IP Verse

Real Time Assessment Of Picture Quality

Patent No. US11671702 (titled "Real Time Assessment Of Picture Quality") was filed by Snapaid Ltd on Feb 8, 2022.

What is this patent about?

’702 is related to the field of image processing, specifically to the analysis of photographed images. Modern cameras, even with advanced auto modes, still require user assessment of image quality. Users often take multiple pictures to ensure at least one good shot. Existing software offers post-processing enhancement tools, but real-time assistance in capturing the best possible image is lacking. The patent addresses this by using camera hardware and software to evaluate and improve picture quality in real time.

The underlying idea behind ’702 is to combine multiple quality indicators derived from various sensors and image analysis techniques to provide real-time feedback and suggestions to the user. Instead of relying on a single quality metric or manually adjusted weights, the invention dynamically adjusts the importance of each indicator based on its reliability and relevance, considering factors like device shake, focus quality, and aesthetic preferences. This allows the system to intelligently guide the user towards capturing a better image.

The claims of ’702 focus on a computerized method for estimating image quality using a device with a camera, motion sensor, and processor. Specifically, claim 1 covers obtaining values related to device motion (QI1), under/over exposure (QI2), face properties (QI3), and lens obstruction (QI4), and then selecting and presenting suggestions to the user based on these values. Claim 11 covers obtaining values related to device angle to the horizon (QI1) and aesthetic quality (QI2), and then selecting and presenting suggestions to the user based on these values.

In practice, the invention uses data from sensors like accelerometers, gyroscopes, and the camera lens itself to compute various quality indicators. For example, accelerometer data is used to detect device shake, while image analysis algorithms detect blur and identify faces. These indicators are then combined, taking into account their individual confidence levels, to generate a total quality score. Based on this score, the system provides feedback to the user, such as suggesting to hold the camera steadier or adjust the exposure settings.

The invention differentiates itself from prior approaches by dynamically adjusting the weights of individual quality indicators based on their reliability and relevance. Unlike systems that use fixed weights or require manual adjustments, ’702 considers the interdependencies between different indicators. For example, if the device shake indicator is high, the system might disregard the aesthetic quality indicator to prevent taking a blurry picture. This dynamic weighting and confidence level assessment allows for more intelligent and context-aware image quality evaluation and guidance.

How does this patent fit in bigger picture?

Technical landscape at the time

In the early 2010s when ’702 was filed, cameras in mobile devices were increasingly equipped with sensors such as accelerometers and gyroscopes, but at a time when these sensors were typically used for basic orientation and motion detection rather than sophisticated real-time image quality assessment. At that time, image processing algorithms commonly relied on basic histogram analysis and face detection, when hardware or software constraints made complex scene understanding and dynamic range optimization non-trivial.

Novelty and Inventive Step

Claims were rejected during prosecution. Specifically, claims 31-40 were rejected for nonstatutory double patenting. Claims 21-30 were allowed. The prosecution record describes the examiner's reasoning for allowance, stating that the prior art does not teach certain combinations of steps related to motion sensing, exposure measurement, face detection, and lens obstruction detection.

Claims

This patent contains 20 claims, with independent claims 1 and 11 directed to methods for estimating image quality using a device with a camera and motion sensor, and providing suggestions to the user. The dependent claims generally elaborate on the specifics of the image quality estimation, the values used, and the suggestions provided to the user.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Device angle to the horizon
(Claim 11)		“As already described, the speed of the device in each direction may be measured and the distance traveled may be computed.”The angle of the device relative to the horizon.
Device motion
(Claim 1, Claim 11)		“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.”Movement of the device, sensed by a motion or location sensor.
Face exposure
(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 property of a detected face related to its exposure level in the image.
Obstruction of at least one optical lens
(Claim 1)		“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.”Blocking of the lens, possibly by a finger or other object.
Under or over exposure
(Claim 1)		“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 of how much a part of an image or a face in the image is underexposed or overexposed.

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

US11671702

SNAPAID LTD
Application Number
US17666585
Filing Date
Feb 8, 2022
Status
Granted
Expiry Date
Oct 22, 2033
External Links
Slate, USPTO, Google Patents