camera ready version

Author: malamatenia

docs/index.html

@@ -366,25 +366,19 @@ <h1>Leveraging Morphology for Historical<br>Script Metrological Analysis</h1>
         </div>
     </header>
 
-    <hr class="section-rule">
-
-    <!-- ══════════════════════════════════════
-         TL;DR
-    ══════════════════════════════════════ -->
     <section>
-
         <p>
-            Paleographic analysis — the study of historical handwriting — still relies heavily on expert eye and subjective comparison. Computational approaches have made progress in recognizing text and extracting character shapes (<em>morphology</em>), but they rarely produce the kind of quantitative measurements (<em>metrology</em>) that are needed for reproducible, large-scale study.
+            Paleographic analysis — the study of historical handwriting — still relies heavily on expert eye and subjective comparison. Computational approaches have made progress in recognizing text and extracting character shapes (<em>morphology</em>), but they rarely produce the kind of <strong>quantitative measurements</strong> (<em>metrology</em>) that are needed for <strong>reproducible, large-scale study</strong>.
         </p>
 
         <ul class="highlights">
             Contributions:
-            <li>We bridge morphological and metrological paleographic analysis by defining
-            measurements based on character prototype alignments, opening the way for
-            more consistent and scalable metrological analysis; </li>
-            <li>we introduce an architecture and training strategy that brings together detection-based character recognition and prototype-based modeling, which improves
-            results, stability, efficiency, and enables us to perform our paleographic measurements;</li>
-            <li> we demonstrate the effectiveness of our approach and measures through a case study, outlining their potential for fine-grained analysis and discovery beyond
+            <li>We <strong>bridge morphological and metrological paleographic analysis</strong> by defining
+            measurements based on <strong>character prototype alignments</strong>, opening the way for
+            more consistent and scalable metrological analysis;</li>
+            <li>we introduce an <strong>architecture and training strategy</strong> that brings together <strong>detection-based character recognition</strong> and <strong>prototype-based modeling</strong>, which improves
+            results, stability, efficiency, and enables our paleographic measurements;</li>
+            <li>we demonstrate the effectiveness of our approach through a <strong>case study</strong>, outlining its potential for <strong>fine-grained analysis and discovery</strong> beyond
             hand recognition.</li>
         </ul>
     </section>
@@ -471,6 +465,7 @@ <h3>Text-line annotations of Paris, BnF, fr. 2813</h3>
         </div>
     </section>
 
+    <hr class="section-rule">
 
     <!-- ══════════════════════════════════════
          RESULTS