Patents by Inventor Omer Moshe Moussaffi
Omer Moshe Moussaffi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240037623Abstract: A photo design smart assistant system for reducing similar photos for display and product design includes a similarity distance computation module that can calculate hash values of images and to calculate similarity distances between the images using at least the hash values, a burst grouping module that can automatically group the images into a burst based at least in part on the similarity distances of the images, wherein at least one image is automatically selected from the burst of images, an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst, and a printing and finishing facility that can automatically make a physical photo product based on the photo product design.Type: ApplicationFiled: August 9, 2023Publication date: February 1, 2024Applicant: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Patent number: 11763369Abstract: A photo design smart assistant system for reducing similar photos for display and product design includes a similarity distance computation module that can calculate hash values of images and to calculate similarity distances between the images using at least the hash values, a burst grouping module that can automatically group the images into a burst based at least in part on the similarity distances of the images, wherein at least one image is automatically selected from the burst of images, an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst, and a printing and finishing facility that can automatically make a physical photo product based on the photo product design.Type: GrantFiled: August 10, 2022Date of Patent: September 19, 2023Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Publication number: 20230079740Abstract: A photo design smart assistant system for reducing similar photos for display and product design includes a similarity distance computation module that can calculate hash values of images and to calculate similarity distances between the images using at least the hash values, a burst grouping module that can automatically group the images into a burst based at least in part on the similarity distances of the images, wherein at least one image is automatically selected from the burst of images, an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst, and a printing and finishing facility that can automatically make a physical photo product based on the photo product design.Type: ApplicationFiled: August 10, 2022Publication date: March 16, 2023Applicant: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Patent number: 11443469Abstract: A photo design smart assistant system for reducing similar photos for display and product design includes a similarity distance computation module that can calculate hash values of images and to calculate similarity distances between the images using at least the hash values, a burst grouping module that can automatically group the images into a burst based at least in part on the similarity distances of the images, wherein at least one image is automatically selected from the burst of images, an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst, and a printing and finishing facility that can automatically make a physical photo product based on the photo product design.Type: GrantFiled: August 14, 2020Date of Patent: September 13, 2022Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Patent number: 11308360Abstract: A computer system selects a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, copies the feature matrix T to produce a feature matrix T_best, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the SVM model on the feature matrix T_best. The first SVM model can be used classify the faces or the objects in the images. An image-product design can be created based on the faces or the objects in the images classified by the first SVM model using the feature matrix T_best.Type: GrantFiled: May 13, 2020Date of Patent: April 19, 2022Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Patent number: 10956713Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the first SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, automatically removing feature vectors corresponding to the FP data set from the feature matrix T by the computer processor to produce a feature matrix T_best, retraining the first SVM model on the feature matrix T_best to produce a second SVM model, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the second SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the second SVM model on the feature matrix T_best.Type: GrantFiled: January 21, 2020Date of Patent: March 23, 2021Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Patent number: 10891522Abstract: A computer-implemented method is disclosed for image recognition and other applications. The method employs an SVM model and can reduce false negatives and increase recognition accuracies by raising the sample-to-support-vector ratio.Type: GrantFiled: April 1, 2020Date of Patent: January 12, 2021Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Publication number: 20200380748Abstract: A photo design smart assistant system for reducing similar photos for display and product design includes a similarity distance computation module that can calculate hash values of images and to calculate similarity distances between the images using at least the hash values, a burst grouping module that can automatically group the images into a burst based at least in part on the similarity distances of the images, wherein at least one image is automatically selected from the burst of images, an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst, and a printing and finishing facility that can automatically make a physical photo product based on the photo product design.Type: ApplicationFiled: August 14, 2020Publication date: December 3, 2020Inventor: Omer Moshe Moussaffi
-
Patent number: 10803298Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the first SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, automatically removing feature vectors corresponding to the FN data set from the feature matrix T by the computer processor to produce a feature matrix T_best of size (n-size(FN))*m, retraining the first SVM model on the feature matrix T_best to produce a second SVM model, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the second SVM model on T_best. If the ratio is above the threshold, SVM predictions is performed using the second SVM model on the feature matrix T_best.Type: GrantFiled: January 4, 2018Date of Patent: October 13, 2020Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Patent number: 10762126Abstract: A photo design smart assistant system for reducing similar photos for display and product design includes a similarity distance computation module that can calculate hash values of images and to calculate similarity distances between the images using at least the hash values, a burst grouping module that can automatically group the images into a burst based at least in part on the similarity distances of the images, wherein at least one image is automatically selected from the burst of images, an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst, and a printing and finishing facility that can automatically make a physical photo product based on the photo product design.Type: GrantFiled: September 27, 2017Date of Patent: September 1, 2020Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Publication number: 20200272858Abstract: A computer system selects a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, copies the feature matrix T to produce a feature matrix T_best, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the SVM model on the feature matrix T_best. The first SVM model can be used classify the faces or the objects in the images. An image-product design can be created based on the faces or the objects in the images classified by the first SVM model using the feature matrix T_best.Type: ApplicationFiled: May 13, 2020Publication date: August 27, 2020Inventor: Omer Moshe Moussaffi
-
Publication number: 20200226428Abstract: A computer-implemented method is disclosed for image recognition and other applications. The method employs an SVM model and can reduce false negatives and increase recognition accuracies by raising the sample-to-support-vector ratio.Type: ApplicationFiled: April 1, 2020Publication date: July 16, 2020Inventor: Omer Moshe Moussaffi
-
Patent number: 10664724Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, copying the feature matrix T to produce a feature matrix T_best, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the SVM model on the feature matrix T_best. The first SVM model can be used classify the faces or the objects in the images. An image-product design can be created based on the faces or the objects in the images classified by the first SVM model using the feature matrix T_best.Type: GrantFiled: July 17, 2018Date of Patent: May 26, 2020Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Publication number: 20200160035Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the first SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, automatically removing feature vectors corresponding to the FP data set from the feature matrix T by the computer processor to produce a feature matrix T_best, retraining the first SVM model on the feature matrix T_best to produce a second SVM model, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the second SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the second SVM model on the feature matrix T_best.Type: ApplicationFiled: January 21, 2020Publication date: May 21, 2020Inventor: Omer Moshe Moussaffi
-
Patent number: 10621475Abstract: A computer-implemented method is disclosed for image recognition and other applications. The method employs an SVM model and can reduce false negatives and increase recognition accuracies by raising the sample-to-support-vector ratio.Type: GrantFiled: December 11, 2018Date of Patent: April 14, 2020Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Patent number: 10558847Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the first SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, automatically removing feature vectors corresponding to the FP data set from the feature matrix T by the computer processor to produce a feature matrix T_best of size (n-size(FN))*m, retraining the first SVM model on the feature matrix T_best to produce a second SVM model, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the second SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the second SVM model on the feature matrix T_best.Type: GrantFiled: February 6, 2018Date of Patent: February 11, 2020Assignee: Shutterfly, LLCInventor: Omer Moshe Moussaffi
-
Publication number: 20200026964Abstract: A computer-implemented method is disclosed for image recognition and other applications. The method employs an SVM model and can reduce false negatives and increase recognition accuracies by raising the sample-to-support-vector ratio.Type: ApplicationFiled: December 11, 2018Publication date: January 23, 2020Inventor: Omer Moshe Moussaffi
-
Publication number: 20200026961Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, copying the feature matrix T to produce a feature matrix T_best, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the SVM model on the feature matrix T_best. The first SVM model can be used classify the faces or the objects in the images. An image-product design can be created based on the faces or the objects in the images classified by the first SVM model using the feature matrix T_best.Type: ApplicationFiled: July 17, 2018Publication date: January 23, 2020Inventor: Omer Moshe Moussaffi
-
Publication number: 20190244009Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the first SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, automatically removing feature vectors corresponding to the FP data set from the feature matrix T by the computer processor to produce a feature matrix T_best of size (n-size(FN))*m, retraining the first SVM model on the feature matrix T_best to produce a second SVM model, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the second SVM model on T_best. If the ratio is above the threshold, SVM predictions is performed using the second SVM model on the feature matrix T_best.Type: ApplicationFiled: February 6, 2018Publication date: August 8, 2019Inventor: Omer Moshe Moussaffi
-
Publication number: 20190205621Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the first SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, automatically removing feature vectors corresponding to the FN data set from the feature matrix T by the computer processor to produce a feature matrix T_best of size (n-size(FN))*m, retraining the first SVM model on the feature matrix T_best to produce a second SVM model, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the second SVM model on T_best. If the ratio is above the threshold, SVM predictions is performed using the second SVM model on the feature matrix T_best.Type: ApplicationFiled: January 4, 2018Publication date: July 4, 2019Inventor: Omer Moshe Moussaffi