not limited to, 100,000-999,999), at least 1,000,000 (e.g., but not limited to, 1,000,000- 9,999,999), at least 10,000,000 (e.g., but not limited to, 10,000,000-99,999,999), at least 100,000,000 (e.g., but not limited to, 100,000,000-999,999,999), at least 1,000,000,000 (e.g., but not limited to, 1,000,000,000-999,999,999,999), and so on.

[0113] In some embodiments, illustrative computer-based systems or platforms of the present disclosure may be configured to output to distinct, specifically programmed graphical user interface implementations of the present disclosure (e.g., a desktop, a web app., etc.). In various implementations of the present disclosure, a final output may be displayed on a displaying screen which may be, without limitation, a screen of a computer, a screen of a mobile device, or the like. In various implementations, the display may be a holographic display. In various implementations, the display may be a transparent surface that may receive a visual projection. Such projections may convey various forms of information, images, or objects. For example, such projections may be a visual overlay for a mobile augmented reality (MAR) application.

[0114] In some embodiments, illustrative computer-based systems or platforms of the present disclosure may be configured to be utilized in various applications which may include, but not limited to, gaming, mobile-device games, video chats, video conferences, live video streaming, video streaming and/or augmented reality applications, mobile-device messenger applications, and others similarly suitable computer-device applications.

[0115] As used herein, the term “mobile electronic device,” or the like, may refer to any portable electronic device that may or may not be enabled with location tracking functionality (e.g., MAC address, Internet Protocol (IP) address, or the like). For example, a mobile electronic device can include, but is not limited to, a mobile phone, Personal Digital Assistant (PDA), Blackberry ™, Pager, Smartphone, or any other reasonable mobile electronic device.

[0116] As used herein, terms “proximity detection,” “locating,” “location data,” “location information,” and “location tracking” refer to any form of location tracking technology or locating method that can be used to provide a location of, for example, a particular computing device, system or platform of the present disclosure and any associated computing devices, based at least in part on one or more of the following techniques and devices, without limitation: accelerometer(s), gyroscope(s), Global Positioning Systems (GPS); GPS accessed using Bluetooth™; GPS accessed using any reasonable form of wireless and non-wireless communication; WiFi™ server location data; Bluetooth ™ based location data; triangulation such as, but not limited to, network based triangulation, WiFi™ server information based tri angulation, Bluetooth™ server information based triangulation; Cell Identification based tri angulation, Enhanced Cell Identification based triangulation, Uplink-Time difference of arrival (U-TDOA) based triangulation, Time of arrival (TOA) based tri angulation, Angle of arrival (AOA) based triangulation; techniques and systems using a geographic coordinate system such as, but not limited to, longitudinal and latitudinal based, geodesic height based, Cartesian coordinates based; Radio Frequency Identification such as, but not limited to, Long range RFID, Short range RFID; using any form of RFID tag such as, but not limited to active RFID tags, passive RFID tags, battery assisted passive RFID tags; or any other reasonable way to determine location. For ease, at times the above variations are not listed or are only partially listed; this is in no way meant to be a limitation.

[0117] As used herein, terms “cloud,” “Internet cloud,” “cloud computing,” “cloud architecture,” and similar terms correspond to at least one of the following: (1) a large number of computers connected through a real-time communication network (e.g., Internet); (2) providing the ability to run a program or application on many connected computers (e.g., physical machines, virtual machines (VMs)) at the same time; (3) network-based services, which appear to be provided by real server hardware, and are in fact served up by virtual hardware (e.g., virtual servers), simulated by software running on one or more real machines (e.g., allowing to be moved around and scaled up (or down) on the fly without affecting the end user).

[0118] In some embodiments, the illustrative computer-based systems or platforms of the present disclosure may be configured to securely store and/or transmit data by utilizing one or more of encryption techniques (e.g., private/public key pair, Triple Data Encryption Standard (3DES), block cipher algorithms (e.g., IDEA, RC2, RC5, CAST and Skipjack), cryptographic hash algorithms (e.g., MD5, RIPEMD-160, RTRO, SHA-1, SHA-2, Tiger (TTH), WHIRLPOOL, RNGs).

[0119] The aforementioned examples are, of course, illustrative and not restrictive.

[0120] As used herein, the term “user” shall have a meaning of at least one user. In some embodiments, the terms “user”, “subscriber” “consumer” or “customer” should be understood to refer to a user of an application or applications as described herein and/or a consumer of data supplied by a data provider. By way of example, and not limitation, the terms “user” or “subscriber” can refer to a person who receives data provided by the data or service provider over the Internet in a browser session, or can refer to an automated software application which receives the data and stores or processes the data.

[0121] As used herein, the terms “and” and “or” may be used interchangeably to refer to a set of items in both the conjunctive and disjunctive in order to encompass the full description of combinations and alternatives of the items. By way of example, a set of items may be listed with the disjunctive “or”, or with the conjunction “and.” In either case, the set is to be interpreted as meaning each of the items singularly as alternatives, as well as any combination of the listed items.

[0122] At least some aspects of the present disclosure will now be described with reference to the following numbered clauses.

1. A method comprising: receiving, by at least one processor, a digital image depicting a color-coded subject; determining, by the at least one processor, at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determining, by the at least one processor, at least one area-of-interest in a subject depicted in the digital image based on extracted features; determining, by the at least one processor, a color patch within each area-of-interest of the at least one area-of-interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each area-of-interest; determining, by the at least one processor, a calibration patch of a known color within the color-coded subject having a same size as each color patch; utilizing, by the at least one processor, a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color; and causing to display, by the at least one processor, the color-based result associated with the at least one area-of-interest on a screen of at least one computing device associated with at least one user.

2. The method as recited in clause 1, wherein the at least one color-space value comprises a luminance value and two chrominance values.

3. The method as recited in clause 1, wherein the at least one color-space channel corresponds to channels of a YUV color space.

4. The method as recited in clause 1, further comprising: determining, by the at least one processor, a mean color patch value for each color- space channel of the at least one color-space channel of pixels in each color patch; determining, by the at least one processor, a mean known patch value for each color- space channel of the at least one color-space channel of pixels in the calibration patch of the known color; and determining, by the at least one processor, the difference between each color patch and the calibration patch of the known color as a difference between the mean known patch value and the mean color patch value for each color patch.

5. The method as recited in clause 4, further comprising mapping, by the at least one processor, the difference between the mean known patch value and the mean color patch value for each color patch to a space based at least in part on the at least one color-space channel.

6. The method as recited in clause 1, further comprising applying, by the at least one processor, edge detection to determine the at least one area of interest.

7. The method as recited in clause 1, wherein the color-based analysis model comprises a support vector machine.

8. The method as recited in clause 1, wherein the support vector machine comprises a non linear support vector machine. 9. The method as recited in clause 1, wherein the color-based result comprises a diagnostic result selected from one of i) negative, ii) trace, or iii) positive.

10. A system comprising: at least one processor in communication with a non-transitory memory having instructions stored thereon, the at least one processor configured to execute the instructions to perform steps comprising: receive a digital image depicting a color-coded subject; determine at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determine at least one area-of-interest in a subject depicted in the digital image based on extracted features; determine a color patch within each area-of-interest of the at least one area-of- interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color- space values for pixels representing each area-of-interest; determine a calibration patch of a known color within the color-coded subject having the same or similar size as each color patch; and utilize a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color.

11. The system as recited in clause 10, wherein the at least one color-space value comprises a luminance value and two chrominance values.

12. The system as recited in clause 10, wherein the at least one color-space channel corresponds to channels of a YUV color space. 13. The system as recited in clause 10, wherein the at least one processor is further configured to perform steps comprising: determine a mean color patch value for each color-space channel of the at least one color-space channel of pixels in each color patch; determine a mean known patch value for each color-space channel of the at least one color-space channel of pixels in the calibration patch of the known color; and determine the difference between each color patch and the calibration patch of the known color as a difference between the mean known patch value and the mean color patch value for each color patch.

14. The system as recited in clause 13, wherein the at least one processor is further configured to perform steps comprising map the difference between the mean known patch value and the mean color patch value for each color patch to a space based at least in part on the at least one color-space channel.

15. The system as recited in clause 10, wherein the at least one processor is further configured to perform steps comprising apply edge detection to determine the at least one area of interest.

16. The system as recited in clause 10, wherein the color-based analysis model comprises a support vector machine.

17. The system as recited in clause 10, wherein the support vector machine comprises a non linear support vector machine.

18. The system as recited in clause 10, wherein the color-based result comprises a diagnostic result selected from one of i) negative, ii) trace, or iii) positive.

19. The system as recited in clause 10, wherein the digital image is received from the at least one computing device associated with the at least one user located remotely from the at least one processor. 20. A non-transitory computer-readable storage medium with an executable program stored thereon, wherein the program instructs at least one processor to perform the following steps: receiving a digital image depicting a color-coded subject; determining at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determining at least one area-of-interest in a subject depicted in the digital image based on extracted features; determining a color patch within each area-of-interest of the at least one area-of-interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each area-of-interest; determining a calibration patch of a known color within the color-coded subject having a same size as each color patch; utilizing a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color; and causing to display the color-based result associated with the at least one area-of-interest on a screen of at least one computing device associated with at least one user.

[0123] While one or more embodiments of the present disclosure have been described, it is understood that these embodiments are illustrative only, and not restrictive, and that many modifications may become apparent to those of ordinary skill in the art, including that various embodiments of the inventive methodologies, the illustrative systems and platforms, and the illustrative devices described herein can be utilized in any combination with each other. Further still, the various steps may be carried out in any desired order (and any desired steps may be added and/or any desired steps may be eliminated).

Claims

1. A method comprising: receiving, by at least one processor, a digital image depicting a color-coded subject; determining, by the at least one processor, at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determining, by the at least one processor, at least one area-of-interest in a subject depicted in the digital image based on extracted features; determining, by the at least one processor, a color patch within each area-of-interest of the at least one area-of-interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each area-of-interest; determining, by the at least one processor, a patch of a known color within the color- coded subject having the same or similar size as each color patch; utilizing, by the at least one processor, a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color; and causing to display, by the at least one processor, the color-based result associated with the at least one area-of-interest on a screen of at least one computing device associated with at least one user.

2. The method as recited in claim 1, wherein the at least one color-space value comprises a luminance value and two chrominance values.

3. The method as recited in claim 1, wherein the at least one color-space channel corresponds to channels of a YUV color space.

4. The method as recited in claim 1, further comprising: determining, by the at least one processor, a mean color patch value for each color- space channel of the at least one color-space channel of pixels in each color patch; determining, by the at least one processor, a mean known patch value for each color- space channel of the at least one color-space channel of pixels in the calibration patch of the known color; and determining, by the at least one processor, the difference between each color patch and the calibration patch of the known color as a difference between the mean known patch value and the mean color patch value for each color patch.

5. The method as recited in claim 4, further comprising mapping, by the at least one processor, the difference between the mean known patch value and the mean color patch value for each color patch to a space based at least in part on the at least one color-space channel.

6. The method as recited in claim 1, further comprising applying, by the at least one processor, edge detection to determine the at least one area of interest.

7. The method as recited in claim 1, wherein the color-based analysis model comprises a support vector machine.

8. The method as recited in claim 1, wherein the support vector machine comprises a non-linear support vector machine.

9. The method as recited in claim 1, wherein the color-based result comprises a diagnostic result selected from one of i) negative, ii) trace, or iii) positive.

10. A system comprising: at least one processor in communication with a non-transitory memory having instructions stored thereon, the at least one processor configured to execute the instructions to perform steps comprising: receive a digital image depicting a color-coded subject; determine at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determine at least one area-of-interest in a subject depicted in the digital image based on extracted features; determine a color patch within each area-of-interest of the at least one area-of- interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color- space values for pixels representing each area-of-interest; determine a calibration patch of a known color within the color-coded subject having a same size as each color patch; and utilize a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color.

11. The system as recited in claim 10, wherein the at least one color-space value comprises a luminance value and two chrominance values.

12. The system as recited in claim 10, wherein the at least one color-space channel corresponds to channels of a YUV color space.

13. The system as recited in claim 10, wherein the at least one processor is further configured to perform steps comprising: determine a mean color patch value for each color-space channel of the at least one color-space channel of pixels in each color patch; determine a mean known patch value for each color-space channel of the at least one color-space channel of pixels in the calibration patch of the known color; and determine the difference between each color patch and the calibration patch of the known color as a difference between the mean known patch value and the mean color patch value for each color patch.

14. The system as recited in claim 13, wherein the at least one processor is further configured to perform steps comprising map the difference between the mean known patch value and the mean color patch value for each color patch to a space based at least in part on the at least one color-space channel.

15. The system as recited in claim 10, wherein the at least one processor is further configured to perform steps comprising apply edge detection to determine the at least one area of interest.

16. The system as recited in claim 10, wherein the color-based analysis model comprises a support vector machine.

17. The system as recited in claim 10, wherein the support vector machine comprises a non linear support vector machine.

18. The system as recited in claim 10, wherein the color-based result comprises a diagnostic result selected from one of i) negative, ii) trace, or iii) positive.

19. The system as recited in claim 10, wherein the digital image is received from the at least one computing device associated with the at least one user located remotely from the at least one processor.

20. A non-transitory computer-readable storage medium with an executable program stored thereon, wherein the program instructs at least one processor to perform the following steps: receiving a digital image depicting a color-coded subject; determining at least one color-space value associated with at least one color-space channel for each pixel in the digital image; determining at least one area-of-interest in a subject depicted in the digital image based on extracted features; determining a color patch within each area-of-interest of the at least one area-of-interest based on a sub-region of each area-of-interest having a minimum difference between the means or medians of the maxima and minima of color-space values for pixels representing each area-of-interest; determining a calibration patch of a known color within the color-coded subject having a same size as each color patch; utilizing a color-based analysis model to determine a color-based result associated with the at least one area-of-interest based at least in part on a difference between each color patch and the calibration patch of the known color; and causing to display the color-based result associated with the at least one area-of-interest on a screen of at least one computing device associated with at least one user.