Integrated circuit for nonlinear data encoding
AssigneeSamsung Display Co., Ltd.
InventorDavid M. Hoffman
Life of this patent
Estimating the term…
Abstract
A method of image processing, the method including performing linear processing of an input data signal encoded with a nonlinear function to generate a linear representation of the input data signal including linearized image data, and using an integrated circuit to generate a processed linear image by nonlinearly quantizing the linearized image data to generate nonlinear quantized data, generating a memory address based on the nonlinear quantized data, and accessing a lookup table based on the generated memory address.
Claims20
A method of nonlinear encoding, the method comprising:
- receiving a linearized data;
- identifying a data block of a plurality of data blocks that contains the linearized data, wherein each data block corresponds to a boundary slice, an offset, and a block bit shift;
- bit-shifting the linearized data according to the block bit shift of the data block to generate most significant bits;
- bit shifting the boundary slice of a previous data block according to the block bit shift to generate a boundary slice offset;
- and
- generating a nonlinear quantized data according to the most significant bits, the offset, and the boundary slice offset.
A compressive lookup table implemented by:
- at least one register for storing a boundary slice, a block bit shift, and an offset for each data block of a plurality of data blocks;
- a compressive addressing computation processor configured to receive a linearized input data and to perform a quantization function on the linearized input data,
- wherein performing a quantization function on the linearized input data comprises:
- identifying a data block from the plurality of data blocks that contains the linearized input data;
- bit-shifting the linearized input data according to a block bit shift of the data block to generate most significant bits;
- bit-shifting the boundary slice of a previous data block according to the block bit shift to generate a boundary slice offset;
- and
- generating a nonlinear quantized data according to the most significant bits, the offset, and the boundary slice offset.
A method of image processing comprising:
- receiving an input image data encoded with a nonlinear function;
- generating a linearized image data by performing linear processing on the input image data;
- and
- retrieving an output value associated with the linearized image data,
- wherein the retrieving the output value comprises:
- determining a data block of a plurality of data blocks that contains the linearized image data wherein each data block of the plurality of data block corresponds to a boundary slice, a block bit shift, and an offset;
- dividing the linearized image data according to the block bit shift corresponding to the data block to generate most significant bits;
- dividing the boundary slice of an adjacent data block by the block bit shift to generate a boundary slice offset;
- calculating a memory address by subtracting boundary slice offset from the most significant bits and adding an offset of the data block;
- and
- retrieving the output value from the memory address.
Dependencies are inferred from the claim text.