Statistics-based segmentation using a continuous-scale naive Bayes approach
Autor: | Henrik Skov Midtiby, Rasmus Nyholm Jørgensen, Morten Stigaard Laursen, Norbert Krüger |
---|---|
Rok vydání: | 2014 |
Předmět: |
Color histogram
Color normalization Computer science INDEXES ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation HSL and HSV Horticulture Vegetation indices Naive Bayes Segmentation RGB plus NIR Computer vision business.industry Forestry Pattern recognition Image segmentation Plant-soil discrimination Computer Science Applications MODEL Feature (computer vision) RGB color model VEGETATION Artificial intelligence business Agronomy and Crop Science |
Zdroj: | Stigaard Laursen, M, Midtiby, H & Krüger, N 2014, ' Statistics-Based Segmentation Using a Continuous-Scale Naive Bayes Approach ', Computers and Electronics in Agriculture, vol. 109C, pp. 271-277 . https://doi.org/10.1016/j.compag.2014.10.009 Laursen, M S, Midtiby, H S, Kruger, N & Jorgensen, R N 2014, ' Statistics-based segmentation using a continuous-scale naive Bayes approach ', Computers and Electronics in Agriculture, vol. 109, pp. 271-277 . https://doi.org/10.1016/j.compag.2014.10.009 |
ISSN: | 0168-1699 |
DOI: | 10.1016/j.compag.2014.10.009 |
Popis: | Naive Bayes classifier was implemented for combination of domain color features.Combined color features proved significantly better than individual color features.Significance was determined with 95% confidence by t-test on cross-validated data.The dataset consisted of 20 images captured under controlled illumination in RGB+NIR. Segmentation is a popular preprocessing stage in the field of machine vision. In agricultural applications it can be used to distinguish between living plant material and soil in images. The normalized difference vegetation index (NDVI) and excess green (ExG) color features are often used in the segmentation of images with multiple color channels. In this paper, a Bayesian method is used to combine existing color features into a common color feature. This feature is then used to segment images into separate regions containing vegetation and soil. The common color feature produces an improved segmentation over the normalized vegetation difference index and excess green. The inputs to this color feature are the R, G, B, and near-infrared color wells, their chromaticities, and NDVI, ExG, and excess red. We apply the developed technique to a dataset consisting of 20 manually segmented images captured under artificial illumination. The results show that our combined feature enables better segmentation using the individual color features. Better segmentation allows for more robust vision-based weeding, thereby allowing for lower safety margins within cell-sprayers and lower herbicide usage. |
Databáze: | OpenAIRE |
Externí odkaz: |
načítá se...