1 / 9

Feature Detection

Feature Detection. Feature Detection. Image Features –Decisions!. Features such as edges, corners, junction, eyes, … are obtained by making some decision from the image measurements.

qamra
Download Presentation

Feature Detection

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Feature Detection Feature Detection Computer Vision

  2. Image Features –Decisions! Features such as edges, corners, junction, eyes, … are obtained by making some decision from the image measurements. Decisions are the result of some comparison followed by a choice. Examples (i) if a measurement is above a threshold we accept, not otherwise; (ii) if a measurement is the largest compared to others, we select it. Computer Vision

  3. A step edge at q=0. The value is (equally) large for both q=0 and q=p/4 as shown (in red) for scale s=3 pixels. It is also large for values q=p/6, p/3 not shown. However, the quantity is significantly larger for q=0. Decisions: Edgels (Edge-pixels and Orientation) Edge threshold: Decision! Edge orientation: Decision! Computer Vision

  4. Decisions: Edgels (cont.) Strength of the Edgel Eliminate some spurious locations. Decision! The gray level indicates the angle: the darkest one is 0 degrees. The larger is the angle the lighter is displayed, up to 5p/6. Computer Vision

  5. Decisions: Local Angle Change Angle change where is the contour curvature multiplied by the arc length , where A contour segment y x Computer Vision

  6. Decisions: Junctions, Corners Junction threshold: Decision! Remove (Undo) detection if Eliminate spurious locations. Decisions! Examining the values of q where allow us to characterize the junctions. For example, when only two value of q pass the test and or suggest a corner. Corners are many times called L-junctions. If three angles are detected, it may be a T-junction or an Y-junction. T-junctions exhibit one region with angle near p, and usually arise in images due to surface occlusions in a scene. Four angles suggest a X-junction, and usually arise in images due to surface transparency in the scene. Note that this detector also detects many edgels. Computer Vision

  7. qmax (xc , yc) Decisions: Connecting Edgels, Pseudocode Algorithm to link edgels. Start with a seed location (xc,yc) Contour-Follower(xc , yc) if (Edgel(xc , yc )  NIL ) Link-neighbors+(xc , yc ,qmax) Link-neighbors-(xc , yc ,qmax) end Link-neighbors±(xc , yc ,qmax) xn±= xc ± xqmaxcosqmax ; yn±= yc ±  yqmaxsinqmax ; if (Edgel(xn±,yn±)  NIL ) Link((xc , yc), (xn±,yn±)) Link-neighbors±( xn±,yn±,qmax(xn±,yn±) ) end Computer Vision

  8. Decisions: Connecting Edgels, Pseudocode Link-neighbors±(xc , yc ,qmax-c) xn±= xc ± xqmaxcosqmax ; yn±= yc ±  yqmaxsinqmax ; if ((Edgel(xn±,yn±)  NIL )&(Coherence(xc , yc xn±,yn±))) Link((xc , yc), (xn±,yn±)) Link-neighbors±( xn±,yn±,qmax-n(xn±,yn±) ) end Coherence(xc , yc xn,yn) if ( and ) return True else Nil end Computer Vision

  9. Threshold Parameters: Estimation We have considered at least four parameters: How to estimate them? One technique is Histogram partition: Plot the Histogram and find the parameter that “best partition it”: Computer Vision

More Related