Method and apparatus for extracting feature points from digital image
First Claim
1. A method of extracting feature points from a digital image in a multiprocessor system using a scale invariant feature transform (SIFT) technique, the method comprising:
- dividing an original image into a plurality of regions so as to be allocated to a plurality of processors of the multiprocessor system;
performing, by the plurality of processors, blurring operations by levels;
dividing the images blurred by levels into a plurality of regions to be allocated to the processors and calculating, by the plurality of processors, differences of Gaussian (DoGs); and
generating feature point data according to the calculated DoGs, wherein;
the performing of the blurring operations comprises;
adding a predetermined number of virtual pixels to both borders of an original line to produce a revised line on which the blurring operation is to be performed;
performing convolution operations on all pixels of the revised line using a blur kernel; and
correcting a result value obtained from one of the convolution operations in which one or more of the virtual pixels is used for calculating the result value, and the correcting the result value comprises;
generating a correction weight which indicates a ratio of a sum of kernel values applied to pixels other than the virtual pixels in the one of the convolution operations to the sum of all kernel values; and
dividing the result value by the generated correction weight.
1 Assignment
0 Petitions
Accused Products
Abstract
An apparatus and method for extracting feature points from an image in a multiprocessor system having a plurality of processors, the method including: dividing an original image into a plurality of regions so as to be allocated to a plurality of processors of the multiprocessor system; performing, by the plurality of processors, blurring operations by levels; dividing the images blurred by levels into a plurality of regions to be allocated to the processors and calculating, by the plurality of processors, differences of Gaussian (DoGs); and generating feature point data according to the calculated DoGs. Because a plurality of processors performs the operations of the method, the total time to extract the feature points from the image is significantly reduced.
-
Citations
18 Claims
-
1. A method of extracting feature points from a digital image in a multiprocessor system using a scale invariant feature transform (SIFT) technique, the method comprising:
-
dividing an original image into a plurality of regions so as to be allocated to a plurality of processors of the multiprocessor system; performing, by the plurality of processors, blurring operations by levels; dividing the images blurred by levels into a plurality of regions to be allocated to the processors and calculating, by the plurality of processors, differences of Gaussian (DoGs); and generating feature point data according to the calculated DoGs, wherein; the performing of the blurring operations comprises; adding a predetermined number of virtual pixels to both borders of an original line to produce a revised line on which the blurring operation is to be performed; performing convolution operations on all pixels of the revised line using a blur kernel; and correcting a result value obtained from one of the convolution operations in which one or more of the virtual pixels is used for calculating the result value, and the correcting the result value comprises; generating a correction weight which indicates a ratio of a sum of kernel values applied to pixels other than the virtual pixels in the one of the convolution operations to the sum of all kernel values; and dividing the result value by the generated correction weight. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A multiprocessor apparatus to extract feature points from a digital image according to a scale invariant feature transform (SIFT) technique, the apparatus comprising:
-
a plurality of processors to perform blurring operations by levels on corresponding regions of the digital image and to calculate differences of Gaussian (DoGs) on corresponding regions of the images blurred by levels; and at least one processor to generate feature point data according to the calculated DoGs wherein; the plurality of processors add a predetermined number of virtual pixels to both borders of an original line to produce a revise line on which the blurring operation is to be performed and perform convolution operations on all pixels of the revised line using a blur kernel, and at least one processor corrects a result value obtained from one of the convolution operations in which one or more of the virtual pixels is used for calculating the result value by generating a correction weight which indicates a ratio of a sum of kernel values applied to pixels other than the virtual pixels used in the one of the convolution operations to the sum of all kernel values and dividing the result value by the generated correction weight. - View Dependent Claims (13, 14, 15, 16, 17, 18)
-
Specification