-
公开(公告)号：US20190080149A1
公开(公告)日：2019-03-14
申请号：US15934559
申请日：2018-03-23
Applicant: Apple Inc.
Inventor： Thorsten Gernoth , Ian R. Fasel , Touraj Tajbakhsh , Jia-Chi Wu
Abstract: Occlusion of facial features may be detected and assessed in an image captured by a camera on a device. Landmark heat maps may be used to estimate the location of landmarks such as the eyes, mouth, and nose of a user's face in the captured image. An occlusion heat map may also be generated for the captured image. The occlusion heat map may include values representing the amount of occlusion in regions of the face. The estimated locations of the eyes, mouth, and nose may be used in combination with the occlusion heat map to assess occlusion scores for the landmarks. The occlusion scores for the landmarks may be used control one or more operations of the device.
-
公开(公告)号：US20170289512A1
公开(公告)日：2017-10-05
申请号：US15626629
申请日：2017-06-19
Applicant: Apple Inc.
Inventor： Yingjun Bai , Michael Chin , Touraj Tajbakhsh
CPC classification number: H04N9/735 , H04N1/60 , H04N1/6086 , H04N5/2353 , H04N5/3572
Abstract: This disclosure pertains to systems, methods, and computer readable media for performing lens shading correction (LSC) operations that modulate gains based on scene lux level and lens focus distance. These gains compensate for both color lens shading (i.e., the deviation between R, G, and B channels) and vignetting (i.e., the drop off in pixel intensity around the edges of an image). As scene illuminance increases, the sensor captures more signal from the actual scene, and the lens shading effects begin to appear. To deal with the situation, the lens shading gains are configured to adaptively ‘scale down’ when scene lux approaches zero and ‘scale up’ when scene lux changes from near zero to become larger. The lens shading gain may also be modulated based on the focus distance. For optical systems without zoom, the inventors have discovered that the amount of lens shading fall off changes as focus distance changes.
-
公开(公告)号：US09699428B2
公开(公告)日：2017-07-04
申请号：US14269941
申请日：2014-05-05
Applicant: Apple Inc.
Inventor： Yingjun Bai , Michael Chin , Touraj Tajbakhsh
CPC classification number: H04N9/735 , H04N1/60 , H04N1/6086 , H04N5/2353 , H04N5/3572
Abstract: This disclosure pertains to systems, methods, and computer readable media for performing lens shading correction (LSC) operations that modulate gains based on scene lux level and lens focus distance. These gains compensate for both color lens shading (i.e., the deviation between R, G, and B channels) and vignetting (i.e., the drop off in pixel intensity around the edges of an image). As scene illuminance increases, the sensor captures more signal from the actual scene, and the lens shading effects begin to appear. To deal with the situation, the lens shading gains are configured to adaptively ‘scale down’ when scene lux approaches zero and ‘scale up’ when scene lux changes from near zero to become larger. The lens shading gain may also be modulated based on the focus distance. For optical systems without zoom, the inventors have discovered that the amount of lens shading fall off changes as focus distance changes.
-
公开(公告)号：US09648261B2
公开(公告)日：2017-05-09
申请号：US14836918
申请日：2015-08-26
Applicant: Apple Inc.
Inventor： Suk Hwan Lim , David R. Pope , Touraj Tajbakhsh
CPC classification number: H04N5/3675 , G06T5/20 , H04N5/23212 , H04N5/357 , H04N5/3572 , H04N9/045
Abstract: An image processing pipeline may account for clipped pixels in auto focus statistics. Generating auto focus statistics may include evaluating a neighborhood of pixels with respect to a given pixel in a stream of pixels for an image. If a clipped pixel is identified within the neighborhood of pixels then the evaluation of the given pixel may be excluded from an auto focus statistic. The image processing pipeline may also provide auto focus statistics that do not exclude clipped pixels. A luminance edge detection value may, in some embodiments, be generated by applying an IIR filter to the given pixel in a stream of pixels to band-pass filter the given pixel before including the band-pass filtered pixel in the generation of the luminance edge detection value.
-
公开(公告)号：US11100620B2
公开(公告)日：2021-08-24
申请号：US16121389
申请日：2018-09-04
Applicant: Apple Inc.
Inventor： Touraj Tajbakhsh , Chihsin Wu , Frederic Cao
Abstract: Embodiments relate to hue preservation post processing for highlight recovery of an input image. Intensity values for multiple color channels of a plurality of color channels of a pixel of the input image is determined using corresponding ratios of target hues for the plurality of color channels of the pixel, wherein the pixel has at least one color channel with an intensity above a predetermined threshold. A hue preserved value for a color channel of the plurality of color channels of the pixel is determined using intensity values determined for the plurality of color channels of the pixel and the target hues. A recovered version of the input image is generated by adjusting hue information of the pixel, using the hue preserved value for the channel of the plurality of color channels of the pixel.
-
Patent Agency Ranking
公开(公告)号：US10171786B2
公开(公告)日：2019-01-01
申请号：US15626629
申请日：2017-06-19
Applicant: Apple Inc.
Inventor： Yingjun Bai , Michael Chin , Touraj Tajbakhsh
Abstract: This disclosure pertains to systems, methods, and computer readable media for performing lens shading correction (LSC) operations that modulate gains based on scene lux level and lens focus distance. These gains compensate for both color lens shading (i.e., the deviation between R, G, and B channels) and vignetting (i.e., the drop off in pixel intensity around the edges of an image). As scene illuminance increases, the sensor captures more signal from the actual scene, and the lens shading effects begin to appear. To deal with the situation, the lens shading gains are configured to adaptively ‘scale down’ when scene lux approaches zero and ‘scale up’ when scene lux changes from near zero to become larger. The lens shading gain may also be modulated based on the focus distance. For optical systems without zoom, the inventors have discovered that the amount of lens shading fall off changes as focus distance changes.
-
公开(公告)号：US20150070570A1
公开(公告)日：2015-03-12
申请号：US14269814
申请日：2014-05-05
Applicant: Apple Inc.
Inventor： Touraj Tajbakhsh , Yingjun Bai , Haitao Guo
IPC: H04N5/235
CPC classification number: H04N9/735 , H04N1/60 , H04N1/6086 , H04N5/2353 , H04N5/3572
Abstract: This disclosure pertains to systems, methods, and computer readable media for extending the dynamic range of images using an operation referred to herein as “Adaptive Auto Exposure” (AAE). According to the embodiments disclosed herein, the AAE-enabled higher dynamic range capture operations are accomplished without blending multiple or bracketed exposure captures (as is the case with traditional high dynamic range (HDR) photography). AAE also enables high signal-to-noise ratio (SNR) rendering when scene content allows for it and/or certain highlight clipping is tolerable. Decisions with regard to preferred AE strategies may be based, at least in part, on one or more of the following: sensor characteristics; scene content; and pre-defined preferences under different scenarios.
Abstract translation: 本公开涉及用于使用本文称为“自适应自动曝光”（AAE）的操作来扩展图像的动态范围的系统，方法和计算机可读介质。 根据本文公开的实施例，在不混合多个或包围曝光捕获的情况下（如传统的高动态范围（HDR）拍摄的情况）），实现了启用AAE的较高动态范围捕获操作。 当场景内容允许时，AAE还能实现高信噪比（SNR）渲染，和/或某些高亮度剪辑是可以容忍的。 关于优选AE策略的决定可以至少部分地基于以下一个或多个：传感器特征; 场景内容; 和不同场景下的预定义偏好。
-
公开(公告)号：US11620738B2
公开(公告)日：2023-04-04
申请号：US17373362
申请日：2021-07-12
Applicant: Apple Inc.
Inventor： Touraj Tajbakhsh , Chihsin Wu , Frederic Cao
Abstract: Embodiments relate to hue preservation post processing for highlight recovery of an input image. Intensity values for multiple color channels of a plurality of color channels of a pixel of the input image is determined using corresponding ratios of target hues for the plurality of color channels of the pixel, wherein the pixel has at least one color channel with an intensity above a predetermined threshold. A hue preserved value for a color channel of the plurality of color channels of the pixel is determined using intensity values determined for the plurality of color channels of the pixel and the target hues. A recovered version of the input image is generated by adjusting hue information of the pixel, using the hue preserved value for the channel of the plurality of color channels of the pixel.
-
公开(公告)号：US11367305B2
公开(公告)日：2022-06-21
申请号：US16549009
申请日：2019-08-23
Applicant: Apple Inc.
Inventor： Touraj Tajbakhsh , Jonathan Pokrass , Feng Tang
Abstract: A facial recognition process operating on a device may include one or more processes that determine if a camera and/or components associated with the camera are obstructed by an object (e.g., a user's hand or fingers). Obstruction of the device may be assessed using flood infrared illumination images when a user's face is not able to be detected by a face detection process operating on the device. Obstruction of the device may also be assessed using a pattern detection process that operates after the user's face is detected by the face detection process. When obstruction of the device is detected, the device may provide a notification to the user that the device (e.g., the camera and/or an illuminator) is obstructed and that the obstruction should be removed for the facial recognition process to operate correctly.
-
公开(公告)号：US09686448B2
公开(公告)日：2017-06-20
申请号：US14836586
申请日：2015-08-26
Applicant: Apple Inc.
Inventor： Touraj Tajbakhsh , Kostadin N. Dabov
Abstract: Methods and systems to improve the operation of graphic's system are described. In general, techniques are disclosed for compensating for an image sensor's non-zero black-level output. More particularly, a image sensor noise model may be used to offset an image's signal prior to clipping so that the image's dark signal exhibits a linear or near linear mean characteristic after clipping. In one implementation the noise model may be based on calibration or characterization of the image sensor prior to image capture. In another implementation the noise model may be based on an evaluation of the image itself during image capture operations. In yet another implementation the noise model may be based on analysis of an image post-capture (e.g., hours, days, . . . after initial image capture).
-
-
-
-
-
-
-
-
-
Search Results
23
records
(took 0.015 seconds)
