Preprint / Prétirage On The Hausdorff Distance Used For The Evaluation Of Segmentation Results

نویسنده

  • G. Edwards
چکیده

Les techniques de segmentation d'images sont largement utilisées en télédétection, comme le démontre leur présence dans la plupart des systèmes commerciaux de traitement d'images. Un effort considérable a été consacré au développement d'algorithmes de segmentation, résultant en une profusion de techniques différentes. En comparaison, le nombre d'outils développés pour l'évaluation quantitative des résultats de segmentation demeure très limité. En fait, l'inspection visuelle des résultats est encore considérée par plusieurs comme le test ultime. Dans cet article, nous présentons une nouvelle méthode quantitative d'évaluation de résultats de segmentation d'images. Cette dernière s'appuie sur la distance d'Hausdorff. La méthode est basée sur le degré de coincidence des points de frontières entre les résultats d'une segmentation d'image et une carte de référence. L'utilité de la méthode est illustrée avec un exemple de segmentation tiré de la littérature.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Grading evaluation study of atlas based auto-segmentation of organs at risk in thorax

Background: The grading evaluation of atlas based auto-segmentation (ABAS) of organs at risk (OARs) in thorax was studied. Materials and Methods: Forty patients with thoracic cancer were included in this study, and for each thirteen thoracic OARs were delineated by an experienced radiation oncologist. The patients were randomly grouped into the training and the test dataset (20 each). The inves...

متن کامل

روشی جدید به منظور تعیین مرز ضایعات در تصاویر فراصوت از بافت پستان: اصلاح وفقی ضریب انتشار ناهمسانگرد

Accurate segmentation plays a vital role in automated analysis of ultrasonic images. A new method based on adaptive anisotropic diffusion is introduced here for lesion detection in ultrasonic images of the breast. In this method, a hypothesis testing framework is defined first to separate lesions from healthy breast tissue. Then the boundary of lesion is estimated by adaptive anisotropic diffus...

متن کامل

Hierarchical Group Compromise Ranking Methodology Based on Euclidean–Hausdorff Distance Measure Under Uncertainty: An Application to Facility Location Selection Problem

Proposing a hierarchical group compromise method can be regarded as a one of major multi-attributes decision-making tool that can be introduced to rank the possible alternatives among conflict criteria. Decision makers’ (DMs’) judgments are considered as imprecise or fuzzy in complex and hesitant situations. In the group decision making, an aggregation of DMs’ judgments and fuzzy group compromi...

متن کامل

Individual virtual phantom reconstruction for organ dosimetry based on standard available phantoms

Background: In nuclear medicine application often it is required to use computational methods for evaluation of organ absorbed dose. Monte Carlo simulation and phantoms have been used in many works before. The shape, size and volume in organs are varied, and this variation will produce error in dose calculation if no correction is applied. Materials and Methods: A computational framewo...

متن کامل

Robust Potato Color Image Segmentation using Adaptive Fuzzy Inference System

Potato image segmentation is an important part of image-based potato defect detection. This paper presents a robust potato color image segmentation through a combination of a fuzzy rule based system, an image thresholding based on Genetic Algorithm (GA) optimization and morphological operators. The proposed potato color image segmentation is robust against variation of background, distance and ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2001