IP Verse

Real Time Assessment Of Picture Quality

Patent No. US10944901 (titled "Real Time Assessment Of Picture Quality") was filed by Snapaid Ltd on May 6, 2020.

What is this patent about?

’901 is related to the field of image processing, specifically to systems and methods for assessing the quality of captured images in real-time on devices like smartphones. The background acknowledges that even with advanced auto modes, users often take multiple pictures to ensure a good one, and existing software offers limited enhancement tools. The patent aims to improve the user experience by providing real-time feedback and suggestions for better image capture.

The underlying idea behind ’901 is to leverage various sensors and image analysis techniques to compute a comprehensive photo quality score by combining multiple quality indicators. This score is not just a static value but dynamically adjusts based on the confidence level of each indicator and their interdependencies. The system then uses this score to provide feedback to the user, guiding them to take better pictures.

The claims of ’901 focus on a method implemented in a device with a camera, motion sensor (accelerometer/gyroscope), and a processor. The method involves obtaining values related to device angle (QI1) and aesthetic quality (QI2), estimating weights for these values, and if either value is below a threshold, selecting and presenting a suggestion to the user from a pre-stored table. Another claim focuses on video quality estimation, incorporating device motion (QI1), exposure (QI2), object analysis (QI3), and lens obstruction (QI4) to provide user suggestions.

In practice, the invention uses data from the camera module (focus, ISO, etc.) and motion sensors to compute various quality indicators like blur, shake, and exposure. A key aspect is the dynamic weighting of these indicators based on their reliability and relevance. For example, if the device is shaking significantly, the aesthetic quality indicator might be temporarily disregarded. The system then compares the combined quality score against a threshold and provides real-time feedback to the user, such as suggesting they hold the device steadier or adjust the exposure.

The differentiation from prior approaches lies in the holistic and adaptive nature of the quality assessment. Unlike previous systems that rely on fixed weights or manual adjustments, ’901 dynamically adjusts the importance of each quality indicator based on sensor data, image analysis, and user preferences. This allows the system to provide more accurate and context-aware feedback, ultimately helping users capture better images in a wider range of conditions. The use of confidence levels for each quality indicator further enhances the robustness of the system.

How does this patent fit in bigger picture?

Technical landscape at the time

In the early 2010s when ’901 was filed, cameras, including those in mobile devices, were increasingly equipped with sensors like accelerometers and gyroscopes. At a time when image processing was typically implemented using dedicated hardware or GPUs to handle the computational load of real-time analysis. When systems commonly relied on analyzing image histograms and identifying over/underexposed regions to assess image quality. When hardware or software constraints made real-time feedback to the user based on multiple sensor inputs and complex image analysis non-trivial.

Novelty and Inventive Step

The examiner approved the application because the prior art does not teach obtaining a first value responsive to the device angle to the horizon, estimating a first weight associated with the first value, obtaining a second value associated with an aesthetic quality of image based on the composition, and estimating a second weight associated with the second value. The examiner further stated that the prior art does not teach selecting at least one appropriate suggestion from a pre-stored table of suggestions of how a user may cause at least one of the values to be above a threshold and presenting said appropriate suggestion to the user when taken in combination with all the limitations of the independent claim.

Claims

This patent includes 20 claims, with claims 1 and 10 being independent. The independent claims are directed to methods for estimating image quality using values and weights derived from device sensors and image analysis, and providing suggestions to the user based on these estimations. The dependent claims generally elaborate on the specifics of the calculations, sensors, suggestions, and image analysis techniques used in the methods.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Aesthetic quality of image
(Claim 1)		“For example, a scene with face recognition in 216 and a very small aperture, say f10 with focus distance in the hyper focal distance of component, 200 yields a bad quality, whereas a wide aperture, say f2.8 on these conditions, yields a good quality.”A value (QI2) that is associated with the aesthetic quality of the image based on the composition.
Device angle to the horizon
(Claim 1)		“Typically, each available sensor, e.g. accelerometers, gyros, sends its raw data to a processing component 400 that outputs a quality indicator e.g. as illustrated in background blurring, which may sometimes actually be desired.”A value (QI1) that is responsive to the angle of the device relative to the horizon.
Obstruction of at least one optical lens
(Claim 10)		“Obstructing the lens may occur as a result of putting the finger partly or fully on the lens. For example, in bright conditions there may be a brown-red area in one corner. In dark conditions there may be no light at all in that location. Confidence in having recognized the situation may be enhanced as more frames are taken and the camera is moved around because if there is no obstruction on the lens, then the size of the area previously believed to be obstructed, would change significantly.”A value (QI4) responsive to obstruction of at least one optical lens.
Pre-stored table of suggestions
(Claim 1, Claim 10)		“Certain embodiments seek to utilize camera hardware such as accelerometers, gyros and autofocus lenses, inter alia, to evaluate pictures taken in real time, and actively assist in obtaining the best picture given the circumstances at hand.”A table containing suggestions of how a user may cause at least one value to be above or below a threshold.
Under or over exposure
(Claim 10)		“Given configurable under and over thresholds (say 5% from pure white and 3% from pure black) the image frame given to the GPU is processed to compute areas that are underexposed and areas that are overexposed, e.g. similar to the zone system by Ansel Adams known in the field of photography.”A measurement (QI2) of under or over exposure of the image.

Patent Family

Patent Family

File Wrapper

The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.

  • Date

    Description

  • Get instant alerts for new documents

US10944901

SNAPAID LTD
Application Number
US16867919
Filing Date
May 6, 2020
Status
Granted
Expiry Date
Oct 22, 2033
External Links
Slate, USPTO, Google Patents