Differences

This shows you the differences between two versions of the page.

--- teaching:saliency:saliency_assignment [2019/09/21 16:58] – anthony
+++ teaching:saliency:saliency_assignment [2019/09/22 09:02] (current) – anthony
@@ Line 1: / Line 1: @@
 ====== Attentional saliency in images ======
-[[teaching:saliency:saliency_instructions|Instructions given to students]]
+[[teaching:methods|Back to teaching methods main page]]
+\\
+Students pick an image and circle regions that appear to draw attention to themselves: salient regions.
+The instructor runs the images through the Itti-Koch saliency algorithm, which marks pixels that ought to jump out at viewers because they represent regions that are different from their surroundings.
+\\
+[[teaching:saliency:saliency_instructions|Background and instructions given to students]]
+\\
+[[https://github.com/acate/saliency_maps|Github page for source code]]
 \\
 ===== Sample results =====
-{{:teaching:saliency:person11_fig.png|}}
+\\
+The algorithm identifies image regions that stand out based on several basic visual features, including color, intensity and edge orientation.
-{{:teaching:saliency:person1_fig.png|}}
+{{:teaching:saliency:person18_fig.png|}}
+\\
+It sometimes appears that the algorithm is picking out complex objects that are similar to what humans ultimately notice ...
-{{:teaching:saliency:person9_fig.png|}}
 {{:teaching:saliency:person15_fig.png|}}
-{{:teaching:saliency:person18_fig.png|}}
+{{:teaching:saliency:person1_fig.png|}}
+... however, the algorithm actually works in "local" fashion based on small, often meaningless visual differences.
+{{:teaching:saliency:person9_fig.png|}}
+{{:teaching:saliency:person11_fig.png|}}