Image segmentation using context sensitive multilevel thresholding method and hybrid meta-heuristic algorithms
Publish Year: 1394
نوع سند: مقاله کنفرانسی
زبان: English
View: 424
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
KBEI02_186
تاریخ نمایه سازی: 5 بهمن 1395
Abstract:
Many traditional techniques histogram-based threshold for effective two-level thresholding and not be able to consider the contextual information space of the image to selectthe optimal threshold. In this paper a new thresholding method with an energy function to generate energy curve of an image bytaking account of contextual information space is provided, whose behavior is very similar to histogram. To incorporate contextual information spatial of the image for the selectionprocess ahead, the energy curve uses the function of the input of energy instead of histogram. In addition, to reduce the problemof multi-level thresholding, we use characteristics of the hybrid genetic algorithms (GA) and particle swarm optimizationoperation (PSO). This algorithm in a number of different types of images was evaluated using validity measure. The result of theproposed method using energy curve is compared with the image histogram based and context sensitive technique with genetic algorithm. These comparisons emphasized the effectiveness of theproposed method with Context sensitive technique with genetic algorithm. These comparisons emphasized the effectiveness of the proposed method.
Keywords:
GA algorithms-PSO algorithm -energy function-Histogram- Image segmentation -Thresholding
Authors
Zahra Alijannejadbaee
Computer Islamic Azad University Babol, Iran
Meysam Mohammadi
Computer Islamic Azad University Amol, Iran
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :