Development of Neural Networks for Weed Recognition in Corn Fields

The main objective of this project was to develop a weed recognition system based on artificial neural networksto assist in the precision application of herbicides in corn fields. Digital images were collected in May 1998 using acommercially available digital camera. The intensities of the three primary colors (red, green, and blue) were compared foreach pixel of the images. The three intensities of a pixel remained unchanged when, in the pixel, the green intensity was greaterthan each of the other two; otherwise, the three intensities of the pixel were set to zero. Background objects, except plants,were thus removed from the images. The resulting pixel intensities of the modified images were used as the inputs for LearningVector Quantization (LVQ) artificial neural networks (ANNs). ANNs were trained to distinguish corn from weeds, as well asto differentiate between weed species. The success rate for a single ANN in distinguishing a given weed species from cornwas as high as 90%, and as high as 80% in distinguishing any of four weed species from corn. Better success rates might beobtainable with more elaborate schemes for data input and/or structural improvements such as cascading. Theimageprocessing time for the ANNs was as short as 0.48 s per image, thus making it useful for realtime data processingand application of herbicides. The development of such ANNs for weed recognition could be useful in precision farming toguide sitespecific herbicide application and ultimately reduce the total amount of herbicide applied as well as lowering therisk of pollution.