Git commit adbced99fa0ca801ecd20b6e4ed5b2e9b2d2a1cf by Yuri Chornoivan. Committed on 18/09/2016 at 10:14. Pushed by yurchor into branch 'master'.
Fix minor typos M +2 -2 digikam/using-mainwindow.docbook http://commits.kde.org/digikam-doc/adbced99fa0ca801ecd20b6e4ed5b2e9b2d2a1cf diff --git a/digikam/using-mainwindow.docbook b/digikam/using-mainwindow.docbook index 27941e9..335b335 100644 --- a/digikam/using-mainwindow.docbook +++ b/digikam/using-mainwindow.docbook @@ -828,7 +828,7 @@ <sect3> <title>Face Recognition</title> <para> - Assigning People tags to face tags is an important prerequisite to Face Recognition. Very obviously &digikam; can only recognize faces if it has something to compare with. So it's up to you to show it the ropes, which means in this case to tell &digikam;: This is Lara, this is Juan, this is Peter an so forth. For that you would, after performing a Face Detection as described in the previous article, typically select the <quote>unknown</quote> tag on the Left Sidebar, click on a thumbnail and click, if necessary, on the + Assigning People tags to face tags is an important prerequisite to Face Recognition. Very obviously &digikam; can only recognize faces if it has something to compare with. So it's up to you to show it the ropes, which means in this case to tell &digikam;: This is Lara, this is Juan, this is Peter and so forth. For that you would, after performing a Face Detection as described in the previous article, typically select the <quote>unknown</quote> tag on the Left Sidebar, click on a thumbnail and click, if necessary, on the <inlinemediaobject> <imageobject><imagedata fileref="&path;using-mainwindow-icon-showfacetags.png" format="PNG" /></imageobject> </inlinemediaobject> @@ -848,7 +848,7 @@ </para> <para> - In case of unsatisfying results it might be helpful to use <guilabel>Clear and rebuild all training data</guilabel>. One reason can be that there are to many face tags assigned to a person which shows this person in a way that doesn't really help the search algorithm, ⪚ with sunglasses, blurred, unusual colors, carnival make up, dark shaded areas in the face, baby/kid/adult photographs mixed... Another reason to use that option can be false face recognition due to a wrong accuracy setting in the <guilabel>Parameters</guilabel> tab. + In case of unsatisfying results it might be helpful to use <guilabel>Clear and rebuild all training data</guilabel>. One reason can be that there are too many face tags assigned to a person which shows this person in a way that doesn't really help the search algorithm, ⪚ with sunglasses, blurred, unusual colors, carnival make up, dark shaded areas in the face, baby/kid/adult photographs mixed... Another reason to use that option can be false face recognition due to a wrong accuracy setting in the <guilabel>Parameters</guilabel> tab. </para> <para>
