technical notes

Author: ehsanx

.gitignore

@@ -2,3 +2,4 @@ runtime/
 .Rhistory
 
 /.quarto/
+.Rproj.user

Comic-Panel-Extractor.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

Comic-Panel-Extractor_Win64.spec

@@ -9,10 +9,10 @@ The OpenCV detection algorithm is specifically tuned to handle the hard stuff: n
 ## 🔬 Technical Details & Known Limitations
 
 **How it works:**
-The engine uses OpenCV to convert each page to grayscale, applies a binary threshold to isolate the ink from the paper, dilates the image to close gaps in the panel borders, and uses contour detection (`cv2.findContours`) to draw bounding boxes around the panels. It then filters out noise based on page-area ratios and nested containment.
-
+The engine uses OpenCV to convert each page to grayscale and applies an Otsu/Adaptive binary threshold to isolate the ink from the paper. It then uses morphological closing to bridge gaps in faded panel borders, and contour detection (`cv2.findContours` using `RETR_EXTERNAL`) to draw bounding boxes while intentionally ignoring internal dialogue balloons. Finally, it filters out noise based on area and aspect ratios, discards overlapping regions via Intersection-over-Union Non-Maximum Suppression (IoU-NMS), and calculates the final reading order using DPI-independent row clustering.
 **Where it might fail (Please read):**
-Because this relies on visual heuristics rather than publisher-provided metadata, it is not 100% perfect. You may experience incorrect crops or missed panels under the following conditions:
+Because this relies on visual heuristics rather than publisher-provided metadata, it may not work in some cases. You may experience incorrect crops or missed panels under the following conditions:
+
 * **Overlapping Panels / Broken Gutters:** If a character's arm reaches outside a panel and breaks the gutter line, the algorithm may merge two panels together.
 * **Non-Rectangular / Splash Pages:** Circular panels, extreme diagonals, or chaotic splash pages without clear borders will likely confuse the bounding box logic.
 * **Zero-Gutter / Full Bleed:** If the page has no gutters at all (the art goes entirely to the edge of the page), the algorithm cannot slice it.