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 .
Response to Amendment
Applicant’s response, filed 24 April 2026, to the last office action has been entered and made of record.
In response to the cancellation of claim 2, it is acknowledged and made of record.
In response to the amendments to the specification and claims, they are acknowledged, supported by the original disclosure, and no new matter is added.
In response to the amendments to the abstract and specification, the amended language has overcome the objections to the specification of the previous Office action, and the respective objections have been withdrawn.
In response to the amendments to the claims, specifically addressing the rejection of claim 3 under 35 U.S.C. § 112(b) / (pre-AIA ), second paragraph, of the previous Office action, the amended language has overcome the respective rejection, and the rejection has been withdrawn.
Amendments to the independent claim 1 have necessitated an updated ground of rejection over the applied prior art. Please see below for the updated interpretations and rejections.
Response to Arguments
Applicant's arguments filed 24 April 2026 have been fully considered but they are not persuasive.
In response to Applicant’s arguments on p. 9-13 of Applicant’s reply, that the combined teachings of De Haan and Tokunaga fail to disclose or suggest the claim features of, “clustering all basic markings of each category to obtain several clusters; … in response that the proportion of the number of basic markings in Cmax to the number of basic markings in the category of Cmax is not less than a first threshold, calculating an average value
X
-
of offset vector of all the basic markings in Cmax; and determining
X
-
as the offset vector of basic markings in the other clusters of the category of Cmax”, the Examiner respectfully disagrees.
Examiner notes the claims are treated with their broadest reasonable interpretations consistent with the specification. See MPEP 2111. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Furthermore, the test for obviousness is what the combined teachings of the references would have suggested to those of ordinary skill in the art. See In re Keller, 642 F.2d 413, 208 USPQ871 (CCPA 1981). Additionally, in considering the disclosure of a reference, it is proper to take into account not only specific teachings of the reference but also the inferences which one skilled in the art would reasonably be expected to draw therefrom. See In re Preda, 401 F.2d 825, 826, 159 USPQ 342, 344 (CCPA 1968). See MPEP 2144.01.
De Haan is relied upon to teach a method for skin detection which segments image sequences, detects trackable interest points, tracks the interest points across consecutive images to determine displacement vectors, and that the interest points are classified using a DBSCAN clustering method into three different types of cluster core points, border points, and noise points (see De Haan [0066], [0070], [0077]-[0078], and [0091]).
Tokunaga is further relied upon to teach the techniques of determining local motion vectors based on matching macroblocks of reference and current images, where the local motion vectors are further clustered into corresponding closest clusters based on obtained distance information between the local motion vector and representative vector of each cluster, where an average value of the respective local motion vectors belonging to a respective cluster is calculated as respective representative vectors, and that a global motion vector is determined based on the cluster with the largest number of elements of the local motion vectors of each cluster and the average values of respective clusters (see Tokunaga [0076]-[0077], [0086]-[0087], [0089], and [0114]).
The combined teachings of De Haan and Tokunaga suggests to one of ordinary skill in the art to further cluster the displacement vectors of the classified tracked points and determine a representative vector of the clusters as the global motion vector according to the average values of respective clusters and the number of elements of the local motion vectors of each cluster, predictably leading to an improved skin detection method which further determines and tracks the local and global motion information.
In regards to the claimed terms of “a second threshold”, “a third threshold”, and “a first threshold” recited in the claim limitations of “determining whether a norm of the offset vector of each basic marking is greater than a second threshold”, “determining whether the number of the basic markings that have moved in each category is greater than a third threshold”, and “the proportion of the number of basic markings in Cmax to the number of basic markings in the category of Cmax is not less than a first threshold”; Examiner notes that the claimed “second threshold” and “third threshold” are not defined or described in the claim or the specification regarding how either the second or third threshold are determined, aside that both thresholds “can be set flexibly” (see specification [0013]-[0014], [0029], [0043]-[0044], and [0055]-[0056]). The claimed “first threshold” is similarly not defined or described in the claim or the specification regarding how a first threshold is determined (see specification [0016], [0030], and [0054]).
Thus, the broadest reasonable interpretation, in light of the specification, for the claimed “second threshold” includes any value for the norm or magnitude of the offset vector, the claimed “third threshold” includes any value for the number of basic markings that have moved, and the claimed “first threshold” includes any proportion value.
In regards to the claim limitation “determining whether a norm of the offset vector of each basic marking is greater than a second threshold, if yes, determining that the basic marking has moved; and if no, determining that the basic marking has not moved”, the combined suggested teachings of De Haan and Tokunaga for determining a displacement vector and local motion vector of tracked interest points (see De Haan [0078] and Tokunaga [0077]) are further noted to implicitly suggest to one of ordinary skill in the art that if a tracked interest point has a displacement vector / local motion vector, then the magnitude of the displacement vector/local motion vector would be greater than a value, e.g. 0, and the tracked interest point is understood to have moved. Thus, the suggested teachings provides for the broadest reasonable interpretation of “determining whether a norm of the offset vector of each basic marking is greater than a second threshold, if yes, determining that the basic marking has moved; and if no, determining that the basic marking has not moved”.
In regards to the claim limitation of “determining whether the number of the basic markings that have moved in each category is greater than a third threshold, if yes, determining that the category has moved; and if no, determining that the category has not moved”, the combined suggested teachings of De Haan and Tokunaga for determining a global motion vector based on the average values of respective clusters and the number of elements of the local motion vectors of each cluster that are used to calculate the average values implicitly suggests to one of ordinary skill in the art that if a cluster with a number of local motion vector elements is greater than a value, e.g. 1, then the corresponding cluster is understood to have moved. Thus, the suggested teachings provides for the broadest reasonable interpretation of “determining whether the number of the basic markings that have moved in each category is greater than a third threshold, if yes, determining that the category has moved; and if no, determining that the category has not moved”.
In regards to the amended claim limitations of “clustering all basic markings of each category to obtain several clusters; recording one cluster comprising the largest number of the basic markings as Cmax; in response that the proportion of the number of basic markings in Cmax to the number of basic markings in the category of Cmax is not less than a first threshold, calculating an average value
X
-
of offset vector of all the basic markings in Cmax; and determining
X
-
as the offset vector of basic markings in the other clusters of the category of Cmax”, the combined suggested teachings of De Haan and Tokunaga for performing a DBSAN clustering method to classify the trackable interest points into cluster core points, border points, and noise points, and further clustering the corresponding displacement vectors / motion vectors of the classified trackable interest points into clusters and determining representative vectors and global motion vector (see De Haan [0091] and Tokunaga [0086]-[0087], [0089], and [0114]) are relied upon to teach the broadest reasonable interpretation of the noted amended claim limitations.
Here, the combined teachings suggests to apply Tokunaga’s technique of clustering local motion vectors into clusters and determining global motion vector based on the representative vectors and cluster with largest number of elements to the trackable interest points of De Haan which have been classified into cluster core points, border points, and noise points categories. That is, the classified trackable interest points are further clustered according to the respective displacement vectors / local motion vectors. Thus, the combined teachings provide for the broadest reasonable interpretation for “clustering all basic markings of each category to obtain several clusters”.
As the global motion vector is determined by outputting the representative vector of the cluster having the largest number of elements, the combined teachings provide for the broadest reasonable interpretation for “recording one cluster comprising the largest number of the basic markings as Cmax”.
Furthermore, the combined suggested teachings of De Haan and Tokunaga for determining a global motion vector based on the cluster having the largest number of elements of the local motion vectors implicitly suggests to one of ordinary skill in the art that the largest cluster would have a number of local motion vector elements greater than a value of the number of the corresponding interest point category, e.g. 1, then the corresponding cluster is understood to have at least a proportion of the corresponding interest point category and representative of the category. As the representative vectors of the clusters are calculated as the average values of respective local motion vectors belonging to the respective clusters, the global motion vector would thus be the average value of corresponding local motion vectors of the cluster with largest number of local motion vectors for corresponding classified trackable interest points. Thus, the suggested teachings provides for the broadest reasonable interpretation of “in response that the proportion of the number of basic markings in Cmax to the number of basic markings in the category of Cmax is not less than a first threshold, calculating an average value
X
-
of offset vector of all the basic markings in Cmax; and determining
X
-
as the offset vector of basic markings in the other clusters of the category of Cmax”.
Therefore, the combined teachings of De Haan and Tokunaga, including implicit teachings suggested to one of ordinary skill in the art, provides for the broadest reasonable interpretation, in light of the specification, for the claim features of, “clustering all basic markings of each category to obtain several clusters; … in response that the proportion of the number of basic markings in Cmax to the number of basic markings in the category of Cmax is not less than a first threshold, calculating an average value
X
-
of offset vector of all the basic markings in Cmax; and determining
X
-
as the offset vector of basic markings in the other clusters of the category of Cmax”.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1 and 3-10 are rejected under 35 U.S.C. 103 as being unpatentable over De Haan (US 2016/0171684) in view of Tokunaga et al. (US 2012/0308144), herein Tokunaga.
Regarding claim 1, De Haan discloses an image-based motion detection method, comprising:
acquiring a reference image of a detecting object (see De Haan [0066], where a sequence of image frames acquired over time are obtained), determining several first detecting points in the reference image, extracting basic markings centered on the first detecting points in the reference image (see De Haan [0070] and [0077], where the image frame is segmented into smaller segments and Harris corner detector is used to detect trackable interest points) and classifying all the basic markings into several categories, wherein each category comprises at least one basic marking (see De Haan [0091], where the points are separated into three different types using a density threshold into cluster core points, border points and noise points);
acquiring a detecting image of the detecting object (see De Haan [0066] and [0078], where a sequence of image frames acquired over time are obtained and remaining images are used to track the detected points in the initial frame),
matching the basic markings in the detecting image with the basic markings in the reference image, obtaining an offset vector of each basic marking between the reference image and the detecting image (see De Haan [0078], where a displacement vector between consecutive images is obtained for finding the trajectory of the tracked points).
De Haan does not explicitly disclose wherein the detecting image and the reference image comprise the same image parameters and the image parameters comprise position, direction, size and resolution;
determining whether a norm of the offset vector of each basic marking is greater than a second threshold, if yes, determining that the basic marking has moved; and if no, determining that the basic marking has not moved;
determining whether the number of the basic markings that have moved in each category is greater than a third threshold, if yes, determining that the category has moved; and if no, determining that the category has not moved;
determining a whole moving state and a part moving state of the detecting object according to a moving state of each category; clustering all basic markings of each category to obtain several clusters; recording one cluster comprising the largest number of the basic markings as Cmax; and in response that the proportion of the number of basic markings in Cmax to the number of basic markings in the category of Cmax is not less than a first threshold, calculating an average value
X
-
of offset vector of all the basic markings in Cmax; and determining
X
-
as the offset vector of basic markings in the other clusters of the category of Cmax.
Tokunaga teaches in a related and pertinent device and method for obtaining the distance between a local motion vector and classifying the local motion vector into a cluster (see Tokunaga Abstract), where a reference image and a current image is received (see Tokunaga [0072]), where the current image and reference image are caused to have the same resolution and each divided into macroblocks, each having m pixels x m pixels (see Tokunaga [0076]-[0077]), where matching blocks are searched by comparing macroblocks of the current image with each macroblock of the reference image and obtains a vector derived from a relation between the block location of the current image and the block location of the reference image as a motion vector of the macroblock of the current image, and local motion vectors per macroblock are obtained (see Tokunaga [0077]), the motion vectors are clustered into a cluster to which the closest vector belongs based on the obtained distance information and an average value is calculated of respective local motion vectors belonging to the clusters (see Tokunaga [0086]-[0087]), and global motion vector is determined based on the average values of respective clusters and the number of elements of the local motion vectors of each cluster that are used to calculate the average values, and a representative vector of the cluster is output as the global motion vector (see Tokunaga [0089]), where the representative vector of the cluster with the largest number of elements is output as the global motion vector (see Tokunaga [0114]).
At the time of filing, one of ordinary skill in the art would have found it obvious to apply the teachings of Tokunaga to the teachings of De Haan, such that the image sequences obtained have the same resolution and size, and that the displacement vectors of the tracked points are further clustered and used to determine a representative vector of the cluster as the global motion vector according to the average values of respective clusters and the cluster with the largest number of elements of the local motion vectors.
This modification is rationalized as an application of a known technique to a known method
ready for improvement to yield predictable results.
In this instance, De Haan disclose a base method for skin detection which segments image sequences, detects trackable interest points, tracks the interest points across consecutive images to determine displacement vectors, and further classifies interest points into three different types.
Tokunaga teaches a known technique of using received reference and current images with the same resolution and size to divide into macroblocks and determining local motion vectors from matching macroblocks, where the local motion vectors are further clustered based on obtained distance information and an average value is calculated of respective local motion vectors belonging to the clusters, and determining global motion vector based on the average values of respective clusters and the number of elements of the local motion vectors of each cluster that are used to calculate the average values.
One of ordinary skill in the art would have recognized that by applying Tokunaga’s technique would allow for the method of De Haan to also use image sequences having the same resolution and size, and that the displacement vectors of the tracked points are further clustered and used to determine a representative vector of the cluster as the global motion vector according to the average values of respective clusters and the number of elements of the local motion vectors of each cluster,
predictably leading to an improved skin detection method which further determines and tracks local and global motion information.
While De Haan and Tokunaga do not explicitly disclose determining whether a norm of the offset vector of each basic marking is greater than a second threshold, if yes, determining that the basic marking has moved; and if no, determining that the basic marking has not moved; determining whether the number of the basic markings that have moved in each category is greater than a third threshold, if yes, determining that the category has moved; and if no, determining that the category has not moved; and in response that the proportion of the number of basic markings in Cmax to the number of basic markings in the category of Cmax is not less than a first threshold; the combined teachings of cited prior art provides implicit teachings to one of ordinary skill in the art to the broadest reasonable interpretation of the noted claim limitations.
Notably, De Haan and Tokunaga’s suggested teachings for determining a displacement vector and local motion vector of tracked interest points implicitly suggests to one of ordinary skill in the art that if a tracked interest point has a displacement vector / local motion vector with a magnitude greater than a value, e.g. 0, then the tracked interest point is understood to have moved.
Similarly, Tokunaga’s suggested teachings for determining a global motion vector based on the average values of respective clusters and the number of elements of the local motion vectors of each cluster that are used to calculate the average values implicitly suggests to one of ordinary skill in the art that if a cluster with a number of local motion vector elements is greater than a value, e.g. 1, then the corresponding cluster is understood to have moved.
Furthermore, De Haan and Tokunaga’s suggested teachings for determining a global motion vector based on the cluster having the largest number of elements of the local motion vectors implicitly suggests to one of ordinary skill in the art that the largest cluster would have a number of local motion vector elements greater than a value of the number of the corresponding interest point category, e.g. 1, then the corresponding cluster is understood to have at least a proportion of the corresponding interest point category and representative of the category. See MPEP 2144.01.
Regarding claim 3, please see the above rejection of claim 1. De Haan and Tokunaga disclose the image-based motion detection method of claim 1, wherein the operation of clustering all basic markings of each category specifically comprises:
classifying two basic markings into a cluster if a norm of a difference between offset vectors of the two basic markings is less than a fifth threshold (see Tokunaga [0086], where a distance between a local motion vector and a representative vector of each of a predetermined of clusters is calculated and the motion vectors are clustered into a cluster to which the closest vector belongs based on the obtained distance; suggesting that motion vectors below an implied distance threshold with a closest cluster are classified into such cluster); and
classifying unclassified basic markings into the cluster if differences between offset vectors of the unclassified basic markings and an average value of offset vectors in the cluster is less than the fifth threshold (see Tokunaga [0086], where a distance between a local motion vector and a representative vector of each of a predetermined of clusters is calculated and the motion vectors are clustered into a cluster to which the closest vector belongs based on the obtained distance; suggesting that motion vectors below an implied distance threshold with a closest cluster are classified into such cluster).
Regarding claim 4, please see the above rejection of claim 1. De Haan and Tokunaga disclose the image-based motion detection method of claim 1, wherein
the basic markings are image fragments, the operation of extracting image fragments specifically comprises: extracting images within a range of a first preset distance centered on the first detecting points to construct the image fragments (see De Haan [0070] and [0077], where the image frame is segmented into smaller segments and Harris corner detector is used to detect trackable interest points and a preset window is used to detect corner points).
Regarding claim 5, please see the above rejection of claim 4. De Haan and Tokunaga disclose the image-based motion detection method of claim 4, wherein
in response that the number of the first detecting points in the reference image is less than a fourth threshold, expanding detecting points (see De Haan [0076], where points suitable for tracking are located in the initial image of the interval and their trajectories are estimated for the entire interval; see De Haan [0091], where a minimal number of points within a range is used to classify tracked points), and the operation of expanding the detecting points comprises:
determining the fourth threshold (see De Haan [0091], where a minimal number of points within a range is used to classify tracked points);
centered on the first detecting points, determining several second detecting points within a range of a second preset distance (see De Haan [0066] and [0078], where a sequence of image frames acquired over time are obtained and remaining images are used to track the detected points in the initial frame, where a displacement vector between consecutive images is obtained for finding the trajectory of the tracked points);
determining an entropy threshold (see De Haan [0077], where a threshold is applied to the corner response measure);
centered on the second detecting points, extracting images in the range of the first preset distance in the reference image (see De Haan [0077], where the Harris corner detector is used to detect trackable interest points and a preset window is used to detect corner points);
saving images whose entropy is greater than the entropy threshold as expanded image fragments (see De Haan [0077], where points with a corner response greater than a certain value can be considered as corner points and suitable for tracking).
Regarding claim 6, please see the above rejection of claim 1. De Haan and Tokunaga disclose the image-based motion detection method of claim 1, wherein
the basic markings are image feature points, and the operation of extracting the image feature points specifically comprises: centered on the first detecting points, identifying the image feature points within a range of a third preset distance in the reference image (see De Haan [0070] and [0077], where the image frame is segmented into smaller segments and Harris corner detector is used to detect trackable interest points and a preset window is used to detect corner points).
Regarding claim 7, please see the above rejection of claim 6. De Haan and Tokunaga disclose the image-based motion detection method of claim 6, wherein the image feature points are Harris corner points (see De Haan [0070] and [0077], where the image frame is segmented into smaller segments and Harris corner detector is used to detect trackable interest points).
Regarding claim 8, please see the above rejection of claim 1. De Haan and Tokunaga disclose the image-based motion detection method of claim 1, wherein a density-based clustering algorithm is adopted to classify satisfied basic markings into a category (see De Haan [0091], where a DBSCAN clustering method is performed to separate the points into three different types using a density threshold into cluster core points, border points and noise points).
Regarding claim 9, please see the above rejection of claim 8. De Haan and Tokunaga disclose the image-based motion detection method of claim 8, wherein the clustering algorithm is density-based spatial clustering of applications with noise (DBSCAN) (see De Haan [0091], where a DBSCAN clustering method is performed to separate the points into three different types using a density threshold into cluster core points, border points and noise points).
Regarding claim 10, please see the above rejection of claim 1. De Haan and Tokunaga disclose the image-based motion detection method of claim 1, further comprising:
dividing the reference image to obtain different image dividing units and classifying the basic markings in a same image dividing unit into a same category (see De Haan [0070] and [0077], where the image frame is segmented into smaller segments and Harris corner detector is used to detect trackable interest points; see De Haan [0091], where a DBSCAN clustering method is performed to separate the points into three different types using a density threshold into cluster core points, border points and noise points; where points in the same segments with similar density conditions would be classified as a similar type).
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TIMOTHY WING HO CHOI whose telephone number is (571)270-3814. The examiner can normally be reached 9:00 AM to 5:00 PM.
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, VINCENT RUDOLPH can be reached at (571) 272-8243. 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.
/TIMOTHY CHOI/Examiner, Art Unit 2671
/VINCENT RUDOLPH/Supervisory Patent Examiner, Art Unit 2671
Prosecution Insights