Expert System for Identification of Weeds

Abstract

Identification of weeds is essential for designing an efficient strategy for their management. However, it is a difficult task requiring expert knowledge and experience. An expert system to help researchers, farmers, extension workers and students to identify weed species of crop and non-crop lands has been developed at the Directorate of Weed Science Research, Jabalpur. The expert system uses family, scientific, common name-based classification and a mix of the text description and photographs. The system is supported by a database containing information about 337 weed species with colour images. The expert system was evaluated following the conventional expert system evaluation methodologies. Results indicated that non-expert users were able to make weed identification using the expert system efficiently.