Image analysis associated with a fuzzy neural network and estimation of shoot length of regenerated rice callus

Honda, Hiroyuki; Takikawa, Naoto; Noguchi, Hideki; Hanai, Taizo; Kobayashi, Takeshi

doi:10.1016/s0922-338x(97)89256-2

Cited by 30 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In plant tissue culture, RGB based image analysis has been restricted to identification and estimation of shoot length (Honda et al 1997), secondary metabolite determination in hairy root cultures (Berzin et al 1999) and clustering of regenerated plants into groups (Mahendra et al 2004;Prasad and Dutta Gupta 2008).…”

Section: Introductionmentioning

confidence: 99%

Estimation of the chlorophyll content of micropropagated potato plants using RGB based image analysis

Yadav

Ibaraki

Gupta

2009

Plant Cell Tiss Organ Cult

126

View full text Add to dashboard Cite

A method has been developed for rapid and non invasive determination of chlorophyll content of leaves of micropropagated potato plants using RGB based image analysis. Among the trichomatic colors, R and G negatively correlated with the chlorophyll content, while a positive correlation was observed with B chromate. Compared to mean brightness value, the use of mean brightness ratio considerably improved the relationship of the tricolors with chlorophyll content. The brightness values and ratios of the primary colors are modeled as linear correlation functions for chlorophyll content. A significant correlation was observed between the model predicted chlorophyll content with the chlorophyll content measured by chlorophyll content meter. Spectral properties such as luminosity and saturation were also found to be negatively correlated with the chlorophyll content. The relationship was improved by combining the mean brightness ratio at B band region with luminosity. The potential of the imaging system in micropropagation has been discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimation of the chlorophyll content of micropropagated potato plants using RGB based image analysis

Yadav

Ibaraki

Gupta

2009

Plant Cell Tiss Organ Cult

126

View full text Add to dashboard Cite

show abstract

“…The work demonstrated the relative efficacy of neural network in estimating plant cell mass growth over the conventional modeling tools. Apart from feed forward back propagation network which has a supervised learning technique, the use of networks having unsupervised architectures in tissue culture is reported in Gladiolus where on the basis of trichometric features of leaves trichometric sorting of in vitro regenerated plants was (Uozumia et al 1993;Suroso Murase et al 1996;Honda et al 1997;Zhang et al 1999). Neural network aided estimation of shoot length of in vitro regenerated rice was demonstrated by Honda et al (1997).…”

Section: Resultsmentioning

confidence: 99%

Efficiency of neural networks for prediction of in vitro culture conditions and inoculum properties for optimum productivity

Mehrotra¹,

Prakash²,

Mishra³

et al. 2008

Plant Cell Tiss Organ Cult

View full text Add to dashboard Cite

This study represents an ANN based computational scheming of physical, chemical and biological parameters at flask level for mass multiplication of plants through micropropagation using bioreactors of larger volumes. The optimal culture environment at small scale for Glycyrrhiza plant was predicted by using neural network approach in terms of pH and volume of growth medium per culture flask, incubation room temperature and month of inoculation along with inoculum properties in terms of inoculum size, fresh weight and number of explant per flask. This kind of study could be a model system in commercial propagation of various economically important plants in bioreactors using tissue culture technique. In present course of study the ANN was trained by implementing MATLAB neural network. A feed-forward back propagation type network was created for input vector (seven input elements), with single hidden layer (seven nodes) and one output unit in output layer. The 'tansig' and 'purelin' transfer functions were adapted for hidden and output layers respectively. The four training functions viz. traingda, trainrp, traincgf, traincgb were randomly selected to train four networks which further examined with available dataset. The efficiency of neural networks was concluded by the comparison of results obtained from this study with that of empirical data obtained from the detailed tissue culture experiments and designated as Target set (mean fresh weight biomass per culture flask after 40 days of in vitro culture duration). Efficiency of networks for better training initialization was judged on the basis of comparative analysis of 'Mean Square Error at zero epoch' for each network trained in which the least error at initial point was observed with trainrp followed by traincgb and traincgf. A comparative assessment between experimental target data range obtained from wet lab practice and all trained network output range for the efficiency of trained networks for least deviation from target range revealed the output range of network 'trainrp' was closest to the empirical target range while least comparison was worked out from network 'traincgb' which had output range more than the target decided and ultimately showed meaningless result.

show abstract

“…Elongated shoots in the regenerating calluses were measured and compared with values simulated by the network. The mean error between the predicted and experimental shoot lengths was only 1.3 mm (Honda et al, 1997). Honda et al, 1997)…”

Section: Simulation Of Temperature Distribution Inside Culture Vesselsmentioning

confidence: 86%

“…The physical conditions during in vitro culture can be simulated with models such as those described above. Honda et al (1997) demonstrated a neural networkassisted estimation of shoot length in in vitro regenerated rice. Data for calculations were taken from digitized images of regenerated cultures.…”

Section: Simulation Of Temperature Distribution Inside Culture Vesselsmentioning

confidence: 99%

Neural modeling of plant tissue cultures: a review

Zielińska¹,

Kępczyńska²

2013

bta

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are widely used in science and technology, and have been successfully applied in plant tissue cultures. First of all, ANNs can simulate the growth of plants under different in vitro conditions. Their usefulness has been confirmed in the estimation of biomass in plant cell cultures and the length of shoots in vitro, in the classification of somatic embryos, evaluation of the physical conditions of an in vitro environment, and in the prediction of optimal conditions for in vitro culture to achieve maximum efficiency and productivity. Secondly, with the help of various types of neural models, in vitro-regenerated plants are sorted, respectively, to their quality and likeliness of further development. Thirdly, ANNs are capable of predicting plant behavior during in vitro rhizogenesis and subsequent acclimatization to ex vitro conditions. Several neural and neurofuzzy models for the aforementioned biological processes are reviewed in this paper. In addition, the fundamentals of neural modeling, namely the construction of ANNs, are presented and their flexibility and attractiveness are highlighted.

show abstract

Image analysis associated with a fuzzy neural network and estimation of shoot length of regenerated rice callus

Cited by 30 publications

References 5 publications

Estimation of the chlorophyll content of micropropagated potato plants using RGB based image analysis

Estimation of the chlorophyll content of micropropagated potato plants using RGB based image analysis

Efficiency of neural networks for prediction of in vitro culture conditions and inoculum properties for optimum productivity

Neural modeling of plant tissue cultures: a review

Contact Info

Product

Resources

About