Identification of Weeds on Crop Lands for Site Specific Spraying
VikinthWitman1, JebaPriya2, Debu3, Piyush Sharma4, BennisamPrakash5
1C.Vikinth Witman, Final year Student, Department of Computer Science, Karunya Institute of Technology and Science, Coimbatore (Tamil Nadu), India.
2S.Jeba Priya, Assistant Professor, Department of Computer Science, Karunya Institute of Technology and Science, Coimbatore (Tamil Nadu), India.
3B.Debu, Final year Student, Department of Computer Science, Karunya Institute of Technology and Science, Coimbatore (Tamil Nadu), India.
4Piyush Sharma, Final year Student, Department of Computer Science, Karunya Institute of Technology and Science, Coimbatore (Tamil Nadu), India.
5BennisamPrakash, Final year Student, Department of Computer Science, Karunya Institute of Technology and Science, Coimbatore (Tamil Nadu), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 117-123 | Volume-8 Issue-5, March 2019 | Retrieval Number: E2886038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Adaptation of this method of identification of weeds in specific areas on crop lands which help for healthy agriculture. Mostly separations of weeds from the crops are done with the help of image processing. It is the process of separation of weeds specifically from the crops. This method of separation will be helpful in optimization of herbicide usage. There are several methods of image pre-processing used to remove the information which is irrelevant from the image other than weeds. Crops are separated in rows. Different colour models are used and then proposed for grey image, vertical projection is used to identify centre line of crop row. Image segmentation is the first process to segment the image using various methods like greenness identification with the help of RGB and H-components with YIQ, HSV, HIS colour spaces. It leads to 126 colour feature extraction from the image. Cultural algorithm is used for separation of feature from the image and Search algorithm is used in specific identification of crops and weeds for specific spraying. After feature extraction SVM algorithm and BP algorithm is used for experimental result for higher accuracy of about 92.8% in real-time decision.
Keyword: Colour Features, Feature Extraction, Image Pre Processing, Image Segmentation, Image Separation, Weed Identification.
Scope of the Article: Automated Software Specification