DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/14/2025 and 09/25/2025 has/have been considered by the examiner.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-4, 9-12, and 16-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chefd'hotel et al (US 20080247646 A1), hereinafter Chefd'hotel in view of Meyer (2015 ICAPR).
-Regarding claim 1, Chefd'hotel discloses a system, comprising (Abstract; FIGS. 1-6; [0044]): a processor that executes computer-executable components stored in a non-transitory computer-readable memory, wherein the computer-executable components comprise (one or more processors and memories has to be used in order implement’s Chefd'hotel’s FIG. 2): an access component that accesses an image generated by a scientific instrument (FIGS. 1A-1F; 5; FIG. 2, step 200; [0003], “CT or MRI”); and an execution component that performs marker-based watershed segmentation on a region adjacency graph of the image (FIG. 2, steps 202-212; [0004], “watershed transform … partition an image into disjoint regions … watershed segmentation algorithm …”; [0008], “constraining the segmentation process with markers”; [0010], “marker-based geodesic partitioning algorithm”; [0013]; [0022], “compute watersheds … set regions containing markers”; [0027]; [0032]; FIGS. 3-4), wherein the region adjacency graph is constructed from a plurality of pixel-region adjacency graphs (FIGS. 2-4; [0004], “partition an image into disjoint regions”; [0011]; [0030], “plural pixel regions … constructs the adjacency graph where the plural pixel watersheds are identified as nodes and where contiguous nodes are interconnected with weighted edges … between adjacent watersheds (i.e., plural containing pixel nodes)”);
Chefd'hotel does not disclose the plurality of pixel-region adjacency graphs respectively corresponding to a plurality of tiles of the image. However, it is known that the pixels are tiles of an image. Each tile is a one pixel region.
In the same field of endeavor, Meyer teaches an image segmentation method using watershed hierarchies (Meyer: Abstract; FIGS. 1-13). Meyer further teaches the plurality of pixel-region adjacency graphs respectively corresponding to a plurality of tiles of the image (Meyer: Page 1, 1st Col., 1st paragraph, “The watershed partition counts numerous tiles, as many tiles as there are regional minima in the gradient images”, Sec. A., “two resolutions. The lowest level is the pixel level … The highest level is the level of regions, of partitions and families of partitions … Partition and dissimilarity between adjacent tiles are then modelled as an edge weighted graph, the region adjacency graph or RAG: each node represents a tile of the partition …”).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Chefd'hotel with the teaching of Meyer by using the watershed hierarchies in order to achieve robust segmentation (Meyer: Sec. I.)
-Regarding claim 9, Chefd'hotel discloses a method, comprising (Abstract; FIGS. 1-6; [0044]): by a device operatively coupled to a processor (one or more processors and memories has to be used in order implement’s Chefd'hotel’s FIG. 2), an image generated by a scientific instrument (FIGS. 1A-1F; 5; FIG. 2, step 200; [0003], “CT or MRI”); and performing, by the device, marker-based watershed segmentation on a region adjacency graph of the image (FIG. 2, steps 202-212; [0004], “watershed transform … partition an image into disjoint regions … watershed segmentation algorithm …”; [0008], “constraining the segmentation process with markers”; [0010], “marker-based geodesic partitioning algorithm”; [0013]; [0022], “compute watersheds … set regions containing markers”; [0027]; [0032]; FIGS. 3-4), wherein the region adjacency graph is constructed from a plurality of pixel-region adjacency graphs (FIGS. 2-4; [0004], “partition an image into disjoint regions”; [0011]; [0030], “plural pixel regions … constructs the adjacency graph where the plural pixel watersheds are identified as nodes and where contiguous nodes are interconnected with weighted edges … between adjacent watersheds (i.e., plural containing pixel nodes)”);
Chefd'hotel does not disclose the plurality of pixel-region adjacency graphs respectively corresponding to a plurality of tiles of the image. However, it is known that the pixels are tiles of an image. Each tile is a one pixel region.
In the same field of endeavor, Meyer teaches an image segmentation method using watershed hierarchies (Meyer: Abstract; FIGS. 1-13). Meyer further teaches the plurality of pixel-region adjacency graphs respectively corresponding to a plurality of tiles of the image (Meyer: Page 1, 1st Col., 1st paragraph, “The watershed partition counts numerous tiles, as many tiles as there are regional minima in the gradient images”, Sec. A., “two resolutions. The lowest level is the pixel level … The highest level is the level of regions, of partitions and families of partitions … Partition and dissimilarity between adjacent tiles are then modelled as an edge weighted graph, the region adjacency graph or RAG: each node represents a tile of the partition …”).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Chefd'hotel with the teaching of Meyer by using the watershed hierarchies in order to achieve robust segmentation (Meyer: Sec. I.).
-Regarding claim 17, Chefd'hotel discloses a computer program product for facilitating tiled region adjacency graph computation via pixel-region adjacency graphs (Abstract; FIGS. 1-6; [0044]), the computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to (one or more processors, memories and computer program or instructions has to be used in order implement’s Chefd'hotel’s FIG. 2): access an image captured by a charged-particle microscope (FIGS. 1A-1F; 5; FIG. 2, step 200; [0003], “CT or MRI”); and construct a region adjacency graph for the image, based on a plurality of pixel-region adjacency graphs (FIGS. 2-4; [0004], “partition an image into disjoint regions”; [0011]; [0030], “plural pixel regions … constructs the adjacency graph where the plural pixel watersheds are identified as nodes and where contiguous nodes are interconnected with weighted edges … between adjacent watersheds (i.e., plural containing pixel nodes)”);
Chefd'hotel does not disclose constructing the region adjacency graphs in tile-wise fashion. However, it is known that the pixels are tiles of an image. Each tile is a one pixel region.
In the same field of endeavor, Meyer teaches an image segmentation method using watershed hierarchies (Meyer: Abstract; FIGS. 1-13). Meyer further teaches the plurality of pixel-region adjacency graphs respectively corresponding to a plurality of tiles of the image (Meyer: Page 1, 1st Col., 1st paragraph, “The watershed partition counts numerous tiles, as many tiles as there are regional minima in the gradient images”, Sec. A., “two resolutions. The lowest level is the pixel level … The highest level is the level of regions, of partitions and families of partitions … Partition and dissimilarity between adjacent tiles are then modelled as an edge weighted graph, the region adjacency graph or RAG: each node represents a tile of the partition …”).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Chefd'hotel with the teaching of Meyer by using the watershed hierarchies in order to achieve robust segmentation (Meyer: Sec. I.)
-Regarding claims 2 and 10, Chefd'hotel in view of Meyer teaches the system of claim 1 and the method of claim 9.
Chefd'hotel does not disclose decomposing the image into the plurality of tiles. However, it is known that the pixels are tiles of an image. Each tile is a one pixel region.
In the same field of endeavor, Meyer teaches an image segmentation method using watershed hierarchies (Meyer: Abstract; FIGS. 1-13). Meyer further teaches decomposing the image into the plurality of tiles (Meyer: Page 1, 1st Col., 1st paragraph, “The watershed partition counts numerous tiles, as many tiles as there are regional minima in the gradient images”, Sec. A., “two resolutions. The lowest level is the pixel level … The highest level is the level of regions, of partitions and families of partitions … Partition and dissimilarity between adjacent tiles are then modelled as an edge weighted graph, the region adjacency graph or RAG: each node represents a tile of the partition …”; FIG. 11).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Chefd'hotel with the teaching of Meyer by using the watershed hierarchies in order to achieve robust segmentation (Meyer: Sec. I.).
-Regarding claims 3 and 11, Chefd'hotel in view of Meyer teaches the system of claim 2 and the method of claim 10.
Chefd'hotel does not disclose a plurality of pixel adjacency graphs based on the plurality of tiles, wherein, for a first pixel adjacency graph that corresponds to a first tile, nodes of the first pixel adjacency graph represent respective pixels or voxels of the first tile. However, it is known that the pixels are tiles of an image. Each tile is a one pixel region.
In the same field of endeavor, Meyer teaches an image segmentation method using watershed hierarchies (Meyer: Abstract; FIGS. 1-13). Meyer further teaches a plurality of pixel adjacency graphs based on the plurality of tiles, wherein, for a first pixel adjacency graph that corresponds to a first tile, nodes of the first pixel adjacency graph represent respective pixels or voxels of the first tile (Meyer: Page 1, 1st Col., 1st paragraph, “The watershed partition counts numerous tiles, as many tiles as there are regional minima in the gradient images”, Sec. A., “two resolutions. The lowest level is the pixel level … The highest level is the level of regions, of partitions and families of partitions … Partition and dissimilarity between adjacent tiles are then modelled as an edge weighted graph, the region adjacency graph or RAG: each node represents a tile of the partition …”; FIG. 2).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Chefd'hotel with the teaching of Meyer by using the watershed hierarchies in order to achieve robust segmentation (Meyer: Sec. I.)
-Regarding claims 4 and 12, Chefd'hotel in view of Meyer teaches the system of claim 3 and the method of claim 11.
Chefd'hotel further discloses generating a plurality of minimum spanning forests based on the plurality of pixel adjacency graphs ([0040], [0042], “The pre-assigned nodes form the roots of spanning trees obtained by adding one edge at a time, always taking the next edge that gives the shortest path from the root nodes to an unmarked node …. the fringe of their growing spanning trees can be seen as competing wavefronts propagating throughout the graph and colliding to form a graph partition”; Note: A forest is a collection of all trees).
Chefd'hotel does not disclose wherein, for a first minimum spanning forest that corresponds to the first pixel adjacency graph, the first minimum spanning forest comprises one or more border trees and one or more interior trees.
In the same field of endeavor, Meyer teaches an image segmentation method using watershed hierarchies (Meyer: Abstract; FIGS. 1-13). Meyer further wherein, for a first minimum spanning forest that corresponds to the first pixel adjacency graph, the first minimum spanning forest comprises one or more border trees and one or more interior trees (Meyer: Page 2, 1st Col., Sec. C.2., “The Minimum Spanning Tree”, Sec. 4; FIG. 2; Note: this is known for Minimum Spanning Forest and Region Adjacency Graph. See also Meyer (Chapter 8 Marker-based Segmentation, in Topographical Tools for Filtering and Segmentation 2 Flooding and Marker-based Segmentation on Node- or Edge-weighted Graphs, Wiley-ISTE 2019): Sec. 8.1.2.).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Chefd'hotel with the teaching of Meyer by using the watershed hierarchies in order to achieve robust segmentation (Meyer: Sec. I.)
-Regarding claim 16, Chefd'hotel in view of Meyer teaches the method of claim 9. Chefd'hotel further discloses wherein the image is an electron tomography image, an X-ray tomography image, or a confocal microscopy image (Chefd'hotel: [0003], “CT or MRI”; FIG. 1A).
Claim(s) 5 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chefd'hotel et al (US 20080247646 A1), hereinafter Chefd'hotel in view of Meyer (2015 ICAPR), and further in view of Manoochehri et al, (2017 International Conference on HPCS, pp. 643-650), hereinafter Manoochehri.
-Regarding claims 5 and 13, Chefd'hotel in view of Meyer teaches the system of claim 4 and the method of claim 12.
Chefd'hotel in view of Meyer does not teach generating the plurality of minimum spanning forests via executing Boruvka’s algorithm.
However, Manoochehri is an analogous art pertinent to the problem to be solved in this application and teaches a method for implementation of minimum spanning forest algorithm (Manoochehri: Abstract; FIGS. 1-5; Algorithms 1-4). Manoochehri further teaches generating the plurality of minimum spanning forests via executing Boruvka’s algorithm (Manoochehri: Abstract; Page 643, 2nd Col., 2nd paragraph; Page 644, 1st Col., 2nd and 4th paragraphs; Page 645, Sec. III.; Algorithms 1-4; ).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify the teaching of Chefd'hotel in view of Meyer with the teaching of Manoochehri by generating the plurality of minimum spanning forests via executing Boruvka’s algorithm in order to maximize resource utilization and load balance.
Claim(s) 6-8, 14-15 and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chefd'hotel et al (US 20080247646 A1), hereinafter Chefd'hotel in view of Meyer (2015 ICAPR), and further in view of Moga et al (Proceedings of 3rd IEEE International Conference on Image Processing, vol. 2, pp. 137-140, 1996), hereinafter Moga.
-Regarding claims 6 and 14, Chefd'hotel discloses the system of claim 4 and the method of claim 12.
Chefd'hotel in view of Meyer does not teach one or more interior trees are condensed.
However, Moga is an analogous art pertinent to the problem to be solved in this application and teaches an image segmentation method using a parallel marker based watershed transformation (Moga: Abstract; Page 137, Sec. 2.; FIGS. 1-3). Moga further teaches condensing one or more interior trees (Moga: Page 138, 2nd Col., 2nd paragraph, “The neighborhood graph is further condensed”; Page 138, 1st Col., last paragraph; Page 137, 2nd Col., 1st paragraph).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify the teaching of Chefd'hotel in view of Meyer with the teaching of Moga by condensing one or more interior trees in order to reduce over segmentation and enhance computation efficiency.
-Regarding claims 7 and 15, Chefd'hotel in view Meyer, and further in view of Moga teaches the system of claim 6 and the method of claim 14.
Chefd'hotel does not disclose merging plurality of pixel-region adjacency graphs into the region adjacency graph, by coupling border regions of adjacent tiles, reflagging such border regions as new interior regions, and condensing such new interior regions into new region-wise nodes.
In the same field of endeavor, Meyer teaches an image segmentation method using watershed hierarchies (Meyer: Abstract; FIGS. 1-13). Meyer further teaches disclose merging plurality of pixel-region adjacency graphs into the region adjacency graph, by coupling border regions of adjacent tiles, reflagging such border regions as new interior regions (Meyer: Abstract, “partition is obtained by merging adjacent regions in a finer partition … measured by the level of the hierarchy for which its two adjacent regions merge”; Page 6, Sec. B. 1)., “A number of tree has merged, creating a forest with less trees, inducing the partition of level 3 of the hierarchy. The same process may go on, creating at each stage a new level of the hierarchy”; See also Moga: Page 138, 2nd Col., 1st -3rd paragraphs, last paragraph).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Chefd'hotel with the teaching of Meyer by using the watershed hierarchies in order to achieve robust segmentation (Meyer: Sec. I.)
Chefd'hotel in view of Meyer does not teach one or more interior trees are condensed.
However, Moga is an analogous art pertinent to the problem to be solved in this application and teaches an image segmentation method using a parallel marker based watershed transformation (Moga: Abstract; Page 137, Sec. 2.; FIGS. 1-3). Moga further teaches condensing one or more interior trees (Moga: Page 138, 2nd Col., 2nd paragraph, “The neighborhood graph is further condensed”; Page 138, 1st Col., last paragraph; Page 137, 2nd Col., 1st paragraph).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify the teaching of Chefd'hotel in view of Meyer with the teaching of Moga by condensing one or more interior trees in order to reduce over segmentation and enhance computation efficiency.
-Regarding claim 8, Chefd'hotel in view of Meyer teaches the system of claim 1.
Chefd'hotel in view of Meyer does not teach computing an amount of memory consumption involved in creation of the region adjacency graph.
However, Moga is an analogous art pertinent to the problem to be solved in this application and teaches an image segmentation method using a parallel marker based watershed transformation (Moga: Abstract; Page 137, Sec. 2.; FIGS. 1-3). Moga further teaches performing a
l
o
g
n
N
distributed message passing algorithm for computing minimum spanning forest on N processors (Moga: Abstract; Page 137, Sec. 2.) and condensing one or more interior trees (Moga: Page 138, 2nd Col., 2nd paragraph, “The neighborhood graph is further condensed”; Page 138, 1st Col., last paragraph; Page 137, 2nd Col., 1st paragraph).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify the teaching of Chefd'hotel in view of Meyer with the teaching of Moga by merging plurality of pixel-region adjacency graphs and condensing one or more interior trees in order to reduce over segmentation and enhance computation efficiency.
-Regarding claim 18, Chefd'hotel in view of Meyer teaches the computer program product of claim 17.
Chefd'hotel does not disclose decomposing the image into a plurality of tiles generating a plurality of pixel adjacency graphs based on the plurality of tiles, wherein, for a first pixel adjacency graph that corresponds to a first tile, nodes of the first pixel adjacency graph represent respective pixels or voxels of the first tile; Chefd'hotel does not disclose wherein, for a first minimum spanning forest that corresponds to the first pixel adjacency graph, the first minimum spanning forest comprises one or more border trees and one or more interior trees. Chefd'hotel does not disclose merging plurality of pixel-region adjacency graphs into the region adjacency graph, by coupling border regions of adjacent tiles, reflagging such border regions as new interior regions, and condensing such new interior regions into new region-wise nodes.
In the same field of endeavor, Meyer teaches an image segmentation method using watershed hierarchies (Meyer: Abstract; FIGS. 1-13). Meyer further teaches decomposing the image into the plurality of tiles and teaches a plurality of pixel adjacency graphs based on the plurality of tiles, wherein, for a first pixel adjacency graph that corresponds to a first tile, nodes of the first pixel adjacency graph represent respective pixels or voxels of the first tile (Meyer: Page 1, 1st Col., 1st paragraph, “The watershed partition counts numerous tiles, as many tiles as there are regional minima in the gradient images”, Sec. A., “two resolutions. The lowest level is the pixel level … The highest level is the level of regions, of partitions and families of partitions … Partition and dissimilarity between adjacent tiles are then modelled as an edge weighted graph, the region adjacency graph or RAG: each node represents a tile of the partition …”; FIGS. 11, 2). Meyer further teaches wherein, for a first minimum spanning forest that corresponds to the first pixel adjacency graph, the first minimum spanning forest comprises one or more border trees and one or more interior trees (Meyer: Page 2, 1st Col., Sec. C.2., “The Minimum Spanning Tree”, Sec. 4; FIG. 2). Meyer further teaches disclose merging plurality of pixel-region adjacency graphs into the region adjacency graph, by coupling border regions of adjacent tiles, reflagging such border regions as new interior regions (Meyer: Abstract, “partition is obtained by merging adjacent regions in a finer partition … measured by the level of the hierarchy for which its two adjacent regions merge”; Page 6, Sec. B. 1)., “A number of tree has merged, creating a forest with less trees, inducing the partition of level 3 of the hierarchy. The same process may go on, creating at each stage a new level of the hierarchy”; See also Moga: Page 138, 2nd Col., 1st -3rd paragraphs, last paragraph).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Chefd'hotel with the teaching of Meyer by using the watershed hierarchies in order to achieve robust segmentation (Meyer: Sec. I.).
Chefd'hotel in view of Meyer does not teach one or more interior trees are condensed.
However, Moga is an analogous art pertinent to the problem to be solved in this application and teaches an image segmentation method using a parallel marker based watershed transformation (Moga: Abstract; Page 137, Sec. 2.; FIGS. 1-3). Moga further teaches condensing one or more interior trees (Moga: Page 138, 2nd Col., 2nd paragraph, “The neighborhood graph is further condensed”; Page 138, 1st Col., last paragraph; Page 137, 2nd Col., 1st paragraph).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify the teaching of Chefd'hotel in view of Meyer with the teaching of Moga by condensing one or more interior trees in order to reduce over segmentation and enhance computation efficiency.
-Regarding claim 19, of Chefd'hotel in view of Meyer, and further in view of Moga teaches the computer program product of claim 18. A person of ordinary skills in the art would understand that one or more processors, memories and program instructions has to be used to execute program instructions in order to implement image segmentation based on watershed adjacency graphs as shown in Chefd'hotel’s FIG. 2.
-Regarding claim 20, of Chefd'hotel in view of Meyer, and further in view of Moga teaches the computer program product of claim 19. A person of ordinary skills in the art would understand that one or more processors has to be used in order to implement image segmentation based on watershed adjacency graphs as shown in Chefd'hotel’s FIG. 2.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XIAO LIU whose telephone number is (571)272-4539. The examiner can normally be reached Monday-Thursday and Alternate Fridays 8:30-4:30.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jennifer Mehmood can be reached at (571) 272-2976. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/XIAO LIU/Primary Examiner, Art Unit 2664