Visual feedback device and method based on machine recognition confidence

Abstract

A method in a computing device includes capturing, via a sensor, an image of a marker; determining a confidence level associated with the machine identification of the marker; selecting a feedback attribute based on the confidence level; prior to outputting the content encoded in the flag, a feedback signal having a feedback attribute is generated via the output device, where the attribute is configured to indicate a likelihood of success of a decoding event for decoding the content encoded in the flag.

Description

Background Technology

[0001] Data acquisition devices can be used to capture images of machine-readable labels (such as barcodes, text, etc.) and obtain data from such images by detecting and decoding barcodes. However, the success of data acquisition devices in extracting data from machine-readable labels can be affected by factors such as device positioning, lighting, or other environmental conditions. Attached Figure Description

[0002] The accompanying drawings (in which the same reference numerals denote the same or functionally similar elements throughout the different views) together with the following detailed description are incorporated into and form part of the specification and serve to further illustrate embodiments including the concepts of the claimed invention, and to explain the various principles and advantages of those embodiments.

[0003] Figure 1 This is a diagram showing the data acquisition equipment.

[0004] Figure 2 It is shown Figure 1 A diagram of the data acquisition device and some of its internal components.

[0005] Figure 3 This is a flowchart of a method for visual feedback based on machine recognition confidence for data acquisition devices.

[0006] Figure 4 It is shown Figure 3 The diagram illustrates an example of the execution of the method in blocks 315 to 330.

[0007] Figure 5 It is shown Figure 3 The diagram illustrates another example of the method executed in boxes 315 to 330.

[0008] Figure 6 It is shown that it is used for Figure 3 A diagram illustrating further example configurations used in the method.

[0009] Those skilled in the art will understand that the elements in the accompanying drawings are shown for simplicity and clarity and are not necessarily drawn to scale. For example, the dimensions of some elements in the drawings may be exaggerated relative to other elements to aid in understanding embodiments of the invention.

[0010] The apparatus and method configurations have been indicated in appropriate places in the accompanying drawings by conventional symbols, which show only those specific details relevant to understanding embodiments of the invention, so as not to obscure this disclosure with details that would be obvious to those skilled in the art who benefit from the description herein. Detailed Implementation

[0011] The examples disclosed herein relate to a method in a computing device, comprising: capturing an image of a tag via a sensor; determining a confidence level associated with machine recognition of the tag; selecting a feedback attribute based on the confidence level; and generating a feedback signal having the feedback attribute via an output device before outputting content encoded in the tag, wherein the attribute is configured to indicate the probability of a successful decoding event for decoding the content encoded in the tag.

[0012] Additional examples disclosed herein relate to a computing device including: a sensor; an output device; and a processor configured to: capture an image of a tag via the sensor; determine a confidence level associated with machine recognition of the tag; select a feedback attribute based on the confidence level; and generate a feedback signal having the feedback attribute via the output device, wherein the attribute is configured to indicate the probability of a successful decoding event for decoding content encoded in the tag.

[0013] Further examples disclosed herein relate to a method in a computing device, comprising: controlling a light emitter to project an indicator light having default visual properties onto a surface carrying a mark; capturing an image of the mark via a sensor; determining a confidence level associated with machine recognition of the mark; selecting a visual feedback property based on the confidence level; and controlling the light emitter to project the indicator light having the visual feedback property.

[0014] Figure 1 A computing device 100 is shown, configured to capture images of markers (such as marker 104 carried on surface 108) and perform machine recognition operations to detect and extract information from marker 104. Marker 104 may include barcodes (such as linear or one-dimensional barcodes (e.g., Code 128, EAN-8, etc.) or two-dimensional barcodes (e.g., QR codes, DataMatrix, etc.)), and computing device 100 may be configured to detect and decode such barcodes. In other examples, marker 104 may include text (e.g., alphanumeric characters printed on or otherwise affixed to surface 108), and computing device 100 may be configured to detect the text and perform optical character recognition (OCR) to extract a machine-readable representation of the text (e.g., a Unicode representation of the text contained in marker 104). Surface 108 may include a wrapped surface, a sheet of paper or other suitable material, a shelf edge, etc.

[0015] In this example, computing device 100 is shown as a wearable data acquisition device, such as a ring scanner. However, in other examples, computing device 100 may be implemented in a variety of other form factors, including as a tablet computer, a smartphone, a scanner with a pistol-grip handle assembly, etc. Device 100 includes a housing 112 that contains various other components of device 100, including sensors configured to capture images within a field of view (FOV) 116. Device 100 is configured to detect markers within such images by performing one or more machine recognition operations, and under certain conditions, decode or otherwise extract information from the detected markers (e.g., barcode decoding and / or OCR processing).

[0016] Device 100 may also include components configured, for example, to direct to FOV 116 (e.g., as... Figure 1 As shown, the light emitter projects the indicator light 120 (basically centered within the FOV 116). Figure 1 As shown, the indicator light 120 can be a point or other suitable shape occupying a relatively small portion of the FOV 116 (e.g., less than about ten percent of the FOV 116, although various indicator light sizes may be used in other examples). The indicator light 120 can be used to assist the aiming device 100 in placing the marker 104 within the FOV 116 for data capture. The device 100 may further include an input 124, such as a button, trigger, capacitive sensor, etc. The input 124 can be activated by an operator of the device 100 (e.g., in this example, a person wearing the device 100 on their hand) to trigger a decoding event (e.g., extracting and outputting content from a marker detected in an image). For example, the device 100 can capture an image stream and can process each image to automatically detect any markers within it. When a marker is detected in an image, the device 100 can, for example, attempt to decode the detected marker in response to the activation of the input 124. However, in the absence of a machine-recognized output trigger (such as the activation of the input 124), the device 100 may discard any data extracted from the image. In response to a machine recognition output trigger, device 100 may provide such extracted data to another computing device and / or to an application running on device 100 for further processing.

[0017] In other words, during operation, device 100 can continuously detect markers in captured images. In response to periodic machine recognition output triggers (such as activation of input 124), device 100 can further initiate decoding events to attempt to extract machine-recognized data (also called content) from the markers detected on the surfaces(s) within FOV 116, and output such content for further use. However, depending on lighting conditions, the distance between device 100 and surface 108, the position of marker 104 within FOV 116, and various other factors, marker 104 may sometimes be difficult to detect and / or decode in images captured by device 100. If input 124 is activated when marker 104 was not successfully detected or was detected with low confidence in the most recently captured image by device 100, device 100 may fail to produce machine recognition output. That is, the decoding event may fail. Repositioning device 100 relative to marker 104 can increase the likelihood of successfully capturing data from marker 104.

[0018] The data acquisition device can generate a confidence level associated with each processed image, and such confidence level can be used to provide feedback to the operator of device 100 (e.g., prompting the operator to reposition device 100 before activating input 124). However, device 100 lacks a display, making it potentially difficult to convey such feedback to the operator. Other computing devices may include a display that presents the current machine recognition confidence level, but the display may be small (e.g., in the case of a wrist-worn scanner), or the orientation of the display may make it difficult to read when the device is used as a data acquisition device.

[0019] Therefore, device 100 implements additional functionality to provide the operator with easily perceptible (e.g., visible, audible, etc.) feedback indicating the current machine recognition confidence level (e.g., the confidence level associated with the detection of a marker in an image). Device 100 can represent feedback by controlling the visual properties of the indicating light 120 based on the machine recognition confidence level, or by controlling the properties of other feedback signals (such as audio signals, tactile feedback, etc.). Such perceptible feedback can, for example, reduce the number of failed decoding events initiated by the machine recognition output trigger, thereby enabling a reduction in scan time.

[0020] Figure 2 Device 100 and some of its internal components are shown. For example... Figure 2 As shown, device 100 may include a scanning window 200, behind which a sensor 204 (such as an image sensor (e.g., a complementary metal-oxide-semiconductor or CMOS sensor)) and a light emitter 208 are disposed. Sensor 204 defines... Figure 1The FOV 116 shown is configured to capture images for processing (e.g., detecting mark 104 and performing machine recognition operations thereon). The light emitter 208 may include a light-emitting diode (LED) (such as a laser diode) configured to project an indicator light 120 into the FOV 116 to assist the operator of device 100 in aiming the FOV 116 at the mark. Therefore, the indicator light 120 can be within the visible spectrum, although the specific color of the indicator light 120 and other visual properties discussed below may vary. In other examples, the indicator light 120 does not need to be projected onto the center of the FOV 116, but may be projected onto another portion of the FOV 116. In a further example, device 100 may include another light emitter (such as an LED disposed on the upper surface 212 of housing 112) for providing visual feedback. In other examples, device 100 may further include other emitters (such as a speaker), and / or a motor for generating haptic feedback.

[0021] Device 100 includes a processor 216, such as a central processing unit (CPU), graphics processing unit (GPU), and / or other suitable control circuitry, microcontroller, etc. Processor 216 is interconnected with a non-transitory computer-readable storage medium (such as memory 220). Memory 220 includes a combination of volatile memory (e.g., random access memory, i.e., RAM) and non-volatile memory (e.g., read-only memory, i.e., electrically erasable programmable read-only memory, i.e., EEPROM, flash memory). Memory 220 may store computer-readable instructions, which, by being executed by processor 216, configure processor 216 to perform various functions in conjunction with certain other components of device 100. Device 100 may also include a communication interface 224, enabling device 100 to exchange data with other computing devices (e.g., via various networks, short-range communication links, etc.). Figure 2 As shown, the processor 216 is also interconnected with the sensor 204, the transmitter 208, and the input 124.

[0022] In some examples, device 100 may include further inputs, such as triggers 228 disposed on the upper surface 212. Device 100 may include other input and / or output devices, such as a microphone, keypad, etc. As shown above, in other examples, device 100 may also include a display that can be integrated with a touchscreen.

[0023] Computer-readable instructions stored in memory 220 for execution by processor 216 include machine recognition application 232 and downstream application 236. When executed by processor 216, application 232 configures device 100 to capture an image stream via a sensor and to project indicator light 120 into FOV 116 during the capture of the image stream. Further, application 232 configures device 100 to generate feedback signals based on a confidence level associated with machine recognition of marker 104 (or any other suitable marker) within the captured image stream, for example, by controlling the visual appearance of indicator light 120 and / or by controlling audio and / or tactile output. The confidence level may correspond to the detection of a marker in the captured image. Therefore, the appearance of indicator light 120 and / or the nature of other feedback signals may vary over time to indicate the current confidence level associated with machine recognition of marker 104, for example, to indicate a favorable time for outputting data extracted from marker 104. In other words, each feedback signal is configured to indicate the probability of a successful decoding event for decoding the content encoded in the detected marker.

[0024] When executed by processor 216, application 236 can configure device 100 to initiate the execution of application 232 (e.g., also known as initiating a scanning session) and begin capturing and processing the aforementioned image stream. Application 236 can also be a recipient of the current machine recognition result from application 232 (e.g., when input 124 is activated). Application 236 can process the result (e.g., by transmitting the result to another computing device and retrieving price or other inventory information associated with the result from a database). In a further example, either or both of application 232 and application 236 can be implemented by one or more specially designed hardware and firmware components (such as FPGA, ASIC, etc.).

[0025] Go to Figure 3 A method 300 based on machine recognition confidence is illustrated. The method 300 is described below in conjunction with the execution of method 300 by device 100 (e.g., extracting data from marker 104). Method 300 can also be executed by a variety of other computing devices having sensors and output devices, such as a light emitter functionally similar to sensor 204 and light emitter 208.

[0026] At box 305, device 100 is configured to initiate a scanning session (also known as a capture session). As described above, initiating a scanning session may include starting execution of application 232. For example, a scanning session may be initiated in response to an initiation command from application 236 (e.g., a request for decoding or other machine-identifiable operation). In other examples, device 100 may automatically execute application 232 at startup.

[0027] During a scanning session, device 100 is configured to capture an image stream via sensor 204 while simultaneously projecting indicator light 120 into the field of view (FOV) 116 of sensor 204. Images can be captured at a suitable frame rate, for example, providing substantially real-time capture and machine recognition (e.g., approximately ten frames per second, but higher or lower frame rates are also possible depending on the computing resources available to device 100). Indicator light 120 can be projected substantially continuously throughout the entire capture session.

[0028] At box 310, device 100 can be configured to generate a feedback signal with default feedback attributes. For example, device 100 can be configured to project an indicator light 120 with default visual attributes. The default visual attributes can be stored in memory 220, for example, as configuration data within or associated with application 232. The default visual attributes can indicate that no confidence measurement associated with machine recognition of tag 104 (e.g., confidence corresponding to tag detection) is available, or that the confidence is low (e.g., low detection confidence, so a decoding event initiated by the machine recognition output trigger is currently unlikely to provide extracted data). In other words, the default visual attributes can be different from confidence-based visual attributes, or they can be the same as visual attributes indicating low machine recognition confidence, as discussed below. In the example where the feedback signal is an audible signal, the default attributes can be, for example, an audible tone with a default frequency, a periodic audible beep, an audible recording indicating no available confidence level, etc.

[0029] At box 315, device 100 is configured to capture an image (e.g., an image of mark 104 and a portion of surface 108). At box 320, device 100 is configured to obtain a confidence level associated with machine recognition of mark 104 and / or any other mark from the captured image from box 315. Obtaining the confidence level may include, for example, processing the image from box 315 via a segmentation algorithm and / or any other suitable detection algorithm to determine the location of the mark in the image (e.g., in the form of a bounding box). Obtaining the confidence level may include performing a detection algorithm with the image as input. The detection algorithm may implement a machine learning model, such as a deep neural network (e.g., You Only Look Once (YOLO) or other convolutional neural networks). Such models produce bounding boxes as output, for example, containing possible barcodes, text blocks, etc. Machine recognition algorithms may also produce a confidence level as output, indicating the probability, score, or other metric of the bounding box accuracy, i.e., the likelihood that the bounding box contains text, barcodes, etc. Confidence levels can be expressed as a percentage, a fraction between zero and one, or in any of a variety of other ranges.

[0030] At box 325, device 100 is configured to select feedback attributes for the output device based on a confidence level from box 320, such as selecting a visual feedback attribute for indicator light 120. Visual feedback attributes are visual properties of the indicator light (such as color, intensity (e.g., brightness), blink frequency, etc.). Other visual feedback indicators (such as beam width (affecting the portion of the FOV 116 occupied by indicator light 120)) may also be used as visual feedback attributes. The selection at box 325 may be based on configuration data stored in memory 220 (e.g., as a component of application 232). Other feedback attributes are also contemplated, such as audible feedback attributes, including recordings of the current confidence level (e.g., rendered via a text-to-speech algorithm, etc.), frequencies corresponding to the confidence level, or beeps, etc.

[0031] At box 330, after selecting a visual feedback attribute (or other perceptible feedback attribute) corresponding to the current confidence level (e.g., the confidence level obtained from the most recently executed box 320), device 100 is configured to control an output device to generate a feedback signal having the selected feedback attribute. For example, device 100 may project an indicator light 120 having the selected visual feedback attribute. (Go to...) Figure 4 Example executions of boxes 315 to 330 are shown.

[0032] Figure 4 The configuration setting 400 described above is shown. In the example shown, setting 400 includes three visual feedback attributes that correspond to three different colors (e.g., red, yellow, and green) of the indicator light 120. Many other colors can also be used, and setting 400 can define as few as two or more than three visual feedback attributes. In this example, a confidence level below 60% results in red being selected as the visual feedback attribute at box 325. When box 310 is executed, red is also selected as the default visual feedback attribute at box 310. Yellow is selected as the visual feedback attribute when the confidence level is between 60% and 80%, and green is selected when the confidence level is above 80%. More generally, a given visual feedback attribute can be selected when the confidence level does not exceed a predetermined threshold, and a different visual feedback attribute can be selected when the confidence level exceeds the predetermined threshold. Further thresholds can be defined in setting 400 to achieve finer-grained control over the indicator light 120.

[0033] Figure 4Image 404, showing marker 104, includes, in this example, an indicator light 120 with default visual properties. From image 404, at box 320, device 100 obtains machine recognition data 408, such as the decoded value from marker 104 and a confidence level (e.g., 62%). The confidence level is higher than the lower threshold of 60% shown in setting 400 and lower than the upper threshold of 80%, so device 100 selects yellow at box 325. Therefore, control of emitter 208 at box 330 projects the yellow indicator light 120, replacing the default red light shown in image 404.

[0034] Return to Figure 3 At box 335, device 100 is configured to determine whether an output trigger is detected. The output trigger may include activation of input 124, or other suitable input received at device 100 corresponding to a command to provide machine identification data to application 236. In other examples, the output trigger may be automatically generated by application 232, for example, by comparing a confidence level from box 320 with an output trigger threshold (e.g., 90%, although various other thresholds may also be used), and if the confidence level exceeds the output threshold, initiating a decoding event to extract and provide to application 236 what has been decoded from the detected tag or otherwise extracted.

[0035] When the determination at box 335 is negative, device 100 is configured to determine at box 340 whether to end the capture session. The determination at box 340 may include determining whether input has been received, to close device 100, stop executing application 232, etc. When the determination at box 340 is positive, execution of method 300 ends. Otherwise, device 100 returns to box 315 to capture further images and repeats boxes 320 through 335. In other examples, box 340 may be omitted, and when the determination at box 335 is negative, device 100 may simply return from box 335 to box 315.

[0036] Go to Figure 5 This illustrates another example of execution in boxes 315 to 330. (In combination...) Figure 4 After capturing image 404 and updating the visual appearance of the indicator light 120 (and / or updating any other perceptible feedback signals), device 100 captures further image 504, in which device 100 has been repositioned relative to marker 104. Figure 5As shown, the indicator light 120 has the visual attribute selected in the previous execution of box 325 (in this case, yellow). At box 320, device 100 decodes the value "1a2b3c" from marker 104, with an associated confidence level of 89%. Therefore, at box 325, device 100 selects green as the visual feedback attribute because the confidence level in the machine recognition data 508 exceeds the upper limit threshold of 80% defined in setting 400. Therefore, at box 330, device 100 controls transmitter 208 to project the green indicator light 120 into FOV 116.

[0037] Refer again Figure 3 When the determination at box 335 is affirmative, device 100 proceeds to box 345, initiates a decoding event, and outputs the machine recognition result (e.g., content 408 or content 508, or an error if the decoding event fails) to application 236 for further processing. In some cases, such as if the confidence level associated with the machine recognition of marker 104 is too low (e.g., below the 60% threshold shown in setting 400), the machine recognition result provided at box 345 may not include the decoded value or the extracted text string, but may instead include the confidence level and / or a failure indicator to indicate that the decoding event triggered at box 335 was unsuccessful.

[0038] Following box 345, at box 350, device 100 may be configured to control an output device (such as transmitter 208) to generate a result feedback signal with result feedback attributes, such as projecting an indicator light with result visual feedback attributes, for example, indicating whether a decoding event initiated by an output trigger resulted in successful delivery of decoded data to application 236, or whether decoding failed. For example, setting 400 may include additional settings for result visual attributes, as discussed below. Following box 350, device 100 proceeds to box 340, or directly to box 315. In other examples, box 350 may be omitted.

[0039] Figure 6Further example configuration settings are shown. In some examples, setting 600 may specify a flashing frequency instead of or as a complement to the color of indicator light 120. For example, setting 600 includes a low confidence or default setting, whereby indicator light 120 is red and flashes at a frequency of 2 Hz. Meanwhile, the visual attributes for medium and high confidence are indicated as having no frequency, meaning they are constantly lit. Further, setting 600 defines the result visual feedback attributes for successful and failed decoding events at box 350. In this example, a successful decoding event (e.g., where the confidence level is above 90% and the decoded or extracted value is returned to application 236) produces a green indicator light that flashes once and then remains constantly lit. A failed decoding event (e.g., where the confidence level is below 70% and a failure indication is returned to application 236) produces a red indicator light 120 that flashes once and then remains constantly lit.

[0040] Various other visual attributes can also be specified. For example, the confidence visual attribute can be set to 50% intensity for the 600 indicator, while the high confidence visual attribute can be set to 90% intensity. In other examples, intensity, blink frequency, and color can be combined in ways other than those shown, or they can be used individually (e.g., making the color of indicator light 120 constant, but the intensity varies as the machine identifies the confidence level). In other examples, at box 325, instead of using discrete thresholds, device 100 can select from a range of colors a visual feedback attribute (such as intensity, blink frequency, or color) that is proportional to the confidence level.

[0041] Specific embodiments have been described in the foregoing specification. However, those skilled in the art will understand that various modifications and changes can be made without departing from the scope of the invention as set forth in the appended claims. Therefore, the specification and drawings are to be considered illustrative rather than restrictive, and all such modifications are intended to be included within the scope of this teaching.

[0042] These benefits, advantages, solutions to problems, and any elements(s) that make any benefit, advantage, or solution occur or become more prominent are not to be construed as key, essential, or necessary features or elements of any or all claims. The invention is defined solely by the appended claims, including any amendments made during the pending period of this application and all equivalents of these claims in the patent announcement.

[0043] Furthermore, in this document, relational terms such as first and second, top and bottom, etc., may be used individually to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between such entities or actions. Terms including “comprises,” “comprising,” “has,” “having,” “includes,” “including,” “contains,” “containing,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes, has, includes, or contains a list of elements may include not only those elements but also other elements not expressly listed or inherent to such process, method, article, or apparatus. Elements beginning with "comprises," "has," "includes," or "contains" do not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes, has, includes, or contains that element, unless otherwise expressly stated herein. The term "a / an" is defined as one or more unless otherwise expressly stated herein. The terms "substantially," "essentially," "approximately," "about," or any other version of these terms are defined as being as close as understood by one of ordinary skill in the art, and in one non-limiting embodiment, these terms are defined as within 10%, in another within 5%, in yet another within 1%, and in yet another within 0.5%. The term "coupled" as used herein is defined as connected, although not necessarily directly connected or mechanically connected. A device or structure that is “configured” in a certain way is configured at least in that way, but may also be configured in ways not listed.

[0044] Certain expressions may be used in this document to list combinations of elements. Examples of such expressions include: “at least one of A, B, and C”; “one or more of A, B, and C”; “at least one of A, B, or C”; “one or more of A, B, or C”. Unless otherwise expressly stated, the above expressions cover any combination of A and / or B and / or C.

[0045] It will be understood that some embodiments may include one or more dedicated processors (or "processing devices"), such as microprocessors, digital signal processors, custom processors, and field-programmable gate arrays (FPGAs), and uniquely stored program instructions (including both software and firmware) that control one or more processors to implement some, most, or all of the functions of the methods and / or apparatuses described herein, in conjunction with certain non-processor circuitry. Alternatively, some or all of the functions may be implemented by a state machine without stored program instructions, or in one or more application-specific integrated circuits (ASICs), wherein each function or some combination of certain functions is implemented as custom logic. Of course, a combination of these two approaches may also be used.

[0046] Furthermore, embodiments can be implemented as computer-readable storage media having computer-readable code stored thereon for programming a computer (e.g., including a processor) to perform the methods described and claimed herein. Examples of such computer-readable storage media include, but are not limited to, hard disks, CD-ROMs, optical storage devices, magnetic storage devices, ROMs (read-only memories), PROMs (programmable read-only memories), EPROMs (erasable programmable read-only memories), EEPROMs (electrically erasable programmable read-only memories), and flash memory. Moreover, it is anticipated that those skilled in the art, while making potentially significant efforts driven by, for example, available time, current technology, and economic considerations, and numerous design choices, will be able to readily generate such software instructions and programs, as well as ICs, with minimal experimentation when guided by the concepts and principles disclosed herein.

[0047] This abstract is provided to allow the reader to quickly determine the nature of the disclosure. This abstract is submitted with the understanding that it is not intended to interpret or limit the scope or meaning of the claims. Furthermore, in the above detailed description, it can be seen that various features are grouped together in various embodiments for the purpose of making the disclosure coherent. This method of disclosure should not be construed as reflecting an intention to require more features than are expressly recited in the claims. Rather, as reflected in the appended claims, the inventive subject matter lies in fewer than all the features of a single disclosed embodiment. Therefore, the appended claims are thus incorporated into the detailed description, wherein each claim represents itself as a separately claimed subject matter.

Claims

1. A method in a computing device, the method comprising: Capture the marked image via the sensor; Determine the confidence level associated with the machine recognition of the tag; Based on the stated confidence level, select the feedback attribute; as well as Before outputting the content encoded in the tag, a feedback signal with the feedback attribute is generated via an output device, wherein the attribute is configured to indicate the probability of a successful decoding event for decoding the content encoded in the tag.

2. The method of claim 1, further comprising: Before capturing the image of the marker, default attributes are retrieved and the feedback signal having the default attributes is generated via the output device.

3. The method of claim 1, wherein the output device is a light emitter, and wherein generating the feedback signal comprises projecting an indicator light having the feedback property.

4. The method of claim 3, wherein projecting the indicator light comprises projecting the indicator light into the aiming region of the sensor's field of view.

5. The method of claim 3, wherein the feedback attribute comprises one or more attributes selected from the group consisting of: color; Strength; and Flicker frequency.

6. The method of claim 1, wherein selecting the feedback attribute comprises: When the confidence level exceeds a predetermined threshold, the first feedback attribute is selected; as well as When the confidence level does not exceed the predetermined threshold, the second feedback attribute is selected.

7. The method of claim 1, further comprising: Initiate a decoding event; as well as In response to the decoding event, the content decoded from the marked image is output to the application executing on the computing device.

8. The method of claim 7, further comprising: In response to the decoding event, select the result feedback attribute; as well as The feedback signal having the result feedback attribute is generated via the output device.

9. The method of claim 8, wherein the feedback attribute includes one of color, intensity, or flashing frequency, and wherein the result feedback attribute includes another of color, intensity, or flashing frequency.

10. A computing device, the computing device comprising: sensor; Output devices; as well as Processor, the processor being configured to: The sensor captures images of the markers; Determine the confidence level associated with the machine recognition of the tag; Based on the stated confidence level, select the feedback attribute; as well as A feedback signal having the feedback attribute is generated via the output device, wherein the attribute is configured to indicate the probability of a successful decoding event for decoding the content encoded in the tag.

11. The computing device of claim 10, wherein the processor is further configured to: retrieve a default attribute and generate the feedback signal having the default attribute via the output device before capturing the image of the marker.

12. The computing device of claim 10, wherein the output device is a light emitter, and wherein generating the feedback signal comprises projecting an indicator light having the feedback property.

13. The computing device of claim 12, wherein the processor is configured to project the indicator light by projecting the indicator light into an aiming region of the sensor's field of view.

14. The computing device of claim 12, wherein the feedback attribute includes one or more attributes selected from the group consisting of: color; Strength; and Flicker frequency.

15. The computing device of claim 10, wherein the processor is configured to select the feedback attribute in such a way as: When the confidence level exceeds a predetermined threshold, the first feedback attribute is selected; and When the confidence level does not exceed the predetermined threshold, the second feedback attribute is selected.

16. The computing device of claim 10, wherein the processor is further configured to: Initiate a decoding event; and In response to the decoding event, the content decoded from the marked image is output to the application executing on the computing device.

17. The computing device of claim 16, wherein the processor is further configured to: In response to the decoding event, select the result feedback attribute; and The output device is controlled to generate the feedback signal having the result feedback attribute.

18. The computing device of claim 17, wherein the feedback attribute includes one of color, intensity, or flashing frequency, and wherein the result feedback attribute includes another of color, intensity, or flashing frequency.

19. A method in a computing device, the method comprising: Control the light emitter to project indicator light with default visual properties onto the surface carrying the mark; The image of the marker is captured via a sensor; Determine the confidence level associated with the machine recognition of the tag; Based on the confidence level, select the visual feedback attribute; as well as The light emitter is controlled to project an indicator light having the visual feedback property.

20. The method of claim 19, further comprising: After the projection, the machine recognizes the output event; as well as In response to the machine recognition output event, a machine recognition result derived from the marked image is output to the application executing on the computing device.

Images