Shape Similarity Measurement for Known-Object Localization: A New Normalized Assessment

Abstract

This paper presents a new, normalized measure for assessing a contour-based object pose. Regarding binary images, the algorithm enables supervised assessment of known-object recognition and localization. A performance measure is computed to quantify differences between a reference edge map and a candidate image. Normalization is appropriate for interpreting the result of the pose assessment. Furthermore, the new measure is well motivated by highlighting the limitations of existing metrics to the main shape variations (translation, rotation, and scaling), by showing how the proposed measure is more robust to them. Indeed, this measure can determine to what extent an object shape differs from a desired position. In comparison with 6 other approaches, experiments performed on real images at different sizes/scales demonstrate the suitability of the new method for object-pose or shape-matching estimation.

UnCanny: Exploiting Reversed Edge Detection as a Basis for Object Tracking in Video

“…The total vector of motion across these points trends downwards as the man flinches. Other techniques may be used at this point to determine motion more precisely, such as object pose matching [ 28 , 29 ] or partially supervised pattern recognition [ 30 , 31 ].…”

Modelling the 2D object recognition task in manufacturing context: An information‐based model

“…In [80], a normalised measure for assessing the contour‐based object pose is developed. The developed measure is applied to binary images for the assessment of known‐object recognition and localisation.…”