An intelligent multimedia system for identification of weed seedlings

Pomar, J.; Hidalgo, Iván Astola

doi:10.1016/s0168-1699(97)00045-8

Cited by 5 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. As a result of the lack of correlation between level of computer use and quiz score, unfamiliarity with computers was probably not a factor in our study, similar to Taraban et al (2004) and Pomar and Hidalgo (1998). A twodimensional picture simply may not be as good a teaching tool as a threedimensional object.…”

Section: Discussionmentioning

confidence: 57%

Comparing Student Performance in Live Versus Web-based Instruction in Herbaceous Plant Identification

Teolis

Peffley

Wester

2007

hortte

View full text Add to dashboard Cite

A study was conducted to evaluate student performance after receiving the same horticultural lesson through one of two modes of instruction. Students enrolled in an introductory horticulture course received either a traditional herbaceous plant identification (ID) lesson with live plant specimens or the same lesson using only text and photographs on the Internet in one of their laboratory sessions. A follow-up experiment was conducted in which web-based students studied photographs of the exact same plants studied by students receiving traditional instruction. Learning style preferences and demographic information were obtained from surveys. For both experiments, students receiving traditional instruction had higher scores on the plant ID quiz than web-based students. All students were able to identify plants from photographs just as well as from live plant specimens. Visual learners scored higher when receiving traditional instruction when compared with web-based instruction. Student grade point average was positively correlated with quiz score for both experiments.

show abstract

Section: Discussionmentioning

confidence: 57%

Comparing Student Performance in Live Versus Web-based Instruction in Herbaceous Plant Identification

Teolis

Peffley

Wester

2007

hortte

View full text Add to dashboard Cite

show abstract

“…ZSTU-GR01with parallel insert grafting, a kind of insert-mating method, can achieve the combination of rootstocks and scions without any auxiliary components. In addition, the fast motion of mechanical operation is also good at reducing water loss from the graft wound [3].…”

Section: Introductionmentioning

confidence: 99%

Experimental Study on an Automatic Graft Robot for Fruits and Vegetables

Zhang

Wang

Zhang

2011

AMR

View full text Add to dashboard Cite

The graft robot (named ZSTU-GR01), developed by authors, is an automatic machine for grafting fruits and vegetables with parallel insert method. The objective of this research is to test the performance of ZSTU-GR01 automatic graft robot and find out the most suitable seedling parameters for grafting. Thus a PLC program and a grafting experiment for graft robot were developed. The experimental results showed that the total grafting speed was 514 seedlings per hour, and total success rate was 84%. Eight independent comparison experiments showed that the most suitable seedling parameters for grafting were: rootstock diameter 3.5-4.5(mm); scion diameter 2-3(mm); rootstock stem and scion stem straight; angle of rootstock cotyledons close to 180 degrees.

show abstract

“…This is due to the specificity that most of the used products exhibit. Consequently, weed indentification is a key tast in chemical weed control methods 4 . Different optical techniques are under investigation for detecting weeds and crops.…”

Section: Introductionmentioning

confidence: 99%

Discrimination of rapeseed and weeds under actual field conditions based on principal component analysis and artificial neural network by VIS/NIR spectroscopy

Huang

Bao

2007

MIPPR 2007: Pattern Recognition and Computer Vision

View full text Add to dashboard Cite

The study documented successful discrimination between five weed species and rapeseed plants under actual field conditions using visible and near infrared (Vis/NIR) spectroscopy. A hybrid recognition model, BP artificial neural networks (BP-ANN) combined with principal component analysis (PCA), had been established for discrimination of weeds in rapeseed field. Spectra tests were performed on the rapeseed and five-weed species canopy of 180 samples in the field using a spectrophotometer (325-1075 nm). 6 optimal PCs were selected as the input of BP neural networks to build the prediction model. Rapeseed samples were marked as 1, while the five weed species marked as 2, 3, 4, 5, 6, which were used as output set of BP-ANN. 120 samples were randomly selected as the training set, and the remainder as prediction set. It showed excellent predictions with the correlation value of 0.9745, and the relative standard deviation (RSD) was under 5% thus 100% of prediction accuracy was achieved. The results are promising for further work in real-time identification of weed patches in rapeseed fields for precision weed management.

show abstract

An intelligent multimedia system for identification of weed seedlings

Cited by 5 publications

References 2 publications

Comparing Student Performance in Live Versus Web-based Instruction in Herbaceous Plant Identification

Comparing Student Performance in Live Versus Web-based Instruction in Herbaceous Plant Identification

Experimental Study on an Automatic Graft Robot for Fruits and Vegetables

Discrimination of rapeseed and weeds under actual field conditions based on principal component analysis and artificial neural network by VIS/NIR spectroscopy

Contact Info

Product

Resources

About