公开(公告)号：US10798420B2

公开(公告)日：2020-10-06

申请号：US15683558

申请日：2017-08-22

Applicant: Apple Inc.

Inventor： Lars M. Lindberg ,  Ali Sazegari ,  Paul S. Chang

IPC: H04N19/66 ,  H04N19/593 ,  H04N19/48 ,  H04N19/59 ,  H04N19/436

Abstract: Disclosed herein are techniques for performing lossless compression of single-channel images (e.g., grayscale images). A first technique involves pre-processing an isolated (i.e., one) single-channel image for compression. In particular, the first technique involves calculating predicted pixel intensity values (within the single-channel image) based on neighboring pixel intensity values (also within the single-channel image). Bit values of the error margins of the predicted pixel intensity values are separated into two different byte streams according to a particular ordering, whereupon the byte streams are separately compressed (e.g., using a Lempel-Ziv-Welch (LZW)-based compressor) and joined together to produce a compressed single-channel image. A second technique involves pre-processing a group of single-channel images into one single-channel image for compression. In particular, the second technique involves interleaving pixel intensity values of the single-channel images to produce an interleaved single-channel image, and subsequently compressing the interleaved single-channel image (e.g., using an LZW-based compressor).

公开(公告)号：US10362325B2

公开(公告)日：2019-07-23

申请号：US15994891

申请日：2018-05-31

Applicant: Apple Inc.

Inventor： Lars M. Lindberg ,  Paul S. Chang ,  Ali Sazegari

IPC: H04N19/46 ,  H04N19/184 ,  H04N19/182 ,  H04N19/60 ,  H04N19/186 ,  H04N19/61 ,  H04N19/11 ,  H04N19/154 ,  H04N19/88

Abstract: Disclosed are techniques for pre-processing an image for compression, e.g., one that includes a plurality of pixels, where each pixel is composed of sub-pixels that include at least an alpha sub-pixel. First, the alpha sub-pixels are separated into a first data stream. Next, invertible transformations are applied to the remaining sub-pixels to produce transformed sub-pixels. Next, for each row of the pixels: (i) identifying a predictive function that yields a smallest prediction differential total for the row, (ii) providing an identifier of the predictive function to a second data stream, and (iii) converting the transformed sub-pixels of the pixels in the row into prediction differentials based on the predictive function. Additionally, the prediction differentials for each of the pixels are encoded into first and second bytes that are provided to third and fourth data streams, respectively. In turn, the various data streams are compressed into a compressed image.

公开(公告)号：US10362319B2

公开(公告)日：2019-07-23

申请号：US15665404

申请日：2017-07-31

Applicant: Apple Inc.

Inventor： Lars M. Lindberg ,  Paul S. Chang ,  Ali Sazegari

IPC: H04N19/186 ,  H04N19/182 ,  H04N19/60 ,  H04N19/61 ,  H04N19/593

Abstract: Disclosed are techniques for pre-processing an image for compression, e.g., one that includes a plurality of pixels, where each pixel is composed of sub-pixels that include at least an alpha sub-pixel. First, the alpha sub-pixels are separated into a first data stream. Next, invertible transformations are applied to the remaining sub-pixels to produce transformed sub-pixels. Next, for each row of the pixels: (i) identifying a predictive function that yields a smallest prediction differential total for the row, (ii) providing an identifier of the predictive function to a second data stream, and (iii) converting the transformed sub-pixels of the pixels in the row into prediction differentials based on the predictive function. Additionally, the prediction differentials for each of the pixels are encoded into first and second bytes that are provided to third and fourth data streams, respectively. In turn, the various data streams are compressed into a compressed image.

公开(公告)号：US10809869B2

公开(公告)日：2020-10-20

申请号：US15700113

申请日：2017-09-09

Applicant: Apple Inc.

Inventor： Lars M. Lindberg ,  Paul S. Chang ,  Ali Sazegari

IPC: G06F3/0481 ,  H04N19/17 ,  H04L29/06 ,  H04N19/167 ,  H04N19/117 ,  H04N19/23 ,  H04N19/174

Abstract: Disclosed are techniques for pre-processing layered images prior to compression and distribution. According to some embodiments, a technique can include accessing at least two images of a layered image: (i) a background image, and (ii) one or more layer images. Next, a flattened image is generated based on the at least two images. Next, respective one or more delta layer images are generated for the one or more layer images by: for at least one pixel of each layer image having (i) an alpha sub-pixel set to fully opaque, and (ii) a first color property equivalent to a second color property of a corresponding pixel within the flattened image: setting bits of the first color property of the pixel to the same value (e.g., zero (0) or one (1)). Finally, the one or more delta layer images are compressed and provided to a destination computing device.

公开(公告)号：US10546044B2

公开(公告)日：2020-01-28

申请号：US16035516

申请日：2018-07-13

Applicant: Apple Inc.

Inventor： Lars M. Lindberg ,  Ali Sazegari ,  Paul S. Chang

IPC: G06F17/15 ,  G06F17/00 ,  G06F17/10 ,  G06T5/20 ,  H03H17/02 ,  G06K9/36

Abstract: This application relates to an optimization for a technique for filtering an input signal according to a convolution kernel that is stored in a floating point format. A method for filtering the input signal includes: receiving a set of filter coefficients that define the convolution kernel; determining an order for a plurality of floating point operations configured to generate an element of an output signal; and filtering the input signal by the convolution kernel to generate the output signal. Each floating point operation corresponds with a particular filter coefficient, and the order for the plurality of floating point operations is determined based on a magnitude of the particular filter coefficient associated with each floating point operation. The filtering is performed by executing the plurality of floating point operations according to the order. The data path can be a half-precision floating point data path implemented on a processor.