DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . It is responsive to the submission dated 02/18/2026. Claims 1-12 and 14-20 are presented for examination, of which, claims 1, 10 and 16 are independent claims.
Response to Arguments
2. Applicant’s arguments, see pages 7-12 of Applicant’s Remarks, filed 02/18/2026, with respect to the indefiniteness rejections under 35 USC 112(b) and the anticipation rejections under 35 USC 102(a1) of the claims have been fully considered and are persuasive. The amendments to the claims are sufficient to overcome the informalities of the previous claims. As such, the rejections to these claims have been withdrawn.
Claim Rejections - 35 USC § 102
3. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
4. Claims 1-8, and 16-20 are rejected under 35 U.S.C. 102(a2) as being anticipated by Batra et al. (US 20240420389).
Considering claim 1, Batra discloses a method comprising: obtaining a pattern prompt and a text image, wherein the pattern prompt describes a visual pattern and the text image depicts text (e.g., Batra discloses obtaining a text prompt encompasses a text image to generate tile-able patterns. See paras. 2 and 3. Wherein the obtaining data including a plurality of images depicting tile-able patterns and a plurality of text descriptions corresponding to the plurality of images. See para. 5. Paras. 25-26 of Batra also teaches a tile-able pattern is included in the text prompt);
generating, using an image generation model comprising a machine learning model implemented by a computing device, a pattern image based on the pattern prompt, wherein the pattern image depicts the visual pattern (Batra discloses: a pattern generation system encodes the text prompt to generate a prompt embedding using a generation model that is trained to generate a latent vector from the prompt embedding to generate vector representations of tile-able images. See para. 4. Batra also teaches the obtained data to be trained includes a plurality of images depicting tile-able patterns and a plurality of text descriptions corresponding to the plurality of images. See para. 5. Paras. 25-26 of Batra also teaches a tile-able pattern is included in the text prompt and that a specific pattern can be created from an input image); and
generating, using the image generation model, a patterned text image based on the pattern image and the pattern prompt, wherein the patterned text image depicts a text character (e.g., text embedding from latent vector) from the text of the text image, and wherein the text character has the visual pattern from the patterned image (for examples, Batra discloses generating, using an image generation model, an output image based on the latent vector, wherein the output image comprises a tile-able pattern including an element from the text prompt. See paras. 4. Paras. 25-26 of Batra also teaches a tile-able pattern is included in the text prompt and that a specific pattern can be created from an input image. Paras. 30-32 and 48 of Batra also teaches the tile-able pattern is generated using the latent vector as guidance for text embedding prompt).
As such, it is submitted that the Batra reference reads on all the elements of claim 1 including the generation of a patterned text image that depicts a text character with visual pattern from the text image included in the text prompt.
As per claims 2-3, Batra discloses generating, using an image generation model, an output image based on the latent vector, wherein the output image comprises a tile-able pattern including an element from the text prompt. See paras. 4. Paras. 25-26 of Batra also teaches a tile-able pattern is included in the text prompt and that a specific pattern can be created from an input image, wherein the generation is conditioned on the latent vector, the prompt embedding, and a noise vector. See Paras. 30-32 and 48. Batra also teaches to generate the patterned image from the prompt, during training, the image generation model includes providing images of vector graphic-style patterns as a positive class and providing images that include other content such as non-repeatable images as a negative class. See para. 52.
As such, it is submitted that the Batra reference teaches all the features of claims 2 and 3, including generating the pattern image by generating a positive conditioning embedding based on the pattern prompt; and generating a negative conditioning embedding based on a negative prompt, wherein the image generation model generates the pattern image and the patterned text image based on the positive conditioning embedding and the negative conditioning embedding, as claimed. See also paras. 104-105 of Batra.
As per claim 4, Batra discloses generating the patterned text image comprises: combining the pattern image and the text image to obtain a preliminary patterned text image (e.g., text embedding or latent vector) wherein the patterned text image is generated based on the preliminary patterned text image (e.g., Batra discloses , Batra discloses generating, using an image generation model, an output image based on the latent vector, wherein the output image comprises a tile-able pattern including an element from the text prompt. See paras. 4. Paras. 25-26 of Batra also teaches a tile-able pattern is included in the text prompt and that a specific pattern can be created from an input image. Paras. 30-32 and 48 of Batra also teaches the tile-able pattern is generated using the latent vector as guidance for text embedding prompt, wherein the generation is conditioned on the latent vector, the prompt embedding, and a noise vector. See also para. 57).
As per claim 5, Considering that in Bara it is provided that the patterned image generated from the text prompt is based on seamlessly tile-able patterns that are repeatable in vertical and horizontal directions to allow the output image to fill and fit all areas (see paras. 3, 25-26), wherein the repeatable seamlessly pattern include four images in a 2x2 arrangement (see paras. 57-60), wherein a Circular convolution is applied across the entirety of the image at both the left and right boundaries as well as the top and bottom boundaries (see paras. 65-66); the Batra reference, therefore, encompasses the performance of arranging a plurality of characters of the text to minimize a background region of the text image, as claimed.
As per claim 6, Batra discloses generating a vector patterned text image based on the patterned text image. See paras. 30-32 and 46-48.
As per claim 7, Batra discloses upscaling the patterned text image to obtain an upscaled patterned text image, wherein the vector patterned text image is generated based on the upscaled patterned text image (e.g., Batra teaches: generate pattern image based on seamlessly tile-able patterns repeatable in all directions to allow the output image to fill and fit all areas (see paras. 3, 25-26) and apply a Circular convolution across the entirety of the image at both the left and right boundaries as well as the top and bottom boundaries (see paras. 65-66), wherein the repeatable process is performed by up-sampling the encoded latent vectors using an up-sampling process to obtain up-sampled features. See paras. 70-71).
As per claim 8, Batra discloses segmenting the patterned text image to obtain a plurality of patterned character images, wherein the vector patterned text image is generated based on the plurality of patterned character images (e.g., training a classifier to generate images composed of a plurality of vector graphic-style patterns, see paras. 51-52, wherein the tiling and classifying of image patterns encompass the image segmentation process).
The subject-matters of claim 16 corresponds in terms of an apparatus to that of independent method claim 1. The features of claim 16 are substantially the same as those of claim 1 except the invention category. Accordingly, the same reasonings applied for the rejections of claim 1 also apply to claim 16.
As per claim 17, Batra discloses the image generation model comprises a first image generation model configured to generate the pattern image, and a second image generation model configured to generate the patterned text image. See paras. 2-3, 24-27, 30-34 and 44-46.
As per claim 18, Batra discloses a prior model trained to generate a conditioning embedding for the image generation model. See Paras. 30-32 and 48.
As per claim 19, Batra discloses an upsampling model trained to upscale the patterned text image to obtain an upscaled patterned text image. See paras. 70-74 in view of para. 24.
Claim 20 has substantially the same technical features as those of claim 6, and is therefore, rejected under the same rationale as claim 6.
Claim Rejections - 35 USC § 103
5. 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.
6. Claims 9-12 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Batra in view of Zeng et al. (US 20220169623).
As per claim 9, Batra fails to teach the image generation model is trained to generate text effects using a training set that includes a ground-truth pattern image and a pattern prompt, which is discloses by Zeng. See paras. 84-85 of Zeng.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Batra to include training an image generation model to generate text effects using a training set that includes a ground-truth pattern image and a pattern prompt as taught by Zeng; in order to predict and compare layout information indicating a location of an element of the text prompt in the training image dataset, so as to eliminate noise from the generated image pattern. See para. 85 of Zeng.
As per claim 10, Batra discloses obtaining a training set that includes a pattern prompt and a pattern image, wherein the pattern prompt describes a visual pattern and the text image depicts text (e.g., Batra discloses obtaining a text prompt encompasses a text image to generate tile-able patterns using a generation model. See paras. 2 and 3. Wherein the obtaining data including a plurality of images depicting tile-able patterns and a plurality of text descriptions corresponding to the plurality of images. See para. 5. Paras. 25-26 of Batra also teaches a tile-able pattern is included in the text prompt. Batra also teaches the obtained data to be trained includes a plurality of images depicting tile-able patterns and a plurality of text descriptions corresponding to the plurality of images. See para. 5. Paras. 25-26 of Batra also teaches a tile-able pattern is included in the text prompt and that a specific pattern can be created from an input image
training, using the training set, an image generation model to generate patterned text images, wherein training the image generation model comprises computing a diffusion loss (e.g., Batra discloses the obtained text prompt and text image is trained to generate tile-able patterns using a generation model that includes a diffusion model that performs a reverse diffusion process that gradually removes noise from an initial pure noise image to generate an image; and a text encoder configured to encode a text prompt to obtain a text embedding that is trained to generate latent vectors corresponding to graphics patterns to generate a tile-able image patterns from the text prompt. See paras. 25-30 and 32-34); and updating parameters of the image generation model based on the diffusion loss (e.g., Batra discloses the image generation model comprises a training component configured to compute loss functions and to update model parameters of the other components in pattern generation apparatus, wherein the training component 230 computes a loss function for a generation prior model 220 based on a training set. See paras. 51-52, 97 and 109-112).
Batra fails to teach the training dataset to include a ground-truth pattern image and a pattern prompt, which is discloses by Zeng. See paras. 84-85 of Zeng.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Batra to include training an image generation model to generate text effects using a training set that includes a ground-truth pattern image and a pattern prompt as taught by Zeng; in order to predict and compare layout information indicating a location of an element of the text prompt in the training image dataset, so as to eliminate noise from the generated image pattern. See para. 85 of Zeng.
As per claim 11, Monica discloses filtering a set of images to remove images depicting text, wherein the training set excludes the removed images (e.g., filtering the final design document to remove generated texts that interfer with the image content from the final document. See par. 58. Monica further teaches an image style encoder 905 are trained to disentangle stylistic features from content features, thereby generating a vector representation of the images that focuses on style (see para. 85); and performing principal component analysis (PCA) to remove the text features from text encoder 910 to yield text features of reduced dimensions. See para. 88). See also paras. 50-53.
As per claim 12, Batra discloses generating an aesthetic score (e.g., similarity or matching aesthetic patterns) for each of a set of images; and filtering the set of images to remove images if the aesthetic score is below a threshold, wherein the training set excludes the removed images. See paras. 49-53, 55-56 and 104-111.
As per claim 14, Batra discloses generating, using a text encoder, a text encoding based on the pattern prompt; and generating, using a prior model, a first embedding (e.g., vector representation or latent vector) based on the text encoding (see paras. 2-3, 24-27, 30-34 and 44-46);
generating, using an image encoder, a second embedding (e.g., positional embedding) based on the [ground-truth] pattern image; and training the prior model based on the first embedding and the second embedding. See paras. 44-46.
Batra fails to teach the training dataset to include a ground-truth pattern image and a pattern prompt, which is discloses by Zeng. See paras. 84-85 of Zeng. See the rejections of claim 10 above for reason of obviousness to combine the references.
As per claim 15, Batra discloses training an upsampling model using a generative adversarial loss. See paras. 70-74 in view of para. 24.
Claim Rejections - 35 USC § 112
7. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
8. Claims 10-15 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
In claim 10, the limitations reciting " training, using the training set, an image generation model to generate patterned text images " renders the claimed limitations indefinite, because it is not clear how the training set is used to train the image generation model.
According to paragraphs 26-34 of the original disclosure, it is assumed that the intention is to input image dataset to a machine learning model of a computing device to train the model to generate text effects. However, the original disclosure lacks the specific details for using a training set to train the image generation model..
The claims not specifically cited in this rejection are rejected as being dependent upon their rejected base claims.
Conclusion
9. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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.
10. Any inquiry concerning this communication or earlier communications from the examiner should be directed to WESNER SAJOUS whose telephone number is (571) 272-7791. The examiner can normally be reached on M-F 10:00 TO 7:30 (ET).
Examiner interviews are available via telephone 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 or email the Examiner directly at wesner.sajous@uspto.gov.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Said Broome can be reached on 571-272-2931. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. 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. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/WESNER SAJOUS/Primary Examiner, Art Unit 2612
WS
05/02/2026
Prosecution Insights