{"search_session":{},"preferences":{"l":"en","queryLanguage":"en"},"patentId":"035-382-254-757-182","frontPageModel":{"patentViewModel":{"ref":{"entityRefType":"PATENT","entityRefId":"035-382-254-757-182"},"entityMetadata":{"linkedIds":{"empty":true},"tags":[],"collections":[{"id":10791,"type":"PATENT","title":"The Hebrew University of Jerusalem - Patent Portfolio","description":"","access":"OPEN_ACCESS","displayAvatar":true,"attested":false,"itemCount":7593,"tags":[],"user":{"id":91044780,"username":"Cambialens","firstName":"","lastName":"","created":"2015-05-04T00:55:26.000Z","displayName":"Cambialens","preferences":"{\"usage\":\"public\",\"beta\":false}","accountType":"PERSONAL","isOauthOnly":false},"notes":[{"id":8259,"type":"COLLECTION","user":{"id":91044780,"username":"Cambialens","firstName":"","lastName":"","created":"2015-05-04T00:55:26.000Z","displayName":"Cambialens","preferences":"{\"usage\":\"public\",\"beta\":false}","accountType":"PERSONAL","isOauthOnly":false},"text":"
Search Applicants and Owners separately: \"hebrew univ* jerusalem\"; \"hebrew univ* jerus*\"
Select more for logical variants. Add to collection. Select all patents in the collection and expand by simple families. Add to collection. Total patents: 1457
Search Applicants and Owners separately: \"hebrew univ* jerusalem\"; \"hebrew univ* jerus*\"
Select more for logical variants. Add to collection. Select all patents in the collection and expand by simple families. Add to collection. Total patents: 1457
(a) dividing, with the processing unit, the image into small windows, w;\n
(b) determining, with the processing unit, weights for all edges of neighboring pixels for the image in said windows;\n
(c) assuming, with the processing unit, within each window w, that α is a linear combination of color channels, c,\n\nαi≈∑cacIic+b,∀i∈w,\n
(d) using, with the processing unit, a cost function\n\nJ(α,a,b)=∑j∈I(∑i∈wj(αi-∑cacjIic-bj)2+ɛ∑cajc2)\n
\n\n\n∑k❘(i,j)∈wk(δij-1wk(1+(Ii-μk)(∑k+ɛwkI3)-1(Ij-μk)))\neliminate a, b to obtain a cost function involving only α of the form J(α)=αTLα where L(i,j) is of the form:\n
\n\n\n\nwhere δij is the Kronecker delta, μk and σk2 are the mean and covariance of the intensities in the window wk around k and |wk| is the number of pixels in this window;\n
(e) solve, with the processing unit, for α where α=arg min αT Lα s.t.αi=si, ∀iεS, S is the group of selected pixels, and si is the value indicated by said characteristic;\n
(f) solve, with the processing unit, for F and B in the equation Ii=αiFi+(1−αi)Bi with additional smoothness assumptions on F and B;\n
(g) compositing, with the processing unit the foreground object F on a selected background B′ so as to generate an image; and\n
(h) storing data representative of the image in memory for subsequent display."],"number":1,"annotation":false,"title":false,"claim":true},{"lines":["The method according to claim 1, wherein the characteristic with said pixels is a respective distinctive color."],"number":2,"annotation":false,"title":false,"claim":true},{"lines":["The method according to claim 2, wherein areas of F and B are each identified by a scribble of a respective distinctive color."],"number":3,"annotation":false,"title":false,"claim":true},{"lines":["The method according to claim 2, wherein only two distinctive colors are used to constrain the opacity α to be 0 or 1."],"number":4,"annotation":false,"title":false,"claim":true},{"lines":["The method according to claim 2, wherein additional colors are used to identify F and B respectively so as to constrain the value of α."],"number":5,"annotation":false,"title":false,"claim":true},{"lines":["The method according to claim 3, wherein the respective values of α in F and B are constrained to be constant but unknown within a scribble."],"number":6,"annotation":false,"title":false,"claim":true},{"lines":["The method according to claim 1, wherein the selected background B′ is different from the background B."],"number":7,"annotation":false,"title":false,"claim":true},{"lines":["The method according to claim 1, wherein the input is a video sequence and the foreground F, background B and opacity α are also video sequences."],"number":8,"annotation":false,"title":false,"claim":true},{"lines":["A system for matting a foreground object F having an opacity α in an image having a background B, the respective opacity of selected pixels in the foreground object F and the background B being constrained by associating a characteristic with said pixels, comprising:\n
a processing unit;\n
a memory coupled to the processing unit for storing\n
software executable on the processing unit, the software being operable to:\n
(a) dividing the image into small windows, w;\n
(b) determining weights for all edges of neighboring pixels for the image in said windows;\n
(c) assuming within each window w, that α is a linear combination of color channels, c,\n\nαi≈∑cacIic+b,∀i∈w,\n
(d) using a cost function\n\nJ(α,a,b)=∑j∈I(∑i∈wj(αi-∑cacjIic-bj)2+ɛ∑cajc2)\n
\n\n\n∑k❘(i,j)∈wk(δij-1wk(1+(Ii-μk)(∑k+ɛwkI3)-1(Ij-μk)))\neliminate a, b to obtain a cost function involving only α of the form J(α)=αT Lα where L(i,j) is of the form:\n
\n\n\n\nwhere δij is the Kronecker delta, μk and σk2 are the mean and covariance of the intensities in the window wk around k and |wk| is the number of pixels in this window;\n
(e) solve for α where α=arg min αT Lα s.t. αi=si, ∀iεS, S is the group of selected pixels, and si is the value indicated by said characteristic;\n
(f) solve for F and B in the equation Ii=αiFi+(1−αi)Bi with additional smoothness assumptions on F and B;\n
(i) compositing the foreground object F on a selected background B′ so as to generate an image; and\n
(g) storing data representative of the image in memory for subsequent display."],"number":9,"annotation":false,"title":false,"claim":true},{"lines":["The system according to claim 9, wherein the characteristic with said pixels is a respective distinctive color."],"number":10,"annotation":false,"title":false,"claim":true},{"lines":["The system according to claim 10, wherein areas of F and B are each identified by a scribble of a respective distinctive color."],"number":11,"annotation":false,"title":false,"claim":true},{"lines":["The system according to claim 10, wherein only two distinctive colors are used to constrain the opacity α to be 0 or 1."],"number":12,"annotation":false,"title":false,"claim":true},{"lines":["The system according to claim 10, wherein additional colors are used to identify F and B respectively so as to constrain the value of α."],"number":13,"annotation":false,"title":false,"claim":true},{"lines":["The system according to claim 11, wherein the respective values of α in F and B are constrained to be constant but unknown within a scribble."],"number":14,"annotation":false,"title":false,"claim":true},{"lines":["The system according to claim 9, wherein the selected background B′ is different from the background B."],"number":15,"annotation":false,"title":false,"claim":true},{"lines":["The system according to claim 9, wherein the input is a video sequence and the foreground F, background B and opacity α are also video sequences."],"number":16,"annotation":false,"title":false,"claim":true},{"lines":["The system according to claim 9 further including a display device coupled to the memory for displaying said image."],"number":17,"annotation":false,"title":false,"claim":true},{"lines":["A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform a method for matting a foreground object F having an opacity α in an image having a background B, the respective opacity of selected pixels in the foreground object F and the background B being constrained by associating a characteristic with said pixels, the method comprising:\n
(a) dividing the image into small windows, w;\n
(b) determining weights for all edges of neighboring pixels for the image in said windows;\n
(c) assuming within each window w, that α is a linear combination of color channels, c,\n\nαi≈∑cacIic+b,∀i∈w,\n
(d) using a cost function\n\nJ(α,a,b)=∑j∈I(∑i∈wj(αi-∑cacjIic-bj)2+ɛ∑cajc2)\n
\n\n\n∑k❘(i,j)∈wk(δij-1wk(1+(Ii-μk)(∑k+ɛwkI3)-1(Ij-μk)))\neliminate a, b to obtain a cost function involving only α of the form J(α)=αT Lα where l,(i j) is of the form:\n
\n\n\n\nwhere δij is the Kronecker delta, μk and σk2 are the mean and covariance of the intensities in the window wk around k and |wk| is the number of pixels in this window;\n
(e) solve for α where α=arg min αT Lα s.t. αi=si, ∀iεS, S is the group of selected pixels, and si is the value indicated by said characteristic;\n
(f) solve for F and B in the equation Ii=αiFi+(1−αi)Bi with additional smoothness assumptions on F and B; and\n
(g) compositing the foreground object F on a selected background B′."],"number":18,"annotation":false,"title":false,"claim":true}]}},"filters":{"npl":[],"notNpl":[],"applicant":[],"notApplicant":[],"inventor":[],"notInventor":[],"owner":[],"notOwner":[],"tags":[],"dates":[],"types":[],"notTypes":[],"j":[],"notJ":[],"fj":[],"notFj":[],"classIpcr":[],"notClassIpcr":[],"classNat":[],"notClassNat":[],"classCpc":[],"notClassCpc":[],"so":[],"notSo":[],"sat":[]},"sequenceFilters":{"s":"SEQIDNO","d":"ASCENDING","p":0,"n":10,"sp":[],"si":[],"len":[],"t":[],"loc":[]}}