Downloads provided by UsageCounts
Les algorithmes de segmentation croissante par région sont utiles pour la segmentation d'images par télédétection. Ces algorithmes nécessitent que l'utilisateur fournisse des paramètres de contrôle, qui contrôlent la qualité de la segmentation résultante. Une fonction objective est proposée pour sélectionner les paramètres appropriés pour les algorithmes de croissance par région afin d'assurer les meilleurs résultats de qualité. Il considère qu'une segmentation a deux propriétés souhaitables : chacun des segments résultants doit être homogène en interne et doit se distinguer de son voisinage. La mesure combine un indicateur d'autocorrélation spatiale qui détecte la séparabilité entre les régions et un indicateur de variance qui exprime l'homogénéité globale des régions.
Los algoritmos de segmentación de crecimiento regional son útiles para la segmentación de imágenes por teledetección. Estos algoritmos necesitan que el usuario suministre parámetros de control, que controlan la calidad de la segmentación resultante. Se propone una función objetiva para seleccionar los parámetros adecuados para los algoritmos decrecimiento regional para garantizar los mejores resultados de calidad. Considera que una segmentación tiene dos propiedades deseables: cada uno de los segmentos resultantes debe ser internamente homogéneo y debe distinguirse de su vecindario. La medida combina un indicador de autocorrelación espacial que detecta la separabilidad entre regiones y un indicador de varianza que expresa la homogeneidad general de las regiones.
Region‐growing segmentation algorithms are useful for remote sensing image segmentation. These algorithms need the user to supply control parameters, which control the quality of the resulting segmentation. An objective function is proposed for selecting suitable parameters for region‐growing algorithms to ensure best quality results. It considers that a segmentation has two desirable properties: each of the resulting segments should be internally homogeneous and should be distinguishable from its neighbourhood. The measure combines a spatial autocorrelation indicator that detects separability between regions and a variance indicator that expresses the overall homogeneity of the regions.
خوارزميات التجزئة المتنامية للمنطقة مفيدة لتجزئة صور الاستشعار عن بعد. تحتاج هذه الخوارزميات إلى المستخدم لتزويد معلمات التحكم، والتي تتحكم في جودة التجزئة الناتجة. يتم اقتراح وظيفة موضوعية لاختيار المعلمات المناسبة لخوارزميات نمو المنطقة لضمان أفضل نتائج الجودة. وهي تعتبر أن التقسيم له خاصيتان مرغوب فيهما: يجب أن يكون كل جزء من الأجزاء الناتجة متجانسًا داخليًا ويجب تمييزه عن جواره. يجمع المقياس بين مؤشر الارتباط الذاتي المكاني الذي يكشف عن قابلية الانفصال بين المناطق ومؤشر التباين الذي يعبر عن التجانس العام للمناطق.
Scale-space segmentation, Artificial intelligence, MRI Segmentation, Social Sciences, Management Science and Operations Research, Image Segmentation, Pattern recognition (psychology), Feature Extraction, Decision Sciences, Engineering, Segmentation, Region growing, Segmentation-based object categorization, Machine learning, Media Technology, FOS: Mathematics, Image Segmentation Techniques, Homogeneous, Data mining, Image segmentation, Application of Grey System Theory in Forecasting, Homogeneity (statistics), Statistics, Spatial analysis, Hyperspectral Image Analysis and Classification, Computer science, Algorithm, Combinatorics, Autocorrelation, Physical Sciences, Computer Science, Computer vision, Computer Vision and Pattern Recognition, Mathematics, Forecasting Model Optimization
Scale-space segmentation, Artificial intelligence, MRI Segmentation, Social Sciences, Management Science and Operations Research, Image Segmentation, Pattern recognition (psychology), Feature Extraction, Decision Sciences, Engineering, Segmentation, Region growing, Segmentation-based object categorization, Machine learning, Media Technology, FOS: Mathematics, Image Segmentation Techniques, Homogeneous, Data mining, Image segmentation, Application of Grey System Theory in Forecasting, Homogeneity (statistics), Statistics, Spatial analysis, Hyperspectral Image Analysis and Classification, Computer science, Algorithm, Combinatorics, Autocorrelation, Physical Sciences, Computer Science, Computer vision, Computer Vision and Pattern Recognition, Mathematics, Forecasting Model Optimization
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 268 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Top 1% | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Top 1% | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Top 10% |
| views | 12 | |
| downloads | 35 |

Views provided by UsageCounts
Downloads provided by UsageCounts