Unique Measure for Geometrical Shape Object Detection-based on Area Matching

Abstract

Object classifier often operates by making decisions based on the values of several shape properties measured from an image of the object. The paper introduces a unique definition of measure for 2-D geometrical object shape detection. Using this definition different object shapes can be identified on the basis of their degree of fitness parameter. Basically, we have fitted a 2-D polygon/curve on the object as a best fitted polygon/curve and computed the parameter degree of fitness which is the ratio of the matching area and non-matching area due to the fitted polygon/curve and the object both. The results show the effectiveness of the proposed measure.

Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation

“…Y la segunda opción es cuando el algoritmo da una caja de predicción porque si encuentra un objeto en la imagen y se da una intersección de unión mayor al 0.5, pero la clase a la que es asignada el objeto es una clase equivocada. 33…”

Automatic Bright Circular Type Oil Tank Detection Using Remote Sensing Images

“…The circularity measure is used to describe departure quantity between the object R i (C j ) and round, which is defined as 19 :…”

Global Contour and Region Based Shape Analysis and Similarity Measures

“…Although the term similarity is often used, dissimilarity corresponds to the notion of distance: small distance means small dissimilarity, and large similarity. Shape similarity measures are used in building extraction and oil tank detection from remote sensing images 2,6,7,8 . Various shape features are often evaluated by how accurately they allow one to retrieve similar shapes from a designated database.…”

“…As for example, for finding rectangular or circular or elliptical shape object one has to define different measure for different shape. A new definition of measure for different geometrical shapes detection is presented by Chaudhuri 6 , et al The definition is a unique (single) measure by which different shape of objects can be identify on the basis of their degree of fitness parameter. In our paper 6 , first, we have fitted a polygon/ curve optimally on the object then compute the degree of fitness, which is a ratio of matching area and the non-matching area due to object and polygon/curve both.…”

“…A new definition of measure for different geometrical shapes detection is presented by Chaudhuri 6 , et al The definition is a unique (single) measure by which different shape of objects can be identify on the basis of their degree of fitness parameter. In our paper 6 , first, we have fitted a polygon/ curve optimally on the object then compute the degree of fitness, which is a ratio of matching area and the non-matching area due to object and polygon/curve both. Next, we are identified the object of a particular geometrical shape (rectangle/circle/ ellipse) on the basis of minimal value of degree of fitness for different fitted polygon/curve.…”