Simd algorithm for image dilation and erosion processing

Patent metadata

Field	Value
Publication number	US-2016292877-A1
Application number	US-201313977509-A
Country	US
Kind code	A1
Filing date	Mar 29, 2013
Priority date	Mar 29, 2013
Publication date	Oct 6, 2016
Grant date	—

Abstract

Systems and methods may receive an input image for data processing, divide the input image into a plurality of blocks, each block including a plurality of rows, and each row including a plurality of pixels and process each pixel in the input image within a row in parallel with a user-defined template. In one example, the user-defined template is to include a structuring element and a row pixel mask.

First claim

1 - 25 . (canceled)

26 . An apparatus to process images, comprising:
a receive module to receive an input image for data processing; a divide module to divide the input image into a plurality of blocks, each block including a plurality of rows, and each row including a plurality of pixels; and a preprocessing module to process each pixel in the input image within a row in parallel with a user-defined template.

27 . The apparatus of claim 26 , further comprising:
a module to perform a morphological operation on each preprocessed pixel using a matrix.

28 . The apparatus of claim 26 , wherein the user-defined template is to include a structuring element.

29 . The apparatus of claim 26 , wherein the user-defined template is to include a mask for processing each pixel in a particular row of a matrix.

30 . The apparatus of claim 29 , wherein a mask value of “1” indicates that a corresponding pixel should be used in calculating a result and a mask value of “0” indicates that a corresponding pixel should not be used in calculating a result.

31 . The apparatus of claim 26 , wherein the pixels in a row are processed in parallel using single instruction multiple data (SIMD) instructions.

32 . The apparatus of claim 26 , wherein each pixel is to include one bit per pixel.

33 . The apparatus of claim 26 , wherein the morphological operation is one of a dilation operation or erosion operation.

34 . A method of processing images, comprising:
receiving an input image for data processing; dividing the input image into a plurality of blocks, each block including a plurality of rows, and each row including a plurality of pixels; and preprocessing each pixel in the input image within a row in parallel with a user-defined template.

35 . The method of claim 34 , further comprising:
performing a morphological operation on each preprocessed pixel using a matrix.

36 . The method of claim 34 , wherein the user-defined template is to include a structuring element.

37 . The method of claim 34 , wherein the user-defined template is to include a mask for processing each pixel in a particular row of a matrix.

38 . The method of claim 37 , wherein a mask value of “1” indicates that a corresponding pixel should be used in calculating a result and a mask value of “0” indicates that a corresponding pixel should not be used in calculating a result.

39 . The method of claim 34 , wherein the pixels in a row are processed in parallel using single instruction multiple data (SIMD) instructions.

40 . The method of claim 34 , wherein each pixel is to include one bit per pixel.

41 . The method of claim 34 , wherein the morphological operation is one of a dilation operation or erosion operation.

42 . At least one computer readable storage medium comprising instructions, which if executed by a computing device, cause the computing device to:
receive an input image for data processing; divide the input image into a plurality of blocks, each block including a plurality of rows, and each row including a plurality of pixels; and preprocess each pixel in the input image within a row in parallel with a user-defined template.

43 . The at least one computer readable storage medium of claim 42 , further comprising instructions, which if executed by a processor, cause a computing device to:
perform a morphological operation on each preprocessed pixel using a matrix.

44 . The at least one computer readable storage medium of claim 42 , wherein the user-defined template is to include a structuring element.

45 . The at least one computer readable storage medium of claim 42 , wherein the user-defined template is to include a mask for processing each pixel in a particular row of a matrix.

46 . A system comprising:
a storage device to store an input image; a receive module to receive the input image for data processing; a divide module to divide the input image into a plurality of blocks, each block including a plurality of rows, and each row including a plurality of pixels; and a preprocessing module to process each pixel in the input image within a row in parallel with a user-defined template.

47 . The apparatus of claim 46 , further comprising:
a module to perform a morphological operation on each preprocessed pixel using a matrix.

48 . The apparatus of claim 46 , wherein the user-defined template is to include a structuring element.

49 . The apparatus of claim 46 , wherein the user-defined template is to include a mask for processing each pixel in a particular row of a matrix.

50 . The apparatus of claim 49 , wherein a mask value of “1” indicates that a corresponding pixel should be used in calculating a result and a mask value of “0” indicates that a corresponding pixel should not be used in calculating a result.

51 . An apparatus to process images, comprising means for performing the method of claim 34 .

Assignees

• Yuan Hao
• Tang Li-An
• Intel Corp

Inventors

• Yuan Hao
• Tang Li-An

Classifications

• G06T2207/10116

  X-ray image · CPC title

• G06T2200/28

  involving image processing hardware · CPC title

• G06T2207/20021

  Dividing image into blocks, subimages or windows · CPC title

• G06T2210/52

  Parallel processing · CPC title

• G06T1/20 Primary

  Processor architectures; Processor configuration, e.g. pipelining · CPC title