GPU based parallel image processing for plant growth analysis

Adnan Ozdemir*, Turgay Altilar

*Bu çalışma için yazışmadan sorumlu yazar

Araştırma sonucu: ???type-name???Konferans katkısıbilirkişi

2 Atıf (Scopus)

Özet

Plant growth analysis is hard to do automatic. The burden of technique makes harder to process the algorithm. Thresholding and segmentation parts are huge part of the approaches. In this study 15 different thresholding algorithms were implemented and compared with images from field for plant growth analysis. To decrease execution time, the algorithm was implemented on GPU (Graphics Processing Unit) with CUDA (Compute Unified Device Architecture) language. Also, thresh-olding methods was applied on GPU. These are Huang's fuzzy, Intermodes, Isodata, Li's Minimum Cross Entropy, Kapur-Sahoo-Wong (Maximum Entropy), Mean, Minimum Error, Minimum, Moments, Otsu, Percentile, RenyiEntropy, Shanbhag, Triangle, and Yen thresholding algorithms. Each method investigated the thresholds on HSV histograms to find proper color values. After all process, threshold results for dynamic and constant values were listed and compared. Moreover, performance metrics were measured.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığı2014 The 3rd International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2014
YayınlayanInstitute of Electrical and Electronics Engineers Inc.
ISBN (Elektronik)9781479941575
DOI'lar
Yayın durumuYayınlandı - 25 Eyl 2014
Etkinlik2014 3rd International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2014 - Beijing, China
Süre: 11 Ağu 201414 Ağu 2014

Yayın serisi

Adı2014 The 3rd International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2014

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2014 3rd International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2014
Ülke/BölgeChina
ŞehirBeijing
Periyot11/08/1414/08/14

Bibliyografik not

Publisher Copyright:
© 2014 IEEE.

Parmak izi

GPU based parallel image processing for plant growth analysis' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

Alıntı Yap